diff --git a/README.es.md b/README.es.md
index 7a313b804..4ec1c5d53 100644
--- a/README.es.md
+++ b/README.es.md
@@ -81,31 +81,51 @@ Para detalles de despliegue, consulta la [Guía Enterprise](/documentation/exper
 
 ### Compatibilidad de arquitectura de modelos
 
-| Modelo | Parámetros | PEFT LoRA | Lycoris | Full-Rank | ControlNet | Cuantización | Flow Matching | Codificadores de texto |
-|--------|------------|-----------|---------|-----------|------------|--------------|---------------|------------------------|
-| **Stable Diffusion XL** | 3.5B | ✓ | ✓ | ✓ | ✓ | int8/nf4 | ✗ | CLIP-L/G |
-| **Stable Diffusion 3** | 2B-8B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L/G + T5-XXL |
-| **Flux.1** | 12B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL |
-| **Flux.2** | 32B | ✓ | ✓ | ✓* | ✗ | int8/fp8/nf4 | ✓ | Mistral-3 Small |
-| **Ideogram 4** | 9B | ✓ | ✓ | ✓* | ✗ | fp8/nf4 | ✓ | Qwen3-VL |
-| **ACE-Step** | 3.5B | ✓ | ✓ | ✓* | ✗ | int8 | ✓ | UMT5 |
-| **HeartMuLa** | 3B | ✓ | ✓ | ✓* | ✗ | int8 | ✗ | Ninguno |
-| **Chroma 1** | 8.9B | ✓ | ✓ | ✓* | ✗ | int8/fp8/nf4 | ✓ | T5-XXL |
-| **Auraflow** | 6.8B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | UMT5-XXL |
-| **PixArt Sigma** | 0.6B-0.9B | ✗ | ✓ | ✓ | ✓ | int8 | ✗ | T5-XXL |
-| **Sana** | 0.6B-4.8B | ✗ | ✓ | ✓ | ✗ | int8 | ✓ | Gemma2-2B |
-| **Lumina2** | 2B | ✓ | ✓ | ✓ | ✗ | int8 | ✓ | Gemma2 |
-| **Kwai Kolors** | 5B | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ChatGLM-6B |
-| **LTX Video** | 5B | ✓ | ✓ | ✓ | ✗ | int8/fp8 | ✓ | T5-XXL |
-| **LTX Video 2** | 19B | ✓ | ✓ | ✓* | ✗ | int8/fp8 | ✓ | Gemma3 |
-| **Wan Video** | 1.3B-14B | ✓ | ✓ | ✓* | ✗ | int8 | ✓ | UMT5 |
-| **HiDream** | 17B (8.5B MoE) | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL + Llama |
-| **Cosmos2** | 2B-14B | ✗ | ✓ | ✓ | ✗ | int8 | ✓ | T5-XXL |
-| **OmniGen** | 3.8B | ✓ | ✓ | ✓ | ✗ | int8/fp8 | ✓ | T5-XXL |
-| **Qwen Image** | 20B | ✓ | ✓ | ✓* | ✗ | int8/nf4 (req.) | ✓ | T5-XXL |
-| **SD 1.x/2.x (Legacy)** | 0.9B | ✓ | ✓ | ✓ | ✓ | int8/nf4 | ✗ | CLIP-L |
-
-*✓ = Compatible, ✗ = No compatible, * = Requiere DeepSpeed para entrenamiento full-rank*
+SimpleTuner es compatible con las siguientes familias de modelos. El soporte detallado de funciones de entrenamiento está en la [Guía Quickstart](/documentation/QUICKSTART.es.md).
+
+| Modelo | Parámetros | Licencia | Uso comercial |
+| --- | --- | --- | --- |
+| **ACE-Step** | 3.5B | Apache-2.0 | Sí |
+| **Anima** | No especificado | CircleStone Labs Non-Commercial License v1.2 | No (modelo); salidas permitidas |
+| **Auraflow** | 6B | Apache-2.0 | Sí |
+| **Boogu-Image** | No especificado | Apache-2.0 | Sí |
+| **Chroma 1** | 8.9B | Apache-2.0 | Sí |
+| **Cosmos2** | 2B-14B | NVIDIA Open Model License | Sí |
+| **Cosmos3** | 16B-65B | OpenMDW-1.1 | Sí |
+| **DeepFloyd IF** | 0.4B-4.3B stages | DeepFloyd IF License | Abandonware |
+| **ERNIE-Image** | No especificado | Apache-2.0 | Sí |
+| **Flux.1** | 8B-12B | Apache-2.0 (schnell); FLUX.1 [dev] Non-Commercial License (dev/Kontext) | Mixto por checkpoint |
+| **Flux.2** | 4B-32B | Apache-2.0 (klein 4B); FLUX Non-Commercial License (dev/klein 9B) | Mixto por checkpoint |
+| **HeartMuLa** | 3B | No especificada en SimpleTuner | Ver términos upstream |
+| **HiDream** | 17B (8.5B MoE) | MIT | Sí |
+| **Hunyuan Video** | 8.3B | AGPL-3.0 | Sí (copyleft) |
+| **Ideogram 4** | 9B | Ideogram 4 Non-Commercial | No |
+| **Kandinsky 5.0 Image** | 6B (lite) | MIT | Sí |
+| **Kandinsky 5.0 Video** | 2B lite, 19B pro | MIT | Sí |
+| **Kwai Kolors** | 2.7B | Apache-2.0 | Abandonware |
+| **Krea2** | No especificado | Krea 2 Community License | Sí (menos de $1M en ingresos; salvaguardas requeridas) |
+| **LongCat Image** | 6B | Apache-2.0 | Sí |
+| **LongCat Video** | 13.6B | MIT | Sí |
+| **LTX Video** | ~2.5B | Apache-2.0 | Sí |
+| **LTX Video 2** | 19B | Apache-2.0 | Sí |
+| **Lumina2** | 2B | Apache-2.0 | Sí |
+| **Mage-Flow** | 4B | MIT | Sí |
+| **OmniGen** | 3.8B | MIT | Sí |
+| **PixArt Sigma** | 0.6B-0.9B | OpenRAIL++ | Sí (restringido) |
+| **Qwen Image** | 20B | Apache-2.0 | Sí |
+| **Sana** | 0.6B-4.8B | Apache-2.0 | Sí |
+| **Sana Video** | 2B | Apache-2.0 | Sí |
+| **SD 1.x/2.x (Legacy)** | 0.9B | OpenRAIL++ | Sí (restringido) |
+| **Stable Diffusion 3** | 2B-8B | Stability AI Community License | Sí (menos de $1M en ingresos) |
+| **Stable Diffusion XL** | 3.5B | CreativeML OpenRAIL-M | Sí (restringido) |
+| **Stable Cascade (Stage C)** | 1B, 3.6B prior | No especificada en SimpleTuner | Abandonware |
+| **Wan Video** | 1.3B-14B | Apache-2.0 | Sí |
+| **Wan S2V** | 14B | Apache-2.0 | Sí |
+| **Z-Image** | 6B | Apache-2.0 | Sí |
+| **Z-Image Omni** | 6B | Apache-2.0 | Sí |
+| **ZLab I1** | 3B | MIT | Sí |
+
+*Los valores de licencia se toman de los helpers de modelos de SimpleTuner cuando están disponibles y de las tarjetas/licencias upstream para entradas que antes no estaban especificadas. `No especificada en SimpleTuner` significa que el helper no nombra una licencia y aquí no se resume ningún término upstream; revisa la tarjeta del modelo upstream antes de usarlo.*
 
 ### Técnicas avanzadas de entrenamiento
 
diff --git a/README.hi.md b/README.hi.md
index 77ff1b91c..699d5bb07 100644
--- a/README.hi.md
+++ b/README.hi.md
@@ -81,31 +81,51 @@ SimpleTuner एक पूर्ण मल्टी‑यूज़र प्र
 
 ### मॉडल आर्किटेक्चर समर्थन {#model-architecture-support}
 
-| मॉडल | पैरामीटर | PEFT LoRA | Lycoris | फुल-रैंक | ControlNet | क्वांटाइज़ेशन | फ्लो मैचिंग | टेक्स्ट एन्कोडर |
-|-------|------------|-----------|---------|-----------|------------|--------------|---------------|---------------|
-| **Stable Diffusion XL** | 3.5B | ✓ | ✓ | ✓ | ✓ | int8/nf4 | ✗ | CLIP-L/G |
-| **Stable Diffusion 3** | 2B-8B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L/G + T5-XXL |
-| **Flux.1** | 12B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL |
-| **Flux.2** | 32B | ✓ | ✓ | ✓* | ✗ | int8/fp8/nf4 | ✓ | Mistral-3 Small |
-| **Ideogram 4** | 9B | ✓ | ✓ | ✓* | ✗ | fp8/nf4 | ✓ | Qwen3-VL |
-| **ACE-Step** | 3.5B | ✓ | ✓ | ✓* | ✗ | int8 | ✓ | UMT5 |
-| **HeartMuLa** | 3B | ✓ | ✓ | ✓* | ✗ | int8 | ✗ | कोई नहीं |
-| **Chroma 1** | 8.9B | ✓ | ✓ | ✓* | ✗ | int8/fp8/nf4 | ✓ | T5-XXL |
-| **Auraflow** | 6.8B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | UMT5-XXL |
-| **PixArt Sigma** | 0.6B-0.9B | ✗ | ✓ | ✓ | ✓ | int8 | ✗ | T5-XXL |
-| **Sana** | 0.6B-4.8B | ✗ | ✓ | ✓ | ✗ | int8 | ✓ | Gemma2-2B |
-| **Lumina2** | 2B | ✓ | ✓ | ✓ | ✗ | int8 | ✓ | Gemma2 |
-| **Kwai Kolors** | 5B | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ChatGLM-6B |
-| **LTX Video** | 5B | ✓ | ✓ | ✓ | ✗ | int8/fp8 | ✓ | T5-XXL |
-| **LTX Video 2** | 19B | ✓ | ✓ | ✓* | ✗ | int8/fp8 | ✓ | Gemma3 |
-| **Wan Video** | 1.3B-14B | ✓ | ✓ | ✓* | ✗ | int8 | ✓ | UMT5 |
-| **HiDream** | 17B (8.5B MoE) | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL + Llama |
-| **Cosmos2** | 2B-14B | ✗ | ✓ | ✓ | ✗ | int8 | ✓ | T5-XXL |
-| **OmniGen** | 3.8B | ✓ | ✓ | ✓ | ✗ | int8/fp8 | ✓ | T5-XXL |
-| **Qwen Image** | 20B | ✓ | ✓ | ✓* | ✗ | int8/nf4 (req.) | ✓ | T5-XXL |
-| **SD 1.x/2.x (Legacy)** | 0.9B | ✓ | ✓ | ✓ | ✓ | int8/nf4 | ✗ | CLIP-L |
-
-*✓ = समर्थित, ✗ = समर्थित नहीं, * = फुल‑रैंक प्रशिक्षण के लिए DeepSpeed आवश्यक*
+SimpleTuner निम्नलिखित मॉडल families का समर्थन करता है। विस्तृत training feature समर्थन [Quickstart Guide](/documentation/QUICKSTART.hi.md) में है।
+
+| मॉडल | पैरामीटर | लाइसेंस | व्यावसायिक उपयोग |
+| --- | --- | --- | --- |
+| **ACE-Step** | 3.5B | Apache-2.0 | हाँ |
+| **Anima** | निर्दिष्ट नहीं | CircleStone Labs Non-Commercial License v1.2 | नहीं (मॉडल); outputs अनुमत |
+| **Auraflow** | 6B | Apache-2.0 | हाँ |
+| **Boogu-Image** | निर्दिष्ट नहीं | Apache-2.0 | हाँ |
+| **Chroma 1** | 8.9B | Apache-2.0 | हाँ |
+| **Cosmos2** | 2B-14B | NVIDIA Open Model License | हाँ |
+| **Cosmos3** | 16B-65B | OpenMDW-1.1 | हाँ |
+| **DeepFloyd IF** | 0.4B-4.3B stages | DeepFloyd IF License | Abandonware |
+| **ERNIE-Image** | निर्दिष्ट नहीं | Apache-2.0 | हाँ |
+| **Flux.1** | 8B-12B | Apache-2.0 (schnell); FLUX.1 [dev] Non-Commercial License (dev/Kontext) | checkpoint के अनुसार mixed |
+| **Flux.2** | 4B-32B | Apache-2.0 (klein 4B); FLUX Non-Commercial License (dev/klein 9B) | checkpoint के अनुसार mixed |
+| **HeartMuLa** | 3B | SimpleTuner में निर्दिष्ट नहीं | upstream शर्तें देखें |
+| **HiDream** | 17B (8.5B MoE) | MIT | हाँ |
+| **Hunyuan Video** | 8.3B | AGPL-3.0 | हाँ (copyleft) |
+| **Ideogram 4** | 9B | Ideogram 4 Non-Commercial | नहीं |
+| **Kandinsky 5.0 Image** | 6B (lite) | MIT | हाँ |
+| **Kandinsky 5.0 Video** | 2B lite, 19B pro | MIT | हाँ |
+| **Kwai Kolors** | 2.7B | Apache-2.0 | Abandonware |
+| **Krea2** | निर्दिष्ट नहीं | Krea 2 Community License | हाँ ($1M से कम राजस्व; safeguards आवश्यक) |
+| **LongCat Image** | 6B | Apache-2.0 | हाँ |
+| **LongCat Video** | 13.6B | MIT | हाँ |
+| **LTX Video** | ~2.5B | Apache-2.0 | हाँ |
+| **LTX Video 2** | 19B | Apache-2.0 | हाँ |
+| **Lumina2** | 2B | Apache-2.0 | हाँ |
+| **Mage-Flow** | 4B | MIT | हाँ |
+| **OmniGen** | 3.8B | MIT | हाँ |
+| **PixArt Sigma** | 0.6B-0.9B | OpenRAIL++ | हाँ (restricted) |
+| **Qwen Image** | 20B | Apache-2.0 | हाँ |
+| **Sana** | 0.6B-4.8B | Apache-2.0 | हाँ |
+| **Sana Video** | 2B | Apache-2.0 | हाँ |
+| **SD 1.x/2.x (Legacy)** | 0.9B | OpenRAIL++ | हाँ (restricted) |
+| **Stable Diffusion 3** | 2B-8B | Stability AI Community License | हाँ ($1M से कम राजस्व) |
+| **Stable Diffusion XL** | 3.5B | CreativeML OpenRAIL-M | हाँ (restricted) |
+| **Stable Cascade (Stage C)** | 1B, 3.6B prior | SimpleTuner में निर्दिष्ट नहीं | Abandonware |
+| **Wan Video** | 1.3B-14B | Apache-2.0 | हाँ |
+| **Wan S2V** | 14B | Apache-2.0 | हाँ |
+| **Z-Image** | 6B | Apache-2.0 | हाँ |
+| **Z-Image Omni** | 6B | Apache-2.0 | हाँ |
+| **ZLab I1** | 3B | MIT | हाँ |
+
+*लाइसेंस मान उपलब्ध होने पर SimpleTuner model helpers से लिए गए हैं, और पहले अनिर्दिष्ट entries के लिए upstream model cards/licenses से। `SimpleTuner में निर्दिष्ट नहीं` का अर्थ है कि helper कोई license name नहीं देता और यहां upstream terms का सार नहीं दिया गया है; उपयोग से पहले upstream model card देखें.*
 
 ### उन्नत प्रशिक्षण तकनीकें {#advanced-training-techniques}
 
diff --git a/README.ja.md b/README.ja.md
index 4fa0b109c..c68739a3a 100644
--- a/README.ja.md
+++ b/README.ja.md
@@ -81,31 +81,51 @@ SimpleTunerには、エンタープライズグレードの機能を備えた完
 
 ### モデルアーキテクチャサポート
 
-| モデル | パラメータ数 | PEFT LoRA | Lycoris | Full-Rank | ControlNet | 量子化 | Flow Matching | テキストエンコーダー |
-|-------|------------|-----------|---------|-----------|------------|--------------|---------------|---------------|
-| **Stable Diffusion XL** | 3.5B | ✓ | ✓ | ✓ | ✓ | int8/nf4 | ✗ | CLIP-L/G |
-| **Stable Diffusion 3** | 2B-8B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L/G + T5-XXL |
-| **Flux.1** | 12B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL |
-| **Flux.2** | 32B | ✓ | ✓ | ✓* | ✗ | int8/fp8/nf4 | ✓ | Mistral-3 Small |
-| **Ideogram 4** | 9B | ✓ | ✓ | ✓* | ✗ | fp8/nf4 | ✓ | Qwen3-VL |
-| **ACE-Step** | 3.5B | ✓ | ✓ | ✓* | ✗ | int8 | ✓ | UMT5 |
-| **HeartMuLa** | 3B | ✓ | ✓ | ✓* | ✗ | int8 | ✗ | なし |
-| **Chroma 1** | 8.9B | ✓ | ✓ | ✓* | ✗ | int8/fp8/nf4 | ✓ | T5-XXL |
-| **Auraflow** | 6.8B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | UMT5-XXL |
-| **PixArt Sigma** | 0.6B-0.9B | ✗ | ✓ | ✓ | ✓ | int8 | ✗ | T5-XXL |
-| **Sana** | 0.6B-4.8B | ✗ | ✓ | ✓ | ✗ | int8 | ✓ | Gemma2-2B |
-| **Lumina2** | 2B | ✓ | ✓ | ✓ | ✗ | int8 | ✓ | Gemma2 |
-| **Kwai Kolors** | 5B | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ChatGLM-6B |
-| **LTX Video** | 5B | ✓ | ✓ | ✓ | ✗ | int8/fp8 | ✓ | T5-XXL |
-| **LTX Video 2** | 19B | ✓ | ✓ | ✓* | ✗ | int8/fp8 | ✓ | Gemma3 |
-| **Wan Video** | 1.3B-14B | ✓ | ✓ | ✓* | ✗ | int8 | ✓ | UMT5 |
-| **HiDream** | 17B (8.5B MoE) | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL + Llama |
-| **Cosmos2** | 2B-14B | ✗ | ✓ | ✓ | ✗ | int8 | ✓ | T5-XXL |
-| **OmniGen** | 3.8B | ✓ | ✓ | ✓ | ✗ | int8/fp8 | ✓ | T5-XXL |
-| **Qwen Image** | 20B | ✓ | ✓ | ✓* | ✗ | int8/nf4 (req.) | ✓ | T5-XXL |
-| **SD 1.x/2.x (Legacy)** | 0.9B | ✓ | ✓ | ✓ | ✓ | int8/nf4 | ✗ | CLIP-L |
-
-*✓ = サポート, ✗ = 非サポート, * = Full-rankトレーニングにDeepSpeedが必要*
+SimpleTunerは以下のモデルファミリーをサポートしています。詳細なトレーニング機能の対応状況は[Quickstartガイド](/documentation/QUICKSTART.ja.md)を参照してください。
+
+| モデル | パラメータ数 | ライセンス | 商用利用 |
+| --- | --- | --- | --- |
+| **ACE-Step** | 3.5B | Apache-2.0 | 可 |
+| **Anima** | 未指定 | CircleStone Labs Non-Commercial License v1.2 | 不可（モデル）；出力は可 |
+| **Auraflow** | 6B | Apache-2.0 | 可 |
+| **Boogu-Image** | 未指定 | Apache-2.0 | 可 |
+| **Chroma 1** | 8.9B | Apache-2.0 | 可 |
+| **Cosmos2** | 2B-14B | NVIDIA Open Model License | 可 |
+| **Cosmos3** | 16B-65B | OpenMDW-1.1 | 可 |
+| **DeepFloyd IF** | 0.4B-4.3B stages | DeepFloyd IF License | Abandonware |
+| **ERNIE-Image** | 未指定 | Apache-2.0 | 可 |
+| **Flux.1** | 8B-12B | Apache-2.0 (schnell); FLUX.1 [dev] Non-Commercial License (dev/Kontext) | checkpointごとに異なる |
+| **Flux.2** | 4B-32B | Apache-2.0 (klein 4B); FLUX Non-Commercial License (dev/klein 9B) | checkpointごとに異なる |
+| **HeartMuLa** | 3B | SimpleTunerでは未指定 | 上流の条件を確認 |
+| **HiDream** | 17B (8.5B MoE) | MIT | 可 |
+| **Hunyuan Video** | 8.3B | AGPL-3.0 | 可（copyleft） |
+| **Ideogram 4** | 9B | Ideogram 4 Non-Commercial | 不可 |
+| **Kandinsky 5.0 Image** | 6B (lite) | MIT | 可 |
+| **Kandinsky 5.0 Video** | 2B lite, 19B pro | MIT | 可 |
+| **Kwai Kolors** | 2.7B | Apache-2.0 | Abandonware |
+| **Krea2** | 未指定 | Krea 2 Community License | 可（年収100万米ドル未満；安全対策必須） |
+| **LongCat Image** | 6B | Apache-2.0 | 可 |
+| **LongCat Video** | 13.6B | MIT | 可 |
+| **LTX Video** | ~2.5B | Apache-2.0 | 可 |
+| **LTX Video 2** | 19B | Apache-2.0 | 可 |
+| **Lumina2** | 2B | Apache-2.0 | 可 |
+| **Mage-Flow** | 4B | MIT | 可 |
+| **OmniGen** | 3.8B | MIT | 可 |
+| **PixArt Sigma** | 0.6B-0.9B | OpenRAIL++ | 可（制限あり） |
+| **Qwen Image** | 20B | Apache-2.0 | 可 |
+| **Sana** | 0.6B-4.8B | Apache-2.0 | 可 |
+| **Sana Video** | 2B | Apache-2.0 | 可 |
+| **SD 1.x/2.x (Legacy)** | 0.9B | OpenRAIL++ | 可（制限あり） |
+| **Stable Diffusion 3** | 2B-8B | Stability AI Community License | 可（年収100万米ドル未満） |
+| **Stable Diffusion XL** | 3.5B | CreativeML OpenRAIL-M | 可（制限あり） |
+| **Stable Cascade (Stage C)** | 1B, 3.6B prior | SimpleTunerでは未指定 | Abandonware |
+| **Wan Video** | 1.3B-14B | Apache-2.0 | 可 |
+| **Wan S2V** | 14B | Apache-2.0 | 可 |
+| **Z-Image** | 6B | Apache-2.0 | 可 |
+| **Z-Image Omni** | 6B | Apache-2.0 | 可 |
+| **ZLab I1** | 3B | MIT | 可 |
+
+*ライセンス値は、利用可能な場合はSimpleTunerのモデルヘルパーから、以前未指定だった項目は上流のモデルカード/ライセンスから取得しています。`SimpleTunerでは未指定`は、ヘルパーがライセンス名を持たず、ここでも上流条件を要約していないことを意味します。使用前に上流モデルカードを確認してください。*
 
 ### 高度なトレーニング技術
 
diff --git a/README.md b/README.md
index 9e9c66558..3a0e88972 100644
--- a/README.md
+++ b/README.md
@@ -81,75 +81,51 @@ For deployment details, see the [Enterprise Guide](/documentation/experimental/s
 
 ### Model Architecture Support
 
-| Model | Parameters | PEFT LoRA | Lycoris | Full-Rank | ControlNet | Ref Inputs | Quantization | Flow Matching | Text Encoders | License | Allows commercial use |
-| ------- | ------------ | ----------- | --------- | ----------- | ------------ | ------------ | -------------- | --------------- | --------------- | ------- | :---: |
-| **Stable Diffusion XL** | 3.5B | ✓ | ✓ | ✓ | ✓ | ✗ | int8/nf4 | ✗ | CLIP-L/G | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Conditions apply<sup>1</sup> |
-| **Stable Diffusion 3** | 2B-8B | ✓ | ✓ | ✓* | ✓ | ✗ | int8/fp8/nf4 | ✓ | CLIP-L/G + T5-XXL | [Stability AI Community](https://stability.ai/license) | Conditions apply<sup>2</sup> |
-| **Flux.1** | 12B | ✓ | ✓ | ✓* | ✓ | ✓ (Kontext) | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Conditions apply<sup>3</sup> |
-| **Flux.2** | 32B | ✓ | ✓ | ✓* | ✗ | ✓ opt | int8/fp8/nf4 | ✓ | Mistral-3 Small | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Conditions apply<sup>4</sup> |
-| **Ideogram 4** | 9B | ✓ | ✓ | ✓* | ✗ | ✗ | fp8/nf4 | ✓ | Qwen3-VL | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | No<sup>5</sup> |
-| **Z-Image** | 6B | ✓ | ✓ | ✓* | ✗ | ✗ | int8 | ✓ | Qwen3 4B | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **Z-Image Omni** | 6B | ✓ | ✓ | ✓* | ✗ | ✓ edit | int8/fp8/nf4 | ✓ | Qwen3 4B | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **Krea2** | - | ✓ | ✓ | ✓* | ✗ | ✓ opt | int8 | ✓ | Qwen3-VL | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | Conditions apply<sup>6</sup> |
-| **Anima** | 2B | ✓ | ✓ | ✓* | ✗ | ✗ | not recommended | ✓ | Qwen3 0.6B | [CircleStone Labs Non-Commercial](https://huggingface.co/circlestone-labs/Anima/blob/main/LICENSE.md) | No<sup>5</sup> |
-| **Mage-Flow** | 4B | ✓ | ✓ | ✓* | ✗ | ✓ edit | int8/fp8 | ✓ | Qwen3-VL | [MIT](https://opensource.org/license/mit) | Yes |
-| **Boogu-Image** | - | ✓ | ✓ | ✓* | ✗ | ✓ edit | fp8 | ✓ | Qwen3-VL | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **zlab i1** | 3B | ✓ | ✓ | ✓ | ✗ | ✗ | int8 | ✓ | T5Gemma 2B | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | Conditions apply<sup>12</sup> |
-| **ERNIE-Image** | - | ✓ | ✓ | ✓* | ✗ | ✗ | int8 | ✓ | ERNIE | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **ACE-Step** | 3.5B | ✓ | ✓ | ✓* | ✗ | ✗ | int8 | ✓ | UMT5 | [Apache-2.0](https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B) / [MIT](https://huggingface.co/ACE-Step/Ace-Step1.5) | Yes |
-| **HeartMuLa** | 3B | ✓ | ✓ | ✓* | ✗ | ✗ | int8 | ✗ | None | [Apache-2.0](https://huggingface.co/HeartMuLa/HeartMuLa-oss-3B) | Yes |
-| **Chroma 1** | 8.9B | ✓ | ✓ | ✓* | ✗ | ✗ | int8/fp8/nf4 | ✓ | T5-XXL | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **Auraflow** | 6.8B | ✓ | ✓ | ✓* | ✓ | ✗ | int8/fp8/nf4 | ✓ | UMT5-XXL | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) / [Pony License](https://huggingface.co/purplesmartai/pony-v7-base/blob/main/LICENSE) | Conditions apply<sup>8</sup> |
-| **PixArt Sigma** | 0.6B-0.9B | ✗ | ✓ | ✓ | ✓ | ✗ | int8 | ✗ | T5-XXL | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Conditions apply<sup>1</sup> |
-| **Sana** | 0.6B-4.8B | ✗ | ✓ | ✓ | ✗ | ✗ | int8 | ✓ | Gemma2-2B | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **Lumina2** | 2B | ✓ | ✓ | ✓ | ✗ | ✗ | int8 | ✓ | Gemma2 | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **Kwai Kolors** | 5B | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ✗ | ChatGLM-6B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Conditions apply<sup>7</sup> |
-| **LTX Video** | 5B | ✓ | ✓ | ✓ | ✗ | ✓ I2V | int8/fp8 | ✓ | T5-XXL | [LTX Video OpenRAIL-M](https://huggingface.co/Lightricks/LTX-Video-0.9.5/blob/main/ltx-video-2b-v0.9.5.license.txt) | Conditions apply<sup>10</sup> |
-| **LTX Video 2** | 19B | ✓ | ✓ | ✓* | ✗ | ✓ opt | int8/fp8 | ✓ | Gemma3 | [LTX-2 Community](https://ltx.io/model/license) | Conditions apply<sup>10</sup> |
-| **Wan Video** | 1.3B-14B | ✓ | ✓ | ✓* | ✗ | ✗ | int8 | ✓ | UMT5 | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **Wan S2V** | 14B | ✓ | ✓ | ✓* | ✗ | audio req | int8 | ✓ | UMT5 | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **HiDream** | 17B (8.5B MoE) | ✓ | ✓ | ✓* | ✓ | ✗ | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL + Llama | [MIT](https://opensource.org/license/mit) | Yes |
-| **Cosmos2** | 2B-14B | ✗ | ✓ | ✓ | ✗ | ✗ | int8 | ✓ | T5-XXL | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) | Yes<sup>9</sup> |
-| **Cosmos3** | 4B-65B | ✓ | ✓ | ✓* | ✗ | ✓ I2V/audio | no_change first | ✓ | built-in | [OpenMDW 1.1](https://github.com/OpenMDW/openmdw/blob/main/1.1/LICENSE.OpenMDW-1.1) | Yes |
-| **Hunyuan Video 1.5** | 8.3B | ✓ | ✓ | ✓* | ✗ | ✓ I2V | int8 | ✓ | Hunyuan LLM + CLIP | [Tencent Hunyuan Community](https://huggingface.co/tencent/HunyuanVideo-1.5/blob/main/LICENSE) | Conditions apply<sup>11</sup> |
-| **SanaVideo** | 2B | ✓ | ✓ | ✓* | ✗ | ✗ | int8/fp8 | ✓ | Gemma2 | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **Kandinsky 5.0 Image** | 6B | ✓ | ✓ | ✓* | ✗ | ✓ I2I | int8 | ✓ | Qwen2.5-VL | [MIT](https://opensource.org/license/mit) | Yes |
-| **Kandinsky 5.0 Video** | 2B-19B | ✓ | ✓ | ✓* | ✗ | ✓ I2V | int8 | ✓ | Qwen2.5-VL | [MIT](https://opensource.org/license/mit) | Yes |
-| **LongCat-Image** | 6B | ✓ | ✓ | ✓* | ✗ | ✓ edit | int8/fp8 | ✓ | Qwen2.5-VL | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **LongCat-Video** | 13.6B | ✓ | ✓ | ✓* | ✗ | ✓ I2V/edit | int8/fp8 | ✓ | Qwen2.5-VL | [MIT](https://opensource.org/license/mit) | Yes |
-| **OmniGen** | 3.8B | ✓ | ✓ | ✓ | ✗ | ✗ | int8/fp8 | ✓ | T5-XXL | [MIT](https://opensource.org/license/mit) | Yes |
-| **Qwen Image** | 20B | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) | int8/nf4 (req.) | ✓ | T5-XXL | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes |
-| **DeepFloyd IF** | 0.4B-4.3B | ✓ | ✓ | ✓ | ✗ | ✓ SR | int8/fp8 | ✗ | T5-XXL | [DeepFloyd IF License](https://huggingface.co/DeepFloyd/IF-I-M-v1.0) | No<sup>5</sup> |
-| **Stable Cascade (C)** | 1B, 3.6B prior | ✓ | ✓ | ✓* | ✗ | ✗ | not supported | ✗ | CLIP-bigG | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | No<sup>5</sup> |
-| **SD 1.x/2.x (Legacy)** | 0.9B | ✓ | ✓ | ✓ | ✓ | ✗ | int8/nf4 | ✗ | CLIP-L | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Conditions apply<sup>1</sup> |
-
-*Commercial-use status covers model weights, derivative checkpoints, fine-tunes, and hosted model use. Generated-output rights can differ; read the linked license text before commercial deployment.*
-
-<sup>1</sup> OpenRAIL-style licenses generally permit commercial use with usage restrictions that remain attached to the model and derivatives.
-
-<sup>2</sup> Stability AI Community License is available for qualifying users below the revenue threshold; larger commercial use needs Stability enterprise terms.
-
-<sup>3</sup> Flux.1 varies by flavour: Schnell and LibreFlux are Apache-2.0, while Dev, Krea, and Kontext use BFL non-commercial terms; review FluxBooru upstream metadata before commercial use.
-
-<sup>4</sup> Flux.2 varies by flavour: Klein 4B is Apache-2.0, while Dev and Klein 9B use BFL non-commercial terms.
-
-<sup>5</sup> Public non-commercial model terms do not permit commercial use of weights, derivative checkpoints, or hosted model services without a separate license.
-
-<sup>6</sup> Krea 2 Community License permits commercial use only under its revenue and safety/filtering requirements; otherwise an enterprise license is required.
-
-<sup>7</sup> Kolors commercial model or derivative use requires applying for and receiving explicit permission from the licensor.
-
-<sup>8</sup> AuraFlow supports Apache-2.0 upstream flavours and a Pony flavour with a separate custom license; check the selected flavour.
-
-<sup>9</sup> NVIDIA Open Model License permits commercial use but includes agreement, acceptable-use, and export-control terms.
-
-<sup>10</sup> LTX Video 0.9.5 uses OpenRAIL-M; LTX Video 2 uses LTX community terms with a revenue threshold for commercial use.
-
-<sup>11</sup> Tencent Hunyuan Community License includes territorial exclusions and a commercial threshold for very large services.
-
-<sup>12</sup> This mirror publishes `license: other` without a standard license text; review upstream terms before commercial use.
-
-*✓ = Supported, ✗ = Not supported, * = Requires DeepSpeed for full-rank training, Ref Inputs marks existing reference/edit/I2V conditioning paths only*
+SimpleTuner supports the following model families. Detailed training feature support lives in the [Quickstart Guide](/documentation/QUICKSTART.md#feature-compatibility).
+
+| Model | Parameters | License | Commercial use |
+| --- | --- | --- | --- |
+| **ACE-Step** | 3.5B | Apache-2.0 | Yes |
+| **Anima** | Not specified | CircleStone Labs Non-Commercial License v1.2 | No (model); outputs allowed |
+| **Auraflow** | 6B | Apache-2.0 | Yes |
+| **Boogu-Image** | Not specified | Apache-2.0 | Yes |
+| **Chroma 1** | 8.9B | Apache-2.0 | Yes |
+| **Cosmos2** | 2B-14B | NVIDIA Open Model License | Yes |
+| **Cosmos3** | 16B-65B | OpenMDW-1.1 | Yes |
+| **DeepFloyd IF** | 0.4B-4.3B stages | DeepFloyd IF License | Abandonware |
+| **ERNIE-Image** | Not specified | Apache-2.0 | Yes |
+| **Flux.1** | 8B-12B | Apache-2.0 (schnell); FLUX.1 [dev] Non-Commercial License (dev/Kontext) | Mixed by checkpoint |
+| **Flux.2** | 4B-32B | Apache-2.0 (klein 4B); FLUX Non-Commercial License (dev/klein 9B) | Mixed by checkpoint |
+| **HeartMuLa** | 3B | Not specified in SimpleTuner | See upstream terms |
+| **HiDream** | 17B (8.5B MoE) | MIT | Yes |
+| **Hunyuan Video** | 8.3B | AGPL-3.0 | Yes (copyleft) |
+| **Ideogram 4** | 9B | Ideogram 4 Non-Commercial | No |
+| **Kandinsky 5.0 Image** | 6B (lite) | MIT | Yes |
+| **Kandinsky 5.0 Video** | 2B lite, 19B pro | MIT | Yes |
+| **Kwai Kolors** | 2.7B | Apache-2.0 | Abandonware |
+| **Krea2** | Not specified | Krea 2 Community License | Yes (under $1M revenue; safeguards required) |
+| **LongCat Image** | 6B | Apache-2.0 | Yes |
+| **LongCat Video** | 13.6B | MIT | Yes |
+| **LTX Video** | ~2.5B | Apache-2.0 | Yes |
+| **LTX Video 2** | 19B | Apache-2.0 | Yes |
+| **Lumina2** | 2B | Apache-2.0 | Yes |
+| **Mage-Flow** | 4B | MIT | Yes |
+| **OmniGen** | 3.8B | MIT | Yes |
+| **PixArt Sigma** | 0.6B-0.9B | OpenRAIL++ | Yes (restricted) |
+| **Qwen Image** | 20B | Apache-2.0 | Yes |
+| **Sana** | 0.6B-4.8B | Apache-2.0 | Yes |
+| **Sana Video** | 2B | Apache-2.0 | Yes |
+| **SD 1.x/2.x (Legacy)** | 0.9B | OpenRAIL++ | Yes (restricted) |
+| **Stable Diffusion 3** | 2B-8B | Stability AI Community License | Yes (under $1M revenue) |
+| **Stable Diffusion XL** | 3.5B | CreativeML OpenRAIL-M | Yes (restricted) |
+| **Stable Cascade (Stage C)** | 1B, 3.6B prior | Not specified in SimpleTuner | Abandonware |
+| **Wan Video** | 1.3B-14B | Apache-2.0 | Yes |
+| **Wan S2V** | 14B | Apache-2.0 | Yes |
+| **Z-Image** | 6B | Apache-2.0 | Yes |
+| **Z-Image Omni** | 6B | Apache-2.0 | Yes |
+| **ZLab I1** | 3B | MIT | Yes |
+
+*License values are taken from SimpleTuner model helpers when available and upstream model cards/licenses for entries that were previously unspecified. `Not specified in SimpleTuner` means the helper does not name a license and no upstream term is summarized here; check the upstream model card before use.*
 
 ### Advanced Training Techniques
 
diff --git a/README.pt-BR.md b/README.pt-BR.md
index 19b7ca412..a4ccf22aa 100644
--- a/README.pt-BR.md
+++ b/README.pt-BR.md
@@ -81,31 +81,51 @@ Para detalhes de deploy, veja o [guia enterprise](/documentation/experimental/se
 
 ### Suporte a arquitetura de modelos
 
-| Modelo | Parametros | PEFT LoRA | Lycoris | Full-Rank | ControlNet | Quantizacao | Flow Matching | Text Encoders |
-|-------|------------|-----------|---------|-----------|------------|--------------|---------------|---------------|
-| **Stable Diffusion XL** | 3.5B | ✓ | ✓ | ✓ | ✓ | int8/nf4 | ✗ | CLIP-L/G |
-| **Stable Diffusion 3** | 2B-8B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L/G + T5-XXL |
-| **Flux.1** | 12B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL |
-| **Flux.2** | 32B | ✓ | ✓ | ✓* | ✗ | int8/fp8/nf4 | ✓ | Mistral-3 Small |
-| **Ideogram 4** | 9B | ✓ | ✓ | ✓* | ✗ | fp8/nf4 | ✓ | Qwen3-VL |
-| **ACE-Step** | 3.5B | ✓ | ✓ | ✓* | ✗ | int8 | ✓ | UMT5 |
-| **HeartMuLa** | 3B | ✓ | ✓ | ✓* | ✗ | int8 | ✗ | Nenhum |
-| **Chroma 1** | 8.9B | ✓ | ✓ | ✓* | ✗ | int8/fp8/nf4 | ✓ | T5-XXL |
-| **Auraflow** | 6.8B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | UMT5-XXL |
-| **PixArt Sigma** | 0.6B-0.9B | ✗ | ✓ | ✓ | ✓ | int8 | ✗ | T5-XXL |
-| **Sana** | 0.6B-4.8B | ✗ | ✓ | ✓ | ✗ | int8 | ✓ | Gemma2-2B |
-| **Lumina2** | 2B | ✓ | ✓ | ✓ | ✗ | int8 | ✓ | Gemma2 |
-| **Kwai Kolors** | 5B | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ChatGLM-6B |
-| **LTX Video** | 5B | ✓ | ✓ | ✓ | ✗ | int8/fp8 | ✓ | T5-XXL |
-| **LTX Video 2** | 19B | ✓ | ✓ | ✓* | ✗ | int8/fp8 | ✓ | Gemma3 |
-| **Wan Video** | 1.3B-14B | ✓ | ✓ | ✓* | ✗ | int8 | ✓ | UMT5 |
-| **HiDream** | 17B (8.5B MoE) | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL + Llama |
-| **Cosmos2** | 2B-14B | ✗ | ✓ | ✓ | ✗ | int8 | ✓ | T5-XXL |
-| **OmniGen** | 3.8B | ✓ | ✓ | ✓ | ✗ | int8/fp8 | ✓ | T5-XXL |
-| **Qwen Image** | 20B | ✓ | ✓ | ✓* | ✗ | int8/nf4 (req.) | ✓ | T5-XXL |
-| **SD 1.x/2.x (Legacy)** | 0.9B | ✓ | ✓ | ✓ | ✓ | int8/nf4 | ✗ | CLIP-L |
-
-*✓ = Suportado, ✗ = Nao suportado, * = Requer DeepSpeed para treino full-rank*
+SimpleTuner suporta as seguintes familias de modelos. O suporte detalhado a recursos de treinamento fica no [guia Quickstart](/documentation/QUICKSTART.pt-BR.md).
+
+| Modelo | Parametros | Licenca | Uso comercial |
+| --- | --- | --- | --- |
+| **ACE-Step** | 3.5B | Apache-2.0 | Sim |
+| **Anima** | Nao especificado | CircleStone Labs Non-Commercial License v1.2 | Nao (modelo); outputs permitidos |
+| **Auraflow** | 6B | Apache-2.0 | Sim |
+| **Boogu-Image** | Nao especificado | Apache-2.0 | Sim |
+| **Chroma 1** | 8.9B | Apache-2.0 | Sim |
+| **Cosmos2** | 2B-14B | NVIDIA Open Model License | Sim |
+| **Cosmos3** | 16B-65B | OpenMDW-1.1 | Sim |
+| **DeepFloyd IF** | 0.4B-4.3B stages | DeepFloyd IF License | Abandonware |
+| **ERNIE-Image** | Nao especificado | Apache-2.0 | Sim |
+| **Flux.1** | 8B-12B | Apache-2.0 (schnell); FLUX.1 [dev] Non-Commercial License (dev/Kontext) | Misto por checkpoint |
+| **Flux.2** | 4B-32B | Apache-2.0 (klein 4B); FLUX Non-Commercial License (dev/klein 9B) | Misto por checkpoint |
+| **HeartMuLa** | 3B | Nao especificada no SimpleTuner | Ver termos upstream |
+| **HiDream** | 17B (8.5B MoE) | MIT | Sim |
+| **Hunyuan Video** | 8.3B | AGPL-3.0 | Sim (copyleft) |
+| **Ideogram 4** | 9B | Ideogram 4 Non-Commercial | Nao |
+| **Kandinsky 5.0 Image** | 6B (lite) | MIT | Sim |
+| **Kandinsky 5.0 Video** | 2B lite, 19B pro | MIT | Sim |
+| **Kwai Kolors** | 2.7B | Apache-2.0 | Abandonware |
+| **Krea2** | Nao especificado | Krea 2 Community License | Sim (menos de $1M em receita; salvaguardas exigidas) |
+| **LongCat Image** | 6B | Apache-2.0 | Sim |
+| **LongCat Video** | 13.6B | MIT | Sim |
+| **LTX Video** | ~2.5B | Apache-2.0 | Sim |
+| **LTX Video 2** | 19B | Apache-2.0 | Sim |
+| **Lumina2** | 2B | Apache-2.0 | Sim |
+| **Mage-Flow** | 4B | MIT | Sim |
+| **OmniGen** | 3.8B | MIT | Sim |
+| **PixArt Sigma** | 0.6B-0.9B | OpenRAIL++ | Sim (restrito) |
+| **Qwen Image** | 20B | Apache-2.0 | Sim |
+| **Sana** | 0.6B-4.8B | Apache-2.0 | Sim |
+| **Sana Video** | 2B | Apache-2.0 | Sim |
+| **SD 1.x/2.x (Legacy)** | 0.9B | OpenRAIL++ | Sim (restrito) |
+| **Stable Diffusion 3** | 2B-8B | Stability AI Community License | Sim (menos de $1M em receita) |
+| **Stable Diffusion XL** | 3.5B | CreativeML OpenRAIL-M | Sim (restrito) |
+| **Stable Cascade (Stage C)** | 1B, 3.6B prior | Nao especificada no SimpleTuner | Abandonware |
+| **Wan Video** | 1.3B-14B | Apache-2.0 | Sim |
+| **Wan S2V** | 14B | Apache-2.0 | Sim |
+| **Z-Image** | 6B | Apache-2.0 | Sim |
+| **Z-Image Omni** | 6B | Apache-2.0 | Sim |
+| **ZLab I1** | 3B | MIT | Sim |
+
+*Os valores de licenca vem dos model helpers do SimpleTuner quando disponiveis e dos model cards/licencas upstream para entradas que antes nao estavam especificadas. `Nao especificada no SimpleTuner` significa que o helper nao informa uma licenca e nenhum termo upstream esta resumido aqui; verifique o model card upstream antes de usar.*
 
 ### Tecnicas avancadas de treinamento
 
diff --git a/README.zh.md b/README.zh.md
index 7e4995b63..e1ce18596 100644
--- a/README.zh.md
+++ b/README.zh.md
@@ -81,31 +81,51 @@ SimpleTuner 包含完整的多用户训练平台，具有企业级功能——**
 
 ### 模型架构支持
 
-| 模型 | 参数量 | PEFT LoRA | Lycoris | 全秩 | ControlNet | 量化 | Flow Matching | 文本编码器 |
-|-------|------------|-----------|---------|-----------|------------|--------------|---------------|---------------|
-| **Stable Diffusion XL** | 3.5B | ✓ | ✓ | ✓ | ✓ | int8/nf4 | ✗ | CLIP-L/G |
-| **Stable Diffusion 3** | 2B-8B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L/G + T5-XXL |
-| **Flux.1** | 12B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL |
-| **Flux.2** | 32B | ✓ | ✓ | ✓* | ✗ | int8/fp8/nf4 | ✓ | Mistral-3 Small |
-| **Ideogram 4** | 9B | ✓ | ✓ | ✓* | ✗ | fp8/nf4 | ✓ | Qwen3-VL |
-| **ACE-Step** | 3.5B | ✓ | ✓ | ✓* | ✗ | int8 | ✓ | UMT5 |
-| **HeartMuLa** | 3B | ✓ | ✓ | ✓* | ✗ | int8 | ✗ | 无 |
-| **Chroma 1** | 8.9B | ✓ | ✓ | ✓* | ✗ | int8/fp8/nf4 | ✓ | T5-XXL |
-| **Auraflow** | 6.8B | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | UMT5-XXL |
-| **PixArt Sigma** | 0.6B-0.9B | ✗ | ✓ | ✓ | ✓ | int8 | ✗ | T5-XXL |
-| **Sana** | 0.6B-4.8B | ✗ | ✓ | ✓ | ✗ | int8 | ✓ | Gemma2-2B |
-| **Lumina2** | 2B | ✓ | ✓ | ✓ | ✗ | int8 | ✓ | Gemma2 |
-| **Kwai Kolors** | 5B | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ChatGLM-6B |
-| **LTX Video** | 5B | ✓ | ✓ | ✓ | ✗ | int8/fp8 | ✓ | T5-XXL |
-| **LTX Video 2** | 19B | ✓ | ✓ | ✓* | ✗ | int8/fp8 | ✓ | Gemma3 |
-| **Wan Video** | 1.3B-14B | ✓ | ✓ | ✓* | ✗ | int8 | ✓ | UMT5 |
-| **HiDream** | 17B (8.5B MoE) | ✓ | ✓ | ✓* | ✓ | int8/fp8/nf4 | ✓ | CLIP-L + T5-XXL + Llama |
-| **Cosmos2** | 2B-14B | ✗ | ✓ | ✓ | ✗ | int8 | ✓ | T5-XXL |
-| **OmniGen** | 3.8B | ✓ | ✓ | ✓ | ✗ | int8/fp8 | ✓ | T5-XXL |
-| **Qwen Image** | 20B | ✓ | ✓ | ✓* | ✗ | int8/nf4（必需） | ✓ | T5-XXL |
-| **SD 1.x/2.x（旧版）** | 0.9B | ✓ | ✓ | ✓ | ✓ | int8/nf4 | ✗ | CLIP-L |
-
-*✓ = 支持，✗ = 不支持，* = 全秩训练需要 DeepSpeed*
+SimpleTuner 支持以下模型系列。详细的训练功能支持请参阅[快速入门指南](/documentation/QUICKSTART.zh.md)。
+
+| 模型 | 参数量 | 许可证 | 商业使用 |
+| --- | --- | --- | --- |
+| **ACE-Step** | 3.5B | Apache-2.0 | 是 |
+| **Anima** | 未指定 | CircleStone Labs Non-Commercial License v1.2 | 否（模型）；输出可商用 |
+| **Auraflow** | 6B | Apache-2.0 | 是 |
+| **Boogu-Image** | 未指定 | Apache-2.0 | 是 |
+| **Chroma 1** | 8.9B | Apache-2.0 | 是 |
+| **Cosmos2** | 2B-14B | NVIDIA Open Model License | 是 |
+| **Cosmos3** | 16B-65B | OpenMDW-1.1 | 是 |
+| **DeepFloyd IF** | 0.4B-4.3B stages | DeepFloyd IF License | Abandonware |
+| **ERNIE-Image** | 未指定 | Apache-2.0 | 是 |
+| **Flux.1** | 8B-12B | Apache-2.0 (schnell)；FLUX.1 [dev] Non-Commercial License (dev/Kontext) | 按 checkpoint 不同 |
+| **Flux.2** | 4B-32B | Apache-2.0 (klein 4B)；FLUX Non-Commercial License (dev/klein 9B) | 按 checkpoint 不同 |
+| **HeartMuLa** | 3B | SimpleTuner 中未指定 | 查看上游条款 |
+| **HiDream** | 17B (8.5B MoE) | MIT | 是 |
+| **Hunyuan Video** | 8.3B | AGPL-3.0 | 是（copyleft） |
+| **Ideogram 4** | 9B | Ideogram 4 Non-Commercial | 否 |
+| **Kandinsky 5.0 Image** | 6B (lite) | MIT | 是 |
+| **Kandinsky 5.0 Video** | 2B lite, 19B pro | MIT | 是 |
+| **Kwai Kolors** | 2.7B | Apache-2.0 | Abandonware |
+| **Krea2** | 未指定 | Krea 2 Community License | 是（年收入低于 100 万美元；需安全防护） |
+| **LongCat Image** | 6B | Apache-2.0 | 是 |
+| **LongCat Video** | 13.6B | MIT | 是 |
+| **LTX Video** | ~2.5B | Apache-2.0 | 是 |
+| **LTX Video 2** | 19B | Apache-2.0 | 是 |
+| **Lumina2** | 2B | Apache-2.0 | 是 |
+| **Mage-Flow** | 4B | MIT | 是 |
+| **OmniGen** | 3.8B | MIT | 是 |
+| **PixArt Sigma** | 0.6B-0.9B | OpenRAIL++ | 是（受限） |
+| **Qwen Image** | 20B | Apache-2.0 | 是 |
+| **Sana** | 0.6B-4.8B | Apache-2.0 | 是 |
+| **Sana Video** | 2B | Apache-2.0 | 是 |
+| **SD 1.x/2.x (Legacy)** | 0.9B | OpenRAIL++ | 是（受限） |
+| **Stable Diffusion 3** | 2B-8B | Stability AI Community License | 是（年收入低于 100 万美元） |
+| **Stable Diffusion XL** | 3.5B | CreativeML OpenRAIL-M | 是（受限） |
+| **Stable Cascade (Stage C)** | 1B, 3.6B prior | SimpleTuner 中未指定 | Abandonware |
+| **Wan Video** | 1.3B-14B | Apache-2.0 | 是 |
+| **Wan S2V** | 14B | Apache-2.0 | 是 |
+| **Z-Image** | 6B | Apache-2.0 | 是 |
+| **Z-Image Omni** | 6B | Apache-2.0 | 是 |
+| **ZLab I1** | 3B | MIT | 是 |
+
+*许可证值在可用时来自 SimpleTuner 模型 helper，并为此前未指定的条目参考上游模型卡/许可证。`SimpleTuner 中未指定` 表示 helper 未命名许可证，且此处未汇总上游条款；使用前请查看上游模型卡。*
 
 ### 高级训练技术
 
diff --git a/documentation/QUICKSTART.es.md b/documentation/QUICKSTART.es.md
index 478abae04..01870c9e3 100644
--- a/documentation/QUICKSTART.es.md
+++ b/documentation/QUICKSTART.es.md
@@ -2,84 +2,291 @@
 
 **Nota**: Para configuraciones más avanzadas, consulta el [tutorial](TUTORIAL.md) y la [referencia de opciones](OPTIONS.md).
 
+## Guías de inicio rápido por modelo
+
+| Modelo | Parámetros | Guía |
+| --- | --- | --- |
+| ACE-Step | 3.5B | [ACE_STEP.es.md](quickstart/ACE_STEP.es.md) |
+| Anima | Not specified | Sin guía dedicada |
+| Auraflow | 6B | [AURAFLOW.es.md](quickstart/AURAFLOW.es.md) |
+| Boogu-Image | Not specified | [BOOGU_IMAGE.es.md](quickstart/BOOGU_IMAGE.es.md) |
+| Chroma 1 | 8.9B | [CHROMA.es.md](quickstart/CHROMA.es.md) |
+| Cosmos2 | 2B-14B | [COSMOS2IMAGE.es.md](quickstart/COSMOS2IMAGE.es.md) |
+| Cosmos3 | 16B-65B | [COSMOS3.es.md](quickstart/COSMOS3.es.md) |
+| DeepFloyd IF | 0.4B-4.3B stages | Sin guía dedicada |
+| ERNIE-Image | Not specified | [ERNIE.es.md](quickstart/ERNIE.es.md) |
+| Flux.1 | 8B-12B | [FLUX.es.md](quickstart/FLUX.es.md)<br>[FLUX_KONTEXT.es.md](quickstart/FLUX_KONTEXT.es.md) |
+| Flux.2 | 4B-32B | [FLUX2.es.md](quickstart/FLUX2.es.md) |
+| HeartMuLa | 3B | [HEARTMULA.es.md](quickstart/HEARTMULA.es.md) |
+| HiDream | 17B (8.5B MoE) | [HIDREAM.es.md](quickstart/HIDREAM.es.md) |
+| Hunyuan Video | 8.3B | [HUNYUANVIDEO.es.md](quickstart/HUNYUANVIDEO.es.md) |
+| Ideogram 4 | 9B | [IDEOGRAM4.es.md](quickstart/IDEOGRAM4.es.md) |
+| Kandinsky 5.0 Image | 6B (lite) | [KANDINSKY5_IMAGE.es.md](quickstart/KANDINSKY5_IMAGE.es.md) |
+| Kandinsky 5.0 Video | 2B lite, 19B pro | [KANDINSKY5_VIDEO.es.md](quickstart/KANDINSKY5_VIDEO.es.md) |
+| Kwai Kolors | 2.7B | [KOLORS.es.md](quickstart/KOLORS.es.md) |
+| Krea2 | Not specified | [KREA2.es.md](quickstart/KREA2.es.md) |
+| LongCat Image | 6B | [LONGCAT_IMAGE.es.md](quickstart/LONGCAT_IMAGE.es.md)<br>[LONGCAT_EDIT.es.md](quickstart/LONGCAT_EDIT.es.md) |
+| LongCat Video | 13.6B | [LONGCAT_VIDEO.es.md](quickstart/LONGCAT_VIDEO.es.md)<br>[LONGCAT_VIDEO_EDIT.es.md](quickstart/LONGCAT_VIDEO_EDIT.es.md) |
+| LTX Video | ~2.5B | [LTXVIDEO.es.md](quickstart/LTXVIDEO.es.md) |
+| LTX Video 2 | 19B | [LTXVIDEO2.es.md](quickstart/LTXVIDEO2.es.md) |
+| Lumina2 | 2B | [LUMINA2.es.md](quickstart/LUMINA2.es.md) |
+| Mage-Flow | 4B | [MAGEFLOW.es.md](quickstart/MAGEFLOW.es.md) |
+| OmniGen | 3.8B | [OMNIGEN.es.md](quickstart/OMNIGEN.es.md) |
+| PixArt Sigma | 0.6B-0.9B | [SIGMA.es.md](quickstart/SIGMA.es.md) |
+| Qwen Image | 20B | [QWEN_IMAGE.es.md](quickstart/QWEN_IMAGE.es.md)<br>[QWEN_EDIT.es.md](quickstart/QWEN_EDIT.es.md) |
+| Sana | 0.6B-4.8B | [SANA.es.md](quickstart/SANA.es.md) |
+| Sana Video | 2B | [SANAVIDEO.es.md](quickstart/SANAVIDEO.es.md) |
+| SD 1.x/2.x (Legacy) | 0.9B | Sin guía dedicada |
+| Stable Diffusion 3 | 2B-8B | [SD3.es.md](quickstart/SD3.es.md) |
+| Stable Diffusion XL | 3.5B | [SDXL.es.md](quickstart/SDXL.es.md) |
+| Stable Cascade (Stage C) | 1B, 3.6B prior | [STABLE_CASCADE_C.es.md](quickstart/STABLE_CASCADE_C.es.md) |
+| Wan Video | 1.3B-14B | [WAN.es.md](quickstart/WAN.es.md) |
+| Wan S2V | 14B | [WAN_S2V.es.md](quickstart/WAN_S2V.es.md) |
+| Z-Image | 6B | [ZIMAGE.es.md](quickstart/ZIMAGE.es.md) |
+| Z-Image Omni | 6B | [ZIMAGE.es.md](quickstart/ZIMAGE.es.md) |
+| ZLab I1 | 3B | [ZLAB_i1.es.md](quickstart/ZLAB_i1.es.md) |
+
 ## Compatibilidad de funciones
 
-Para la matriz de funciones completa y más precisa, consulta el [README principal](https://github.com/bghira/SimpleTuner#model-architecture-support).
+La matriz completa de compatibilidad se divide por área de función para que cada tabla sea legible.
 
-## Guías de inicio rápido por modelo
+<details>
+<summary>Soporte de entrenamiento</summary>
+
+| Modelo | PEFT LoRA | LyCORIS | Rango completo | ControlNet | Ref Inputs |
+| --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Anima | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| Chroma 1 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓* | ✗ | audio opt |
+| DeepFloyd IF | ✓ | ✓ | ✓ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓* | ✓ | ✓ opt (Kontext) |
+| Flux.2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| HeartMuLa | ✓ | ✓ | ✓* | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Ideogram 4 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓* | ✗ | ✓ I2I |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Kwai Kolors | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| LongCat Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| LongCat Video | ✓ | ✓ | ✓* | ✗ | ✓ opt/edit |
+| LTX Video | ✓ | ✓ | ✓ | ✗ | ✓ I2V |
+| LTX Video 2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| OmniGen | ✓ | ✓ | ✓ | ✗ | ✗ |
+| PixArt Sigma | ✗ | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| Sana | ✗ | ✓ | ✓ | ✗ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Stable Diffusion XL | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Wan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V/VACE |
+| Wan S2V | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image Omni | ✓ | ✓ | ✓* | ✗ | ✓ opt (Edit) |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ | ✗ |
+
+</details>
+
+<details>
+<summary>Compatibilidad de precisión</summary>
+
+| Modelo | Cuantización | Precisión mixta |
+| --- | --- | --- |
+| ACE-Step | int8 optional | bf16 |
+| Anima | not specified | bf16 |
+| Auraflow | int8/fp8/nf4 optional | bf16 |
+| Boogu-Image | fp8 optional | bf16 |
+| Chroma 1 | int8/fp8/nf4 optional | bf16 |
+| Cosmos2 | int8 optional | bf16 |
+| Cosmos3 | no_change first; int8 optional | bf16 |
+| DeepFloyd IF | not recommended | bf16 |
+| ERNIE-Image | int8 optional | bf16 |
+| Flux.1 | int8/fp8/nf4 optional | bf16 |
+| Flux.2 | int8/fp8/nf4 optional | bf16 |
+| HeartMuLa | int8 optional | bf16 |
+| HiDream | int8/fp8/nf4 optional | bf16 |
+| Hunyuan Video | int8 optional | bf16 |
+| Ideogram 4 | fp8 default, nf4 optional | bf16 |
+| Kandinsky 5.0 Image | int8 optional | bf16 |
+| Kandinsky 5.0 Video | int8 optional | bf16 |
+| Kwai Kolors | not recommended | bf16 |
+| Krea2 | int8 optional | bf16 |
+| LongCat Image | int8/fp8 optional | bf16 |
+| LongCat Video | int8/fp8 optional | bf16 |
+| LTX Video | int8/fp8 optional | bf16 |
+| LTX Video 2 | int8/fp8 optional | bf16 |
+| Lumina2 | int8 optional | bf16 |
+| Mage-Flow | fp8 optional | bf16 |
+| OmniGen | int8/fp8 optional | bf16 |
+| PixArt Sigma | int8 optional | bf16 |
+| Qwen Image | required (int8/nf4) | bf16 |
+| Sana | int8 optional | bf16 |
+| Sana Video | not recommended for full | bf16 |
+| SD 1.x/2.x (Legacy) | int8/nf4 optional | bf16 |
+| Stable Diffusion 3 | int8/fp8/nf4 optional | bf16 |
+| Stable Diffusion XL | int8/nf4 optional | bf16 |
+| Stable Cascade (Stage C) | not supported | fp32 required |
+| Wan Video | int8 optional | bf16 |
+| Wan S2V | int8 optional | bf16 |
+| Z-Image | int8 optional | bf16 |
+| Z-Image Omni | int8 optional | bf16 |
+| ZLab I1 | int8 optional | bf16 |
+
+</details>
+
+<details>
+<summary>Granularidad de checkpointing</summary>
+
+| Modelo | Checkpointing de gradiente | Intervalo | Segment stride | Offload de atención |
+| --- | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓ | ✗ |
+| Anima | ✓ | ✗ | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓ | ✗ |
+| Chroma 1 | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓ | ✗ |
+| DeepFloyd IF | ✓ | ✗ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | ✓ | ✗ | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | ✓ | ✓ | ✓ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | ✓ | ✗ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | ✓ | ✓ | ✓ | ✗ |
+| LTX Video 2 | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓ | ✓ |
+| OmniGen | ✓ | ✗ | ✗ | ✗ |
+| PixArt Sigma | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓ | ✗ |
+| Sana | ✓ | ✓ | ✓ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✗ | ✗ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | ✓ | ✗ | ✗ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓ | ✗ |
+| Wan Video | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | ✓ | ✓ | ✓ | ✗ |
+| Z-Image | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | ✓ | ✗ | ✗ | ✗ |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ |
+
+</details>
+
+<details>
+<summary>Flujo, destilación y alineación</summary>
+
+| Modelo | Predicción | Flow Shift | TwinFlow | Self-Flow | LayerSync | Sliders |
+| --- | --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Anima | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Auraflow | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Boogu-Image | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Chroma 1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | sample | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Cosmos3 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| DeepFloyd IF | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| ERNIE-Image | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Flux.1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | autoregressive next-token | ✗ | ✗ | ✗ | ✗ | ✗ |
+| HiDream | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Hunyuan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Kandinsky 5.0 Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Krea2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video 2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Mage-Flow | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| OmniGen | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| PixArt Sigma | epsilon | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Qwen Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| SD 1.x/2.x (Legacy) | epsilon / v-pred | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Diffusion 3 | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Cascade (Stage C) | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Wan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Z-Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| ZLab I1 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+
+</details>
+
+<details>
+<summary>Encoders de texto y tipos de VAE</summary>
+
+| Modelo | Encoders de texto | Parámetros de encoder | VAE |
+| --- | --- | --- | --- |
+| ACE-Step | UMT5 Encoder | 0.6B | Music DCAE |
+| Anima | Qwen3 0.6B | 0.6B | Qwen Image VAE |
+| Auraflow | Pile T5 | not specified | AutoencoderKL |
+| Boogu-Image | Qwen3-VL | not specified | AutoencoderKL |
+| Chroma 1 | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Cosmos2 | T5 11B | 11B | Wan VAE |
+| Cosmos3 | Cosmos3 reasoner | not specified | Wan/Cosmos VAE |
+| DeepFloyd IF | T5 XXL v1.1 | 11B | None |
+| ERNIE-Image | ERNIE text encoder | not specified | Flux.2 VAE |
+| Flux.1 | CLIP-L/14 + T5 XXL v1.1 | 123M + 11B | AutoencoderKL |
+| Flux.2 | Mistral-Small-3.1-24B | 24B | Flux.2 VAE |
+| HeartMuLa | None | N/A | HeartCodec tokens |
+| HiDream | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 + Llama | 123M + 694M + 11B + not specified | AutoencoderKL |
+| Hunyuan Video | Hunyuan LLM | not specified | Hunyuan Video 3D VAE |
+| Ideogram 4 | Qwen3-VL-8B-Instruct | 8B | Ideogram AutoEncoder |
+| Kandinsky 5.0 Image | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Flux VAE (AutoencoderKL) |
+| Kandinsky 5.0 Video | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Hunyuan Video VAE |
+| Kwai Kolors | ChatGLM-6B | 6B | AutoencoderKL |
+| Krea2 | Qwen3VL | not specified | Qwen Image VAE |
+| LongCat Image | Qwen2.5-VL | 7B | AutoencoderKL |
+| LongCat Video | Qwen2.5-VL | 7B | Wan VAE |
+| LTX Video | T5 XXL v1.1 | 11B | LTX Video VAE |
+| LTX Video 2 | Gemma3 | not specified | LTX Video 2 VAE |
+| Lumina2 | Gemma2 | 2B | AutoencoderKL |
+| Mage-Flow | Qwen3-VL | not specified | Mage-VAE |
+| OmniGen | Integrated OmniGen encoder | not specified | AutoencoderKL |
+| PixArt Sigma | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Qwen Image | Qwen2.5-VL | 7B | Qwen Image VAE |
+| Sana | Gemma2 2B-IT | 2B | Sana AutoencoderDC |
+| Sana Video | Gemma 2 | 2B | Wan VAE |
+| SD 1.x/2.x (Legacy) | CLIP-L/14 | 123M | AutoencoderKL |
+| Stable Diffusion 3 | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 | 123M + 694M + 11B | AutoencoderKL |
+| Stable Diffusion XL | CLIP-L/14 + CLIP-G/14 | 123M + 694M | AutoencoderKL |
+| Stable Cascade (Stage C) | CLIP-ViT-bigG-14 | 694M | Stable Cascade Stage C VAE |
+| Wan Video | UMT5 | not specified | Wan VAE |
+| Wan S2V | UMT5 | not specified | Wan VAE |
+| Z-Image | Qwen3 4B | 4B | AutoencoderKL |
+| Z-Image Omni | Qwen3 4B | 4B | AutoencoderKL |
+| ZLab I1 | T5Gemma 2B | 2B | AutoencoderKL |
+
+</details>
 
-| Modelo | Parámetros | PEFT LoRA | Lycoris | Rango completo | Cuantización | Precisión mixta | Checkpointing de gradiente | Flow Shift | TwinFlow | Self-Flow | LayerSync | Ref Inputs | ControlNet | Sliders† | Licencia | Permite uso comercial | Guía |
-| --- | --- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | --- | :---: | --- |
-| PixArt Sigma | 0.6B–0.9B | ✗ | ✓ | ✓ | int8 opcional | bf16 | ✓ | ✗ | ✗ | ✓ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Aplican condiciones<sup>1</sup> | [SIGMA.md](quickstart/SIGMA.md) |
-| NVLabs Sana | 1.6B–4.8B | ✗ | ✓ | ✓ | int8 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [SANA.md](quickstart/SANA.md) |
-| Kwai Kolors | 2.7B | ✓ | ✓ | ✓ | no recomendado | bf16 | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Aplican condiciones<sup>7</sup> | [KOLORS.md](quickstart/KOLORS.md) |
-| Stable Diffusion 3 | 2B–8B | ✓ | ✓ | ✓ | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Stability AI Community](https://stability.ai/license) | Aplican condiciones<sup>2</sup> | [SD3.md](quickstart/SD3.md) |
-| Flux.1 | 8B–12B | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Aplican condiciones<sup>3</sup> | [FLUX.md](quickstart/FLUX.md) |
-| Flux.2 | 32B | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Aplican condiciones<sup>4</sup> | [FLUX2.md](quickstart/FLUX2.md) |
-| Flux Kontext | 8B–12B | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) | No<sup>5</sup> | [FLUX_KONTEXT.md](quickstart/FLUX_KONTEXT.md) |
-| Z-Image Turbo | 6B | ✓ | ✗ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [ZIMAGE.md](quickstart/ZIMAGE.md) |
-| Krea2 | - | ✓ | ✗ | ✓* | int8 opcional | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✓ opt | ✗ | ✓ | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | Aplican condiciones<sup>6</sup> | [KREA2.md](quickstart/KREA2.es.md) |
-| Mage-Flow | 4B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ edit | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sí | [MAGEFLOW.md](quickstart/MAGEFLOW.es.md) |
-| Boogu-Image 0.1 | - | ✓ | ✓ | ✓* | fp8 opcional | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ edit | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [BOOGU_IMAGE.md](quickstart/BOOGU_IMAGE.es.md) |
-| zlab i1 | 3B | ✓ | ✓ | ✓ | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | Aplican condiciones<sup>12</sup> | [ZLAB_i1.md](quickstart/ZLAB_i1.es.md) |
-| Ideogram 4 | 9B | ✓ | ✓ | ✓* | fp8 predeterminado, nf4 opcional | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | No<sup>5</sup> | [IDEOGRAM4.md](quickstart/IDEOGRAM4.es.md) |
-| ERNIE-Image | - | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [ERNIE.md](quickstart/ERNIE.es.md) |
-| ACE-Step | 3.5B | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B) / [MIT](https://huggingface.co/ACE-Step/Ace-Step1.5) | Sí | [ACE_STEP.md](quickstart/ACE_STEP.md) |
-| Chroma 1 | 8.9B | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [CHROMA.md](quickstart/CHROMA.md) |
-| Auraflow | 6B | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) / [Pony License](https://huggingface.co/purplesmartai/pony-v7-base/blob/main/LICENSE) | Aplican condiciones<sup>8</sup> | [AURAFLOW.md](quickstart/AURAFLOW.md) |
-| HiDream I1 | 17B (8.5B MoE) | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [MIT](https://opensource.org/license/mit) | Sí | [HIDREAM.md](quickstart/HIDREAM.md) |
-| OmniGen | 3.8B | ✓ | ✓ | ✓ | int8/fp8 opcional | bf16 | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sí | [OMNIGEN.md](quickstart/OMNIGEN.md) |
-| Stable Diffusion XL | 2.6B | ✓ | ✓ | ✓ | no recomendado | bf16 | ✓ | ✗ | ✗ | ✗ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Aplican condiciones<sup>1</sup> | [SDXL.md](quickstart/SDXL.md) |
-| Lumina2 | 2B | ✓ | ✓ | ✓ | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [LUMINA2.md](quickstart/LUMINA2.md) |
-| Cosmos2 | 2B | ✓ | ✓ | ✓ | no recomendado | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) | Sí<sup>9</sup> | [COSMOS2IMAGE.md](quickstart/COSMOS2IMAGE.md) |
-| Cosmos3 | 16B-65B | ✓ | ✓ | ✓* | no_change primero | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | audio opt | ✗ | ✓ | [OpenMDW 1.1](https://github.com/OpenMDW/openmdw/blob/main/1.1/LICENSE.OpenMDW-1.1) | Sí | [COSMOS3.md](quickstart/COSMOS3.es.md) |
-| LTX Video | ~2.5B | ✓ | ✓ | ✓ | int8/fp8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [LTX Video OpenRAIL-M](https://huggingface.co/Lightricks/LTX-Video-0.9.5/blob/main/ltx-video-2b-v0.9.5.license.txt) | Aplican condiciones<sup>10</sup> | [LTXVIDEO.md](quickstart/LTXVIDEO.md) |
-| LTX Video 2 | 19B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [LTX-2 Community](https://ltx.io/model/license) | Aplican condiciones<sup>10</sup> | [LTXVIDEO2.md](quickstart/LTXVIDEO2.md) |
-| Hunyuan Video 1.5 | 8.3B | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [Tencent Hunyuan Community](https://huggingface.co/tencent/HunyuanVideo-1.5/blob/main/LICENSE) | Aplican condiciones<sup>11</sup> | [HUNYUANVIDEO.md](quickstart/HUNYUANVIDEO.md) |
-| SanaVideo | 2B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓ | ✗ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [SANAVIDEO.md](quickstart/SANAVIDEO.es.md) |
-| Wan 2.x | 1.3B–14B | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [WAN.md](quickstart/WAN.md) |
-| Wan 2.2 S2V | 14B | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [WAN_S2V.md](quickstart/WAN_S2V.md) |
-| Qwen Image | 20B | ✓ | ✓ | ✓* | **requerido** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [QWEN_IMAGE.md](quickstart/QWEN_IMAGE.md) |
-| Qwen Image Edit | 20B | ✓ | ✓ | ✓* | **requerido** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [QWEN_EDIT.md](quickstart/QWEN_EDIT.md) |
-| Stable Cascade (C) | 1B, prior 3.6B | ✓ | ✓ | ✓* | no soportado | fp32 (requerido) | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | No<sup>5</sup> | [STABLE_CASCADE_C.md](quickstart/STABLE_CASCADE_C.md) |
-| Kandinsky 5.0 Image | 6B (lite) | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ I2I | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sí | [KANDINSKY5_IMAGE.md](quickstart/KANDINSKY5_IMAGE.md) |
-| Kandinsky 5.0 Video | 2B (lite), 19B (pro) | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sí | [KANDINSKY5_VIDEO.md](quickstart/KANDINSKY5_VIDEO.md) |
-| LongCat-Video | 13.6B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sí | [LONGCAT_VIDEO.md](quickstart/LONGCAT_VIDEO.md) |
-| LongCat-Video Edit | 13.6B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sí | [LONGCAT_VIDEO_EDIT.md](quickstart/LONGCAT_VIDEO_EDIT.md) |
-| LongCat-Image | 6B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [LONGCAT_IMAGE.md](quickstart/LONGCAT_IMAGE.md) |
-| LongCat-Image Edit | 6B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [LONGCAT_EDIT.md](quickstart/LONGCAT_EDIT.md) |
-
-*✓ = soportado, ✓* = requiere DeepSpeed/FSDP2 para rango completo, ✗ = no soportado, `✓+` indica que se recomienda checkpointing por presión de VRAM. Ref Inputs marca rutas existentes de condicionamiento por referencia/edición/I2V; `opt` significa opcional y `req` significa requerido por el flavour de edición/I2V. TwinFlow ✓ significa soporte nativo cuando `twinflow_enabled=true` (los modelos de difusión necesitan `diff2flow_enabled+twinflow_allow_diff2flow`). Self-Flow ✓ significa soporte nativo para `crepa_enabled=true` con `crepa_feature_source=self_flow`, `use_ema=true` y `crepa_teacher_block_index` configurado. LayerSync ✓ significa que el backbone expone estados ocultos del transformer para autoalineación; ✗ marca backbones tipo UNet sin ese buffer. †Sliders aplican a LoRA y LyCORIS (incluido LyCORIS de rango completo “full”).*
-
-**Notas de licencia:** El estado de uso comercial cubre pesos del modelo, checkpoints derivados, fine-tunes y uso del modelo alojado. Los derechos sobre salidas generadas pueden diferir; lee el texto de licencia enlazado antes de un despliegue comercial.
-
-<sup>1</sup> Las licencias estilo OpenRAIL suelen permitir uso comercial con restricciones de uso que siguen aplicando al modelo y sus derivados.
-
-<sup>2</sup> La Stability AI Community License está disponible para usuarios que califican por debajo del umbral de ingresos; el uso comercial mayor requiere términos empresariales de Stability.
-
-<sup>3</sup> Flux.1 varía por flavour: Schnell y LibreFlux son Apache-2.0, mientras que Dev, Krea y Kontext usan términos no comerciales de BFL; revisa los metadatos upstream de FluxBooru antes de uso comercial.
-
-<sup>4</sup> Flux.2 varía por flavour: Klein 4B es Apache-2.0, mientras que Dev y Klein 9B usan términos no comerciales de BFL.
-
-<sup>5</sup> Los términos públicos no comerciales no permiten uso comercial de pesos, checkpoints derivados o servicios alojados del modelo sin una licencia separada.
-
-<sup>6</sup> La Krea 2 Community License permite uso comercial solo bajo sus requisitos de ingresos y seguridad/filtrado; de lo contrario se requiere una licencia empresarial.
-
-<sup>7</sup> El uso comercial del modelo Kolors o sus derivados requiere solicitar y recibir permiso explícito del licenciante.
-
-<sup>8</sup> AuraFlow admite flavours upstream Apache-2.0 y un flavour Pony con una licencia personalizada separada; revisa el flavour seleccionado.
-
-<sup>9</sup> La NVIDIA Open Model License permite uso comercial, pero incluye términos de acuerdo, uso aceptable y control de exportación.
-
-<sup>10</sup> LTX Video 0.9.5 usa OpenRAIL-M; LTX Video 2 usa términos comunitarios de LTX con un umbral de ingresos para uso comercial.
-
-<sup>11</sup> La Tencent Hunyuan Community License incluye exclusiones territoriales y un umbral comercial para servicios muy grandes.
-
-<sup>12</sup> Este mirror publica `license: other` sin un texto de licencia estándar; revisa los términos upstream antes de uso comercial.
-
-> ℹ️ El inicio rápido de Wan incluye presets de las etapas 2.1 y 2.2 y el toggle de time-embedding. Flux Kontext cubre flujos de edición construidos sobre Flux.1.
-
-> ⚠️ Estos quickstarts son documentos vivos. Espera actualizaciones ocasionales a medida que llegan nuevos modelos o se mejoran recetas de entrenamiento.
+*✓ = soportado, ✓* = soportado pero normalmente requiere DeepSpeed/FSDP2 para entrenamiento full-rank, ✗ = no soportado. Ref Inputs marca rutas existentes de condicionamiento por referencia/edición/I2V; `opt` significa opcional y `req` significa requerido por el flavour de edición/I2V.*
+*TwinFlow es nativo cuando `twinflow_enabled=true`; los modelos de difusión aún requieren `diff2flow_enabled=true` y `twinflow_allow_diff2flow=true`. Self-Flow se refiere al soporte CREPA self-flow. LayerSync marca backbones que exponen estados ocultos para alineación.*
 
 ### Rutas rápidas: Z-Image Turbo y Flux Schnell
 
diff --git a/documentation/QUICKSTART.hi.md b/documentation/QUICKSTART.hi.md
index ec34ffb04..e404d878c 100644
--- a/documentation/QUICKSTART.hi.md
+++ b/documentation/QUICKSTART.hi.md
@@ -2,84 +2,291 @@
 
 **नोट**: अधिक उन्नत कॉन्फ़िगरेशनों के लिए, [ट्यूटोरियल](TUTORIAL.md) और [options reference](OPTIONS.md) देखें।
 
-## फ़ीचर संगतता
+## मॉडल क्विकस्टार्ट गाइड
 
-पूरा और सबसे सटीक फीचर मैट्रिक्स देखने के लिए, [मुख्य README](https://github.com/bghira/SimpleTuner#model-architecture-support) देखें।
+| मॉडल | पैरामीटर | गाइड |
+| --- | --- | --- |
+| ACE-Step | 3.5B | [ACE_STEP.hi.md](quickstart/ACE_STEP.hi.md) |
+| Anima | Not specified | Dedicated guide नहीं है |
+| Auraflow | 6B | [AURAFLOW.hi.md](quickstart/AURAFLOW.hi.md) |
+| Boogu-Image | Not specified | [BOOGU_IMAGE.hi.md](quickstart/BOOGU_IMAGE.hi.md) |
+| Chroma 1 | 8.9B | [CHROMA.hi.md](quickstart/CHROMA.hi.md) |
+| Cosmos2 | 2B-14B | [COSMOS2IMAGE.hi.md](quickstart/COSMOS2IMAGE.hi.md) |
+| Cosmos3 | 16B-65B | [COSMOS3.hi.md](quickstart/COSMOS3.hi.md) |
+| DeepFloyd IF | 0.4B-4.3B stages | Dedicated guide नहीं है |
+| ERNIE-Image | Not specified | [ERNIE.hi.md](quickstart/ERNIE.hi.md) |
+| Flux.1 | 8B-12B | [FLUX.hi.md](quickstart/FLUX.hi.md)<br>[FLUX_KONTEXT.hi.md](quickstart/FLUX_KONTEXT.hi.md) |
+| Flux.2 | 4B-32B | [FLUX2.hi.md](quickstart/FLUX2.hi.md) |
+| HeartMuLa | 3B | [HEARTMULA.hi.md](quickstart/HEARTMULA.hi.md) |
+| HiDream | 17B (8.5B MoE) | [HIDREAM.hi.md](quickstart/HIDREAM.hi.md) |
+| Hunyuan Video | 8.3B | [HUNYUANVIDEO.hi.md](quickstart/HUNYUANVIDEO.hi.md) |
+| Ideogram 4 | 9B | [IDEOGRAM4.hi.md](quickstart/IDEOGRAM4.hi.md) |
+| Kandinsky 5.0 Image | 6B (lite) | [KANDINSKY5_IMAGE.hi.md](quickstart/KANDINSKY5_IMAGE.hi.md) |
+| Kandinsky 5.0 Video | 2B lite, 19B pro | [KANDINSKY5_VIDEO.hi.md](quickstart/KANDINSKY5_VIDEO.hi.md) |
+| Kwai Kolors | 2.7B | [KOLORS.hi.md](quickstart/KOLORS.hi.md) |
+| Krea2 | Not specified | [KREA2.hi.md](quickstart/KREA2.hi.md) |
+| LongCat Image | 6B | [LONGCAT_IMAGE.hi.md](quickstart/LONGCAT_IMAGE.hi.md)<br>[LONGCAT_EDIT.hi.md](quickstart/LONGCAT_EDIT.hi.md) |
+| LongCat Video | 13.6B | [LONGCAT_VIDEO.hi.md](quickstart/LONGCAT_VIDEO.hi.md)<br>[LONGCAT_VIDEO_EDIT.hi.md](quickstart/LONGCAT_VIDEO_EDIT.hi.md) |
+| LTX Video | ~2.5B | [LTXVIDEO.hi.md](quickstart/LTXVIDEO.hi.md) |
+| LTX Video 2 | 19B | [LTXVIDEO2.hi.md](quickstart/LTXVIDEO2.hi.md) |
+| Lumina2 | 2B | [LUMINA2.hi.md](quickstart/LUMINA2.hi.md) |
+| Mage-Flow | 4B | [MAGEFLOW.hi.md](quickstart/MAGEFLOW.hi.md) |
+| OmniGen | 3.8B | [OMNIGEN.hi.md](quickstart/OMNIGEN.hi.md) |
+| PixArt Sigma | 0.6B-0.9B | [SIGMA.hi.md](quickstart/SIGMA.hi.md) |
+| Qwen Image | 20B | [QWEN_IMAGE.hi.md](quickstart/QWEN_IMAGE.hi.md)<br>[QWEN_EDIT.hi.md](quickstart/QWEN_EDIT.hi.md) |
+| Sana | 0.6B-4.8B | [SANA.hi.md](quickstart/SANA.hi.md) |
+| Sana Video | 2B | [SANAVIDEO.hi.md](quickstart/SANAVIDEO.hi.md) |
+| SD 1.x/2.x (Legacy) | 0.9B | Dedicated guide नहीं है |
+| Stable Diffusion 3 | 2B-8B | [SD3.hi.md](quickstart/SD3.hi.md) |
+| Stable Diffusion XL | 3.5B | [SDXL.hi.md](quickstart/SDXL.hi.md) |
+| Stable Cascade (Stage C) | 1B, 3.6B prior | [STABLE_CASCADE_C.hi.md](quickstart/STABLE_CASCADE_C.hi.md) |
+| Wan Video | 1.3B-14B | [WAN.hi.md](quickstart/WAN.hi.md) |
+| Wan S2V | 14B | [WAN_S2V.hi.md](quickstart/WAN_S2V.hi.md) |
+| Z-Image | 6B | [ZIMAGE.hi.md](quickstart/ZIMAGE.hi.md) |
+| Z-Image Omni | 6B | [ZIMAGE.hi.md](quickstart/ZIMAGE.hi.md) |
+| ZLab I1 | 3B | [ZLAB_i1.hi.md](quickstart/ZLAB_i1.hi.md) |
 
-## मॉडल क्विकस्टार्ट गाइड
+## फीचर संगतता
+
+पूरी compatibility matrix को feature area के अनुसार बांटा गया है ताकि हर table पढ़ने योग्य रहे।
+
+<details>
+<summary>Training support</summary>
+
+| मॉडल | PEFT LoRA | LyCORIS | Full-Rank | ControlNet | Ref Inputs |
+| --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Anima | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| Chroma 1 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓* | ✗ | audio opt |
+| DeepFloyd IF | ✓ | ✓ | ✓ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓* | ✓ | ✓ opt (Kontext) |
+| Flux.2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| HeartMuLa | ✓ | ✓ | ✓* | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Ideogram 4 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓* | ✗ | ✓ I2I |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Kwai Kolors | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| LongCat Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| LongCat Video | ✓ | ✓ | ✓* | ✗ | ✓ opt/edit |
+| LTX Video | ✓ | ✓ | ✓ | ✗ | ✓ I2V |
+| LTX Video 2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| OmniGen | ✓ | ✓ | ✓ | ✗ | ✗ |
+| PixArt Sigma | ✗ | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| Sana | ✗ | ✓ | ✓ | ✗ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Stable Diffusion XL | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Wan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V/VACE |
+| Wan S2V | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image Omni | ✓ | ✓ | ✓* | ✗ | ✓ opt (Edit) |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ | ✗ |
+
+</details>
+
+<details>
+<summary>Precision level support</summary>
+
+| मॉडल | Quantization | Mixed Precision |
+| --- | --- | --- |
+| ACE-Step | int8 optional | bf16 |
+| Anima | not specified | bf16 |
+| Auraflow | int8/fp8/nf4 optional | bf16 |
+| Boogu-Image | fp8 optional | bf16 |
+| Chroma 1 | int8/fp8/nf4 optional | bf16 |
+| Cosmos2 | int8 optional | bf16 |
+| Cosmos3 | no_change first; int8 optional | bf16 |
+| DeepFloyd IF | not recommended | bf16 |
+| ERNIE-Image | int8 optional | bf16 |
+| Flux.1 | int8/fp8/nf4 optional | bf16 |
+| Flux.2 | int8/fp8/nf4 optional | bf16 |
+| HeartMuLa | int8 optional | bf16 |
+| HiDream | int8/fp8/nf4 optional | bf16 |
+| Hunyuan Video | int8 optional | bf16 |
+| Ideogram 4 | fp8 default, nf4 optional | bf16 |
+| Kandinsky 5.0 Image | int8 optional | bf16 |
+| Kandinsky 5.0 Video | int8 optional | bf16 |
+| Kwai Kolors | not recommended | bf16 |
+| Krea2 | int8 optional | bf16 |
+| LongCat Image | int8/fp8 optional | bf16 |
+| LongCat Video | int8/fp8 optional | bf16 |
+| LTX Video | int8/fp8 optional | bf16 |
+| LTX Video 2 | int8/fp8 optional | bf16 |
+| Lumina2 | int8 optional | bf16 |
+| Mage-Flow | fp8 optional | bf16 |
+| OmniGen | int8/fp8 optional | bf16 |
+| PixArt Sigma | int8 optional | bf16 |
+| Qwen Image | required (int8/nf4) | bf16 |
+| Sana | int8 optional | bf16 |
+| Sana Video | not recommended for full | bf16 |
+| SD 1.x/2.x (Legacy) | int8/nf4 optional | bf16 |
+| Stable Diffusion 3 | int8/fp8/nf4 optional | bf16 |
+| Stable Diffusion XL | int8/nf4 optional | bf16 |
+| Stable Cascade (Stage C) | not supported | fp32 required |
+| Wan Video | int8 optional | bf16 |
+| Wan S2V | int8 optional | bf16 |
+| Z-Image | int8 optional | bf16 |
+| Z-Image Omni | int8 optional | bf16 |
+| ZLab I1 | int8 optional | bf16 |
+
+</details>
+
+<details>
+<summary>Checkpointing granularity</summary>
+
+| मॉडल | Gradient Checkpoint | Interval | Segment Stride | Attention Offload |
+| --- | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓ | ✗ |
+| Anima | ✓ | ✗ | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓ | ✗ |
+| Chroma 1 | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓ | ✗ |
+| DeepFloyd IF | ✓ | ✗ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | ✓ | ✗ | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | ✓ | ✓ | ✓ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | ✓ | ✗ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | ✓ | ✓ | ✓ | ✗ |
+| LTX Video 2 | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓ | ✓ |
+| OmniGen | ✓ | ✗ | ✗ | ✗ |
+| PixArt Sigma | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓ | ✗ |
+| Sana | ✓ | ✓ | ✓ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✗ | ✗ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | ✓ | ✗ | ✗ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓ | ✗ |
+| Wan Video | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | ✓ | ✓ | ✓ | ✗ |
+| Z-Image | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | ✓ | ✗ | ✗ | ✗ |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ |
+
+</details>
+
+<details>
+<summary>Flow, distillation, and alignment</summary>
+
+| मॉडल | Prediction | Flow Shift | TwinFlow | Self-Flow | LayerSync | Sliders |
+| --- | --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Anima | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Auraflow | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Boogu-Image | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Chroma 1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | sample | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Cosmos3 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| DeepFloyd IF | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| ERNIE-Image | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Flux.1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | autoregressive next-token | ✗ | ✗ | ✗ | ✗ | ✗ |
+| HiDream | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Hunyuan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Kandinsky 5.0 Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Krea2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video 2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Mage-Flow | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| OmniGen | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| PixArt Sigma | epsilon | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Qwen Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| SD 1.x/2.x (Legacy) | epsilon / v-pred | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Diffusion 3 | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Cascade (Stage C) | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Wan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Z-Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| ZLab I1 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+
+</details>
+
+<details>
+<summary>Text encoders and VAE types</summary>
+
+| मॉडल | Text Encoders | Text Encoder Params | VAE |
+| --- | --- | --- | --- |
+| ACE-Step | UMT5 Encoder | 0.6B | Music DCAE |
+| Anima | Qwen3 0.6B | 0.6B | Qwen Image VAE |
+| Auraflow | Pile T5 | not specified | AutoencoderKL |
+| Boogu-Image | Qwen3-VL | not specified | AutoencoderKL |
+| Chroma 1 | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Cosmos2 | T5 11B | 11B | Wan VAE |
+| Cosmos3 | Cosmos3 reasoner | not specified | Wan/Cosmos VAE |
+| DeepFloyd IF | T5 XXL v1.1 | 11B | None |
+| ERNIE-Image | ERNIE text encoder | not specified | Flux.2 VAE |
+| Flux.1 | CLIP-L/14 + T5 XXL v1.1 | 123M + 11B | AutoencoderKL |
+| Flux.2 | Mistral-Small-3.1-24B | 24B | Flux.2 VAE |
+| HeartMuLa | None | N/A | HeartCodec tokens |
+| HiDream | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 + Llama | 123M + 694M + 11B + not specified | AutoencoderKL |
+| Hunyuan Video | Hunyuan LLM | not specified | Hunyuan Video 3D VAE |
+| Ideogram 4 | Qwen3-VL-8B-Instruct | 8B | Ideogram AutoEncoder |
+| Kandinsky 5.0 Image | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Flux VAE (AutoencoderKL) |
+| Kandinsky 5.0 Video | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Hunyuan Video VAE |
+| Kwai Kolors | ChatGLM-6B | 6B | AutoencoderKL |
+| Krea2 | Qwen3VL | not specified | Qwen Image VAE |
+| LongCat Image | Qwen2.5-VL | 7B | AutoencoderKL |
+| LongCat Video | Qwen2.5-VL | 7B | Wan VAE |
+| LTX Video | T5 XXL v1.1 | 11B | LTX Video VAE |
+| LTX Video 2 | Gemma3 | not specified | LTX Video 2 VAE |
+| Lumina2 | Gemma2 | 2B | AutoencoderKL |
+| Mage-Flow | Qwen3-VL | not specified | Mage-VAE |
+| OmniGen | Integrated OmniGen encoder | not specified | AutoencoderKL |
+| PixArt Sigma | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Qwen Image | Qwen2.5-VL | 7B | Qwen Image VAE |
+| Sana | Gemma2 2B-IT | 2B | Sana AutoencoderDC |
+| Sana Video | Gemma 2 | 2B | Wan VAE |
+| SD 1.x/2.x (Legacy) | CLIP-L/14 | 123M | AutoencoderKL |
+| Stable Diffusion 3 | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 | 123M + 694M + 11B | AutoencoderKL |
+| Stable Diffusion XL | CLIP-L/14 + CLIP-G/14 | 123M + 694M | AutoencoderKL |
+| Stable Cascade (Stage C) | CLIP-ViT-bigG-14 | 694M | Stable Cascade Stage C VAE |
+| Wan Video | UMT5 | not specified | Wan VAE |
+| Wan S2V | UMT5 | not specified | Wan VAE |
+| Z-Image | Qwen3 4B | 4B | AutoencoderKL |
+| Z-Image Omni | Qwen3 4B | 4B | AutoencoderKL |
+| ZLab I1 | T5Gemma 2B | 2B | AutoencoderKL |
+
+</details>
 
-| मॉडल | पैरामीटर | PEFT LoRA | Lycoris | फुल-रैंक | क्वांटाइज़ेशन | मिक्स्ड प्रिसिजन | ग्रैड चेकपॉइंट | फ्लो शिफ्ट | TwinFlow | Self-Flow | LayerSync | Ref Inputs | ControlNet | Sliders† | लाइसेंस | व्यावसायिक उपयोग की अनुमति | गाइड |
-| --- | --- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | --- | :---: | --- |
-| PixArt Sigma | 0.6B–0.9B | ✗ | ✓ | ✓ | int8 वैकल्पिक | bf16 | ✓ | ✗ | ✗ | ✓ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | शर्तें लागू<sup>1</sup> | [SIGMA.md](quickstart/SIGMA.md) |
-| NVLabs Sana | 1.6B–4.8B | ✗ | ✓ | ✓ | int8 वैकल्पिक | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [SANA.md](quickstart/SANA.md) |
-| Kwai Kolors | 2.7B | ✓ | ✓ | ✓ | अनुशंसित नहीं | bf16 | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | शर्तें लागू<sup>7</sup> | [KOLORS.md](quickstart/KOLORS.md) |
-| Stable Diffusion 3 | 2B–8B | ✓ | ✓ | ✓ | int8/fp8/nf4 वैकल्पिक | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Stability AI Community](https://stability.ai/license) | शर्तें लागू<sup>2</sup> | [SD3.md](quickstart/SD3.md) |
-| Flux.1 | 8B–12B | ✓ | ✓ | ✓* | int8/fp8/nf4 वैकल्पिक | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | शर्तें लागू<sup>3</sup> | [FLUX.md](quickstart/FLUX.md) |
-| Flux.2 | 32B | ✓ | ✓ | ✓* | int8/fp8/nf4 वैकल्पिक | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | शर्तें लागू<sup>4</sup> | [FLUX2.md](quickstart/FLUX2.md) |
-| Flux Kontext | 8B–12B | ✓ | ✓ | ✓* | int8/fp8/nf4 वैकल्पिक | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) | नहीं<sup>5</sup> | [FLUX_KONTEXT.md](quickstart/FLUX_KONTEXT.md) |
-| Z-Image Turbo | 6B | ✓ | ✗ | ✓* | int8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [ZIMAGE.md](quickstart/ZIMAGE.md) |
-| Krea2 | - | ✓ | ✗ | ✓* | int8 वैकल्पिक | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✓ opt | ✗ | ✓ | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | शर्तें लागू<sup>6</sup> | [KREA2.md](quickstart/KREA2.hi.md) |
-| Mage-Flow | 4B | ✓ | ✓ | ✓* | int8/fp8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ edit | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | हाँ | [MAGEFLOW.md](quickstart/MAGEFLOW.hi.md) |
-| Boogu-Image 0.1 | - | ✓ | ✓ | ✓* | fp8 वैकल्पिक | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ edit | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [BOOGU_IMAGE.md](quickstart/BOOGU_IMAGE.hi.md) |
-| zlab i1 | 3B | ✓ | ✓ | ✓ | int8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | शर्तें लागू<sup>12</sup> | [ZLAB_i1.md](quickstart/ZLAB_i1.hi.md) |
-| Ideogram 4 | 9B | ✓ | ✓ | ✓* | fp8 डिफ़ॉल्ट, nf4 वैकल्पिक | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | नहीं<sup>5</sup> | [IDEOGRAM4.md](quickstart/IDEOGRAM4.hi.md) |
-| ERNIE-Image | - | ✓ | ✓ | ✓* | int8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [ERNIE.md](quickstart/ERNIE.hi.md) |
-| ACE-Step | 3.5B | ✓ | ✓ | ✓* | int8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B) / [MIT](https://huggingface.co/ACE-Step/Ace-Step1.5) | हाँ | [ACE_STEP.md](quickstart/ACE_STEP.md) |
-| Chroma 1 | 8.9B | ✓ | ✓ | ✓* | int8/fp8/nf4 वैकल्पिक | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [CHROMA.md](quickstart/CHROMA.md) |
-| Auraflow | 6B | ✓ | ✓ | ✓* | int8/fp8/nf4 वैकल्पिक | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) / [Pony License](https://huggingface.co/purplesmartai/pony-v7-base/blob/main/LICENSE) | शर्तें लागू<sup>8</sup> | [AURAFLOW.md](quickstart/AURAFLOW.md) |
-| HiDream I1 | 17B (8.5B MoE) | ✓ | ✓ | ✓* | int8/fp8/nf4 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [MIT](https://opensource.org/license/mit) | हाँ | [HIDREAM.md](quickstart/HIDREAM.md) |
-| OmniGen | 3.8B | ✓ | ✓ | ✓ | int8/fp8 वैकल्पिक | bf16 | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | हाँ | [OMNIGEN.md](quickstart/OMNIGEN.md) |
-| Stable Diffusion XL | 2.6B | ✓ | ✓ | ✓ | अनुशंसित नहीं | bf16 | ✓ | ✗ | ✗ | ✗ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | शर्तें लागू<sup>1</sup> | [SDXL.md](quickstart/SDXL.md) |
-| Lumina2 | 2B | ✓ | ✓ | ✓ | int8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [LUMINA2.md](quickstart/LUMINA2.md) |
-| Cosmos2 | 2B | ✓ | ✓ | ✓ | अनुशंसित नहीं | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) | हाँ<sup>9</sup> | [COSMOS2IMAGE.md](quickstart/COSMOS2IMAGE.md) |
-| Cosmos3 | 16B-65B | ✓ | ✓ | ✓* | no_change first | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | audio opt | ✗ | ✓ | [OpenMDW 1.1](https://github.com/OpenMDW/openmdw/blob/main/1.1/LICENSE.OpenMDW-1.1) | हाँ | [COSMOS3.md](quickstart/COSMOS3.hi.md) |
-| LTX Video | ~2.5B | ✓ | ✓ | ✓ | int8/fp8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [LTX Video OpenRAIL-M](https://huggingface.co/Lightricks/LTX-Video-0.9.5/blob/main/ltx-video-2b-v0.9.5.license.txt) | शर्तें लागू<sup>10</sup> | [LTXVIDEO.md](quickstart/LTXVIDEO.md) |
-| LTX Video 2 | 19B | ✓ | ✓ | ✓* | int8/fp8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [LTX-2 Community](https://ltx.io/model/license) | शर्तें लागू<sup>10</sup> | [LTXVIDEO2.md](quickstart/LTXVIDEO2.md) |
-| Hunyuan Video 1.5 | 8.3B | ✓ | ✓ | ✓* | int8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [Tencent Hunyuan Community](https://huggingface.co/tencent/HunyuanVideo-1.5/blob/main/LICENSE) | शर्तें लागू<sup>11</sup> | [HUNYUANVIDEO.md](quickstart/HUNYUANVIDEO.md) |
-| SanaVideo | 2B | ✓ | ✓ | ✓* | int8/fp8 वैकल्पिक | bf16 | ✓ | ✗ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [SANAVIDEO.md](quickstart/SANAVIDEO.hi.md) |
-| Wan 2.x | 1.3B–14B | ✓ | ✓ | ✓* | int8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [WAN.md](quickstart/WAN.md) |
-| Wan 2.2 S2V | 14B | ✓ | ✓ | ✓* | int8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [WAN_S2V.md](quickstart/WAN_S2V.md) |
-| Qwen Image | 20B | ✓ | ✓ | ✓* | **आवश्यक** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [QWEN_IMAGE.md](quickstart/QWEN_IMAGE.md) |
-| Qwen Image Edit | 20B | ✓ | ✓ | ✓* | **आवश्यक** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [QWEN_EDIT.md](quickstart/QWEN_EDIT.md) |
-| Stable Cascade (C) | 1B, 3.6B prior | ✓ | ✓ | ✓* | समर्थित नहीं | fp32 (आवश्यक) | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | नहीं<sup>5</sup> | [STABLE_CASCADE_C.md](quickstart/STABLE_CASCADE_C.md) |
-| Kandinsky 5.0 Image | 6B (lite) | ✓ | ✓ | ✓* | int8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ I2I | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | हाँ | [KANDINSKY5_IMAGE.md](quickstart/KANDINSKY5_IMAGE.md) |
-| Kandinsky 5.0 Video | 2B (lite), 19B (pro) | ✓ | ✓ | ✓* | int8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | हाँ | [KANDINSKY5_VIDEO.md](quickstart/KANDINSKY5_VIDEO.md) |
-| LongCat-Video | 13.6B | ✓ | ✓ | ✓* | int8/fp8 वैकल्पिक | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | हाँ | [LONGCAT_VIDEO.md](quickstart/LONGCAT_VIDEO.md) |
-| LongCat-Video Edit | 13.6B | ✓ | ✓ | ✓* | int8/fp8 वैकल्पिक | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | हाँ | [LONGCAT_VIDEO_EDIT.md](quickstart/LONGCAT_VIDEO_EDIT.md) |
-| LongCat-Image | 6B | ✓ | ✓ | ✓* | int8/fp8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [LONGCAT_IMAGE.md](quickstart/LONGCAT_IMAGE.md) |
-| LongCat-Image Edit | 6B | ✓ | ✓ | ✓* | int8/fp8 वैकल्पिक | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [LONGCAT_EDIT.md](quickstart/LONGCAT_EDIT.md) |
-
-*✓ = समर्थित, ✓* = फुल‑रैंक के लिए DeepSpeed/FSDP2 आवश्यक, ✗ = समर्थित नहीं, `✓+` VRAM दबाव के कारण checkpointing की सिफ़ारिश को दर्शाता है। Ref Inputs सिर्फ मौजूदा reference/edit/I2V conditioning paths को दिखाता है; `opt` वैकल्पिक है और `req` edit/I2V flavour के लिए आवश्यक है। TwinFlow ✓ का अर्थ है `twinflow_enabled=true` होने पर native support (diffusion मॉडल्स को `diff2flow_enabled+twinflow_allow_diff2flow` चाहिए)। Self-Flow ✓ का अर्थ है `crepa_enabled=true`, `crepa_feature_source=self_flow`, `use_ema=true`, और `crepa_teacher_block_index` सेट होने पर native support। LayerSync ✓ का अर्थ है कि backbone self‑alignment के लिए transformer hidden states उपलब्ध कराता है; ✗ UNet‑style backbones को दर्शाता है जिनमें वह buffer नहीं होता। †Sliders LoRA और LyCORIS (full‑rank LyCORIS “full” सहित) पर लागू होते हैं।*
-
-**लाइसेंस नोट्स:** व्यावसायिक उपयोग की स्थिति model weights, derivative checkpoints, fine-tunes, और hosted model use को कवर करती है। Generated outputs के अधिकार अलग हो सकते हैं; commercial deployment से पहले linked license text पढ़ें।
-
-<sup>1</sup> OpenRAIL-style licenses आम तौर पर commercial use की अनुमति देती हैं, लेकिन usage restrictions model और derivatives के साथ बनी रहती हैं।
-
-<sup>2</sup> Stability AI Community License revenue threshold से नीचे qualify करने वाले users के लिए उपलब्ध है; बड़े commercial use के लिए Stability enterprise terms चाहिए।
-
-<sup>3</sup> Flux.1 flavour के अनुसार बदलता है: Schnell और LibreFlux Apache-2.0 हैं, जबकि Dev, Krea, और Kontext BFL non-commercial terms का उपयोग करते हैं; commercial use से पहले FluxBooru upstream metadata देखें।
-
-<sup>4</sup> Flux.2 flavour के अनुसार बदलता है: Klein 4B Apache-2.0 है, जबकि Dev और Klein 9B BFL non-commercial terms का उपयोग करते हैं।
-
-<sup>5</sup> Public non-commercial model terms अलग license के बिना weights, derivative checkpoints, या hosted model services के commercial use की अनुमति नहीं देते।
-
-<sup>6</sup> Krea 2 Community License केवल revenue और safety/filtering requirements के तहत commercial use की अनुमति देती है; अन्यथा enterprise license चाहिए।
-
-<sup>7</sup> Kolors model या derivatives का commercial use करने के लिए licensor से explicit permission माँगनी और प्राप्त करनी होती है।
-
-<sup>8</sup> AuraFlow Apache-2.0 upstream flavours और अलग custom license वाले Pony flavour को support करता है; selected flavour देखें।
-
-<sup>9</sup> NVIDIA Open Model License commercial use की अनुमति देती है, लेकिन agreement, acceptable-use, और export-control terms शामिल हैं।
-
-<sup>10</sup> LTX Video 0.9.5 OpenRAIL-M का उपयोग करता है; LTX Video 2 commercial use के लिए revenue threshold वाले LTX community terms का उपयोग करता है।
-
-<sup>11</sup> Tencent Hunyuan Community License में territorial exclusions और बहुत बड़े services के लिए commercial threshold शामिल है।
-
-<sup>12</sup> यह mirror standard license text के बिना `license: other` publish करता है; commercial use से पहले upstream terms देखें।
-
-> ℹ️ Wan quickstart में 2.1 + 2.2 stage presets और time‑embedding toggle शामिल है। Flux Kontext में Flux.1 के ऊपर बने editing वर्कफ़्लो शामिल हैं।
-
-> ⚠️ ये क्विकस्टार्ट living documents हैं। नए मॉडल आने या प्रशिक्षण रेसिपीज़ सुधरने के साथ समय‑समय पर अपडेट की उम्मीद करें।
+*✓ = supported, ✓* = supported लेकिन full-rank training के लिए आम तौर पर DeepSpeed/FSDP2 चाहिए, ✗ = not supported. Ref Inputs मौजूदा reference/edit/I2V conditioning paths को दिखाता है; `opt` optional और `req` edit/I2V flavour में required है.*
+*TwinFlow native है जब `twinflow_enabled=true`; diffusion models को अभी भी `diff2flow_enabled=true` और `twinflow_allow_diff2flow=true` चाहिए। Self-Flow CREPA self-flow support है। LayerSync alignment के लिए hidden states expose करने वाले backbones को दिखाता है.*
 
 ### तेज़ रास्ते: Z-Image Turbo और Flux Schnell
 
diff --git a/documentation/QUICKSTART.ja.md b/documentation/QUICKSTART.ja.md
index d465b6bac..e26c33129 100644
--- a/documentation/QUICKSTART.ja.md
+++ b/documentation/QUICKSTART.ja.md
@@ -2,84 +2,291 @@
 
 **注意**: より高度な設定については、[チュートリアル](TUTORIAL.md)および[オプションリファレンス](OPTIONS.md)を参照してください。
 
-## 機能互換性
+## モデル別クイックスタートガイド
 
-完全かつ最も正確な機能マトリックスについては、[メインREADME](https://github.com/bghira/SimpleTuner#model-architecture-support)を参照してください。
+| モデル | パラメータ | ガイド |
+| --- | --- | --- |
+| ACE-Step | 3.5B | [ACE_STEP.ja.md](quickstart/ACE_STEP.ja.md) |
+| Anima | Not specified | 専用ガイドなし |
+| Auraflow | 6B | [AURAFLOW.ja.md](quickstart/AURAFLOW.ja.md) |
+| Boogu-Image | Not specified | [BOOGU_IMAGE.ja.md](quickstart/BOOGU_IMAGE.ja.md) |
+| Chroma 1 | 8.9B | [CHROMA.ja.md](quickstart/CHROMA.ja.md) |
+| Cosmos2 | 2B-14B | [COSMOS2IMAGE.ja.md](quickstart/COSMOS2IMAGE.ja.md) |
+| Cosmos3 | 16B-65B | [COSMOS3.ja.md](quickstart/COSMOS3.ja.md) |
+| DeepFloyd IF | 0.4B-4.3B stages | 専用ガイドなし |
+| ERNIE-Image | Not specified | [ERNIE.ja.md](quickstart/ERNIE.ja.md) |
+| Flux.1 | 8B-12B | [FLUX.ja.md](quickstart/FLUX.ja.md)<br>[FLUX_KONTEXT.ja.md](quickstart/FLUX_KONTEXT.ja.md) |
+| Flux.2 | 4B-32B | [FLUX2.ja.md](quickstart/FLUX2.ja.md) |
+| HeartMuLa | 3B | [HEARTMULA.ja.md](quickstart/HEARTMULA.ja.md) |
+| HiDream | 17B (8.5B MoE) | [HIDREAM.ja.md](quickstart/HIDREAM.ja.md) |
+| Hunyuan Video | 8.3B | [HUNYUANVIDEO.ja.md](quickstart/HUNYUANVIDEO.ja.md) |
+| Ideogram 4 | 9B | [IDEOGRAM4.ja.md](quickstart/IDEOGRAM4.ja.md) |
+| Kandinsky 5.0 Image | 6B (lite) | [KANDINSKY5_IMAGE.ja.md](quickstart/KANDINSKY5_IMAGE.ja.md) |
+| Kandinsky 5.0 Video | 2B lite, 19B pro | [KANDINSKY5_VIDEO.ja.md](quickstart/KANDINSKY5_VIDEO.ja.md) |
+| Kwai Kolors | 2.7B | [KOLORS.ja.md](quickstart/KOLORS.ja.md) |
+| Krea2 | Not specified | [KREA2.ja.md](quickstart/KREA2.ja.md) |
+| LongCat Image | 6B | [LONGCAT_IMAGE.ja.md](quickstart/LONGCAT_IMAGE.ja.md)<br>[LONGCAT_EDIT.ja.md](quickstart/LONGCAT_EDIT.ja.md) |
+| LongCat Video | 13.6B | [LONGCAT_VIDEO.ja.md](quickstart/LONGCAT_VIDEO.ja.md)<br>[LONGCAT_VIDEO_EDIT.ja.md](quickstart/LONGCAT_VIDEO_EDIT.ja.md) |
+| LTX Video | ~2.5B | [LTXVIDEO.ja.md](quickstart/LTXVIDEO.ja.md) |
+| LTX Video 2 | 19B | [LTXVIDEO2.ja.md](quickstart/LTXVIDEO2.ja.md) |
+| Lumina2 | 2B | [LUMINA2.ja.md](quickstart/LUMINA2.ja.md) |
+| Mage-Flow | 4B | [MAGEFLOW.ja.md](quickstart/MAGEFLOW.ja.md) |
+| OmniGen | 3.8B | [OMNIGEN.ja.md](quickstart/OMNIGEN.ja.md) |
+| PixArt Sigma | 0.6B-0.9B | [SIGMA.ja.md](quickstart/SIGMA.ja.md) |
+| Qwen Image | 20B | [QWEN_IMAGE.ja.md](quickstart/QWEN_IMAGE.ja.md)<br>[QWEN_EDIT.ja.md](quickstart/QWEN_EDIT.ja.md) |
+| Sana | 0.6B-4.8B | [SANA.ja.md](quickstart/SANA.ja.md) |
+| Sana Video | 2B | [SANAVIDEO.ja.md](quickstart/SANAVIDEO.ja.md) |
+| SD 1.x/2.x (Legacy) | 0.9B | 専用ガイドなし |
+| Stable Diffusion 3 | 2B-8B | [SD3.ja.md](quickstart/SD3.ja.md) |
+| Stable Diffusion XL | 3.5B | [SDXL.ja.md](quickstart/SDXL.ja.md) |
+| Stable Cascade (Stage C) | 1B, 3.6B prior | [STABLE_CASCADE_C.ja.md](quickstart/STABLE_CASCADE_C.ja.md) |
+| Wan Video | 1.3B-14B | [WAN.ja.md](quickstart/WAN.ja.md) |
+| Wan S2V | 14B | [WAN_S2V.ja.md](quickstart/WAN_S2V.ja.md) |
+| Z-Image | 6B | [ZIMAGE.ja.md](quickstart/ZIMAGE.ja.md) |
+| Z-Image Omni | 6B | [ZIMAGE.ja.md](quickstart/ZIMAGE.ja.md) |
+| ZLab I1 | 3B | [ZLAB_i1.ja.md](quickstart/ZLAB_i1.ja.md) |
 
-## モデルクイックスタートガイド
+## 機能互換性
 
-| モデル | パラメータ数 | PEFT LoRA | Lycoris | Full-Rank | 量子化 | 混合精度 | Grad Checkpoint | Flow Shift | TwinFlow | Self-Flow | LayerSync | Ref Inputs | ControlNet | Sliders† | ライセンス | 商用利用 | ガイド |
-| --- | --- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | --- | :---: | --- |
-| PixArt Sigma | 0.6B–0.9B | ✗ | ✓ | ✓ | int8 オプション | bf16 | ✓ | ✗ | ✗ | ✓ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | 条件付き<sup>1</sup> | [SIGMA.md](quickstart/SIGMA.md) |
-| NVLabs Sana | 1.6B–4.8B | ✗ | ✓ | ✓ | int8 オプション | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [SANA.md](quickstart/SANA.md) |
-| Kwai Kolors | 2.7B | ✓ | ✓ | ✓ | 非推奨 | bf16 | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | 条件付き<sup>7</sup> | [KOLORS.md](quickstart/KOLORS.md) |
-| Stable Diffusion 3 | 2B–8B | ✓ | ✓ | ✓ | int8/fp8/nf4 オプション | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Stability AI Community](https://stability.ai/license) | 条件付き<sup>2</sup> | [SD3.md](quickstart/SD3.md) |
-| Flux.1 | 8B–12B | ✓ | ✓ | ✓* | int8/fp8/nf4 オプション | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 条件付き<sup>3</sup> | [FLUX.md](quickstart/FLUX.md) |
-| Flux.2 | 32B | ✓ | ✓ | ✓* | int8/fp8/nf4 オプション | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 条件付き<sup>4</sup> | [FLUX2.md](quickstart/FLUX2.md) |
-| Flux Kontext | 8B–12B | ✓ | ✓ | ✓* | int8/fp8/nf4 オプション | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) | いいえ<sup>5</sup> | [FLUX_KONTEXT.md](quickstart/FLUX_KONTEXT.md) |
-| Z-Image Turbo | 6B | ✓ | ✗ | ✓* | int8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [ZIMAGE.md](quickstart/ZIMAGE.md) |
-| Krea2 | - | ✓ | ✗ | ✓* | int8 オプション | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✓ opt | ✗ | ✓ | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | 条件付き<sup>6</sup> | [KREA2.md](quickstart/KREA2.ja.md) |
-| Mage-Flow | 4B | ✓ | ✓ | ✓* | int8/fp8 オプション | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ edit | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | はい | [MAGEFLOW.md](quickstart/MAGEFLOW.ja.md) |
-| Boogu-Image 0.1 | - | ✓ | ✓ | ✓* | fp8 オプション | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ edit | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [BOOGU_IMAGE.md](quickstart/BOOGU_IMAGE.ja.md) |
-| zlab i1 | 3B | ✓ | ✓ | ✓ | int8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | 条件付き<sup>12</sup> | [ZLAB_i1.md](quickstart/ZLAB_i1.ja.md) |
-| Ideogram 4 | 9B | ✓ | ✓ | ✓* | fp8 デフォルト、nf4 オプション | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | いいえ<sup>5</sup> | [IDEOGRAM4.md](quickstart/IDEOGRAM4.ja.md) |
-| ERNIE-Image | - | ✓ | ✓ | ✓* | int8 オプション | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [ERNIE.md](quickstart/ERNIE.ja.md) |
-| ACE-Step | 3.5B | ✓ | ✓ | ✓* | int8 オプション | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B) / [MIT](https://huggingface.co/ACE-Step/Ace-Step1.5) | はい | [ACE_STEP.md](quickstart/ACE_STEP.md) |
-| Chroma 1 | 8.9B | ✓ | ✓ | ✓* | int8/fp8/nf4 オプション | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [CHROMA.md](quickstart/CHROMA.md) |
-| Auraflow | 6B | ✓ | ✓ | ✓* | int8/fp8/nf4 オプション | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) / [Pony License](https://huggingface.co/purplesmartai/pony-v7-base/blob/main/LICENSE) | 条件付き<sup>8</sup> | [AURAFLOW.md](quickstart/AURAFLOW.md) |
-| HiDream I1 | 17B (8.5B MoE) | ✓ | ✓ | ✓* | int8/fp8/nf4 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [MIT](https://opensource.org/license/mit) | はい | [HIDREAM.md](quickstart/HIDREAM.md) |
-| OmniGen | 3.8B | ✓ | ✓ | ✓ | int8/fp8 オプション | bf16 | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | はい | [OMNIGEN.md](quickstart/OMNIGEN.md) |
-| Stable Diffusion XL | 2.6B | ✓ | ✓ | ✓ | 非推奨 | bf16 | ✓ | ✗ | ✗ | ✗ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | 条件付き<sup>1</sup> | [SDXL.md](quickstart/SDXL.md) |
-| Lumina2 | 2B | ✓ | ✓ | ✓ | int8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [LUMINA2.md](quickstart/LUMINA2.md) |
-| Cosmos2 | 2B | ✓ | ✓ | ✓ | 非推奨 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) | はい<sup>9</sup> | [COSMOS2IMAGE.md](quickstart/COSMOS2IMAGE.md) |
-| Cosmos3 | 16B-65B | ✓ | ✓ | ✓* | no_change first | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | audio opt | ✗ | ✓ | [OpenMDW 1.1](https://github.com/OpenMDW/openmdw/blob/main/1.1/LICENSE.OpenMDW-1.1) | はい | [COSMOS3.md](quickstart/COSMOS3.ja.md) |
-| LTX Video | ~2.5B | ✓ | ✓ | ✓ | int8/fp8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [LTX Video OpenRAIL-M](https://huggingface.co/Lightricks/LTX-Video-0.9.5/blob/main/ltx-video-2b-v0.9.5.license.txt) | 条件付き<sup>10</sup> | [LTXVIDEO.md](quickstart/LTXVIDEO.md) |
-| LTX Video 2 | 19B | ✓ | ✓ | ✓* | int8/fp8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [LTX-2 Community](https://ltx.io/model/license) | 条件付き<sup>10</sup> | [LTXVIDEO2.md](quickstart/LTXVIDEO2.md) |
-| Hunyuan Video 1.5 | 8.3B | ✓ | ✓ | ✓* | int8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [Tencent Hunyuan Community](https://huggingface.co/tencent/HunyuanVideo-1.5/blob/main/LICENSE) | 条件付き<sup>11</sup> | [HUNYUANVIDEO.md](quickstart/HUNYUANVIDEO.md) |
-| SanaVideo | 2B | ✓ | ✓ | ✓* | int8/fp8 オプション | bf16 | ✓ | ✗ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [SANAVIDEO.md](quickstart/SANAVIDEO.ja.md) |
-| Wan 2.x | 1.3B–14B | ✓ | ✓ | ✓* | int8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [WAN.md](quickstart/WAN.md) |
-| Wan 2.2 S2V | 14B | ✓ | ✓ | ✓* | int8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [WAN_S2V.md](quickstart/WAN_S2V.md) |
-| Qwen Image | 20B | ✓ | ✓ | ✓* | **必須** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [QWEN_IMAGE.md](quickstart/QWEN_IMAGE.md) |
-| Qwen Image Edit | 20B | ✓ | ✓ | ✓* | **必須** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [QWEN_EDIT.md](quickstart/QWEN_EDIT.md) |
-| Stable Cascade (C) | 1B, 3.6B prior | ✓ | ✓ | ✓* | 非対応 | fp32 (必須) | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | いいえ<sup>5</sup> | [STABLE_CASCADE_C.md](quickstart/STABLE_CASCADE_C.md) |
-| Kandinsky 5.0 Image | 6B (lite) | ✓ | ✓ | ✓* | int8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ I2I | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | はい | [KANDINSKY5_IMAGE.md](quickstart/KANDINSKY5_IMAGE.md) |
-| Kandinsky 5.0 Video | 2B (lite), 19B (pro) | ✓ | ✓ | ✓* | int8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | はい | [KANDINSKY5_VIDEO.md](quickstart/KANDINSKY5_VIDEO.md) |
-| LongCat-Video | 13.6B | ✓ | ✓ | ✓* | int8/fp8 オプション | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | はい | [LONGCAT_VIDEO.md](quickstart/LONGCAT_VIDEO.md) |
-| LongCat-Video Edit | 13.6B | ✓ | ✓ | ✓* | int8/fp8 オプション | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | はい | [LONGCAT_VIDEO_EDIT.md](quickstart/LONGCAT_VIDEO_EDIT.md) |
-| LongCat-Image | 6B | ✓ | ✓ | ✓* | int8/fp8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [LONGCAT_IMAGE.md](quickstart/LONGCAT_IMAGE.md) |
-| LongCat-Image Edit | 6B | ✓ | ✓ | ✓* | int8/fp8 オプション | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [LONGCAT_EDIT.md](quickstart/LONGCAT_EDIT.md) |
+完全な互換性マトリクスは、読みやすいように機能領域ごとに分割しています。
 
-*✓ = サポート、✓* = Full-RankにはDeepSpeed/FSDP2が必要、✗ = 非サポート、`✓+`はVRAMプレッシャーによりチェックポイントが推奨されることを示します。Ref Inputs は既存の参照/編集/I2V 条件パスのみを示し、`opt` は任意、`req` は編集/I2V flavour で必須であることを示します。TwinFlow ✓は`twinflow_enabled=true`のときのネイティブサポートを意味します（拡散モデルには`diff2flow_enabled+twinflow_allow_diff2flow`が必要）。Self-Flow ✓は`crepa_enabled=true`、`crepa_feature_source=self_flow`、`use_ema=true`、および`crepa_teacher_block_index`設定時のネイティブサポートを意味します。LayerSync ✓はバックボーンがセルフアライメント用のトランスフォーマー隠れ状態を公開していることを意味し、✗はそのバッファを持たないUNetスタイルのバックボーンを示します。†SlidersはLoRAおよびLyCORIS（Full-Rank LyCORIS "full"を含む）に適用されます。*
+<details>
+<summary>トレーニングサポート</summary>
 
-**ライセンス注記:** 商用利用の表示はモデル重み、派生チェックポイント、fine-tune、ホスト型モデル利用を対象にしています。生成出力の権利は異なる場合があります。商用展開前にリンク先のライセンス本文を確認してください。
+| モデル | PEFT LoRA | LyCORIS | フルランク | ControlNet | Ref Inputs |
+| --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Anima | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| Chroma 1 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓* | ✗ | audio opt |
+| DeepFloyd IF | ✓ | ✓ | ✓ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓* | ✓ | ✓ opt (Kontext) |
+| Flux.2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| HeartMuLa | ✓ | ✓ | ✓* | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Ideogram 4 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓* | ✗ | ✓ I2I |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Kwai Kolors | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| LongCat Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| LongCat Video | ✓ | ✓ | ✓* | ✗ | ✓ opt/edit |
+| LTX Video | ✓ | ✓ | ✓ | ✗ | ✓ I2V |
+| LTX Video 2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| OmniGen | ✓ | ✓ | ✓ | ✗ | ✗ |
+| PixArt Sigma | ✗ | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| Sana | ✗ | ✓ | ✓ | ✗ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Stable Diffusion XL | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Wan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V/VACE |
+| Wan S2V | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image Omni | ✓ | ✓ | ✓* | ✗ | ✓ opt (Edit) |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ | ✗ |
 
-<sup>1</sup> OpenRAIL 系ライセンスは通常、商用利用を許可しますが、モデルと派生物には利用制限が残ります。
+</details>
 
-<sup>2</sup> Stability AI Community License は収益しきい値未満の対象ユーザー向けです。より大きな商用利用には Stability のエンタープライズ条件が必要です。
+<details>
+<summary>精度レベルのサポート</summary>
 
-<sup>3</sup> Flux.1 は flavour により異なります。Schnell と LibreFlux は Apache-2.0、Dev、Krea、Kontext は BFL の非商用条件です。FluxBooru は商用利用前に upstream metadata を確認してください。
+| モデル | 量子化 | 混合精度 |
+| --- | --- | --- |
+| ACE-Step | int8 optional | bf16 |
+| Anima | not specified | bf16 |
+| Auraflow | int8/fp8/nf4 optional | bf16 |
+| Boogu-Image | fp8 optional | bf16 |
+| Chroma 1 | int8/fp8/nf4 optional | bf16 |
+| Cosmos2 | int8 optional | bf16 |
+| Cosmos3 | no_change first; int8 optional | bf16 |
+| DeepFloyd IF | not recommended | bf16 |
+| ERNIE-Image | int8 optional | bf16 |
+| Flux.1 | int8/fp8/nf4 optional | bf16 |
+| Flux.2 | int8/fp8/nf4 optional | bf16 |
+| HeartMuLa | int8 optional | bf16 |
+| HiDream | int8/fp8/nf4 optional | bf16 |
+| Hunyuan Video | int8 optional | bf16 |
+| Ideogram 4 | fp8 default, nf4 optional | bf16 |
+| Kandinsky 5.0 Image | int8 optional | bf16 |
+| Kandinsky 5.0 Video | int8 optional | bf16 |
+| Kwai Kolors | not recommended | bf16 |
+| Krea2 | int8 optional | bf16 |
+| LongCat Image | int8/fp8 optional | bf16 |
+| LongCat Video | int8/fp8 optional | bf16 |
+| LTX Video | int8/fp8 optional | bf16 |
+| LTX Video 2 | int8/fp8 optional | bf16 |
+| Lumina2 | int8 optional | bf16 |
+| Mage-Flow | fp8 optional | bf16 |
+| OmniGen | int8/fp8 optional | bf16 |
+| PixArt Sigma | int8 optional | bf16 |
+| Qwen Image | required (int8/nf4) | bf16 |
+| Sana | int8 optional | bf16 |
+| Sana Video | not recommended for full | bf16 |
+| SD 1.x/2.x (Legacy) | int8/nf4 optional | bf16 |
+| Stable Diffusion 3 | int8/fp8/nf4 optional | bf16 |
+| Stable Diffusion XL | int8/nf4 optional | bf16 |
+| Stable Cascade (Stage C) | not supported | fp32 required |
+| Wan Video | int8 optional | bf16 |
+| Wan S2V | int8 optional | bf16 |
+| Z-Image | int8 optional | bf16 |
+| Z-Image Omni | int8 optional | bf16 |
+| ZLab I1 | int8 optional | bf16 |
 
-<sup>4</sup> Flux.2 は flavour により異なります。Klein 4B は Apache-2.0、Dev と Klein 9B は BFL の非商用条件です。
+</details>
 
-<sup>5</sup> 公開されている非商用モデル条件では、別ライセンスなしに重み、派生チェックポイント、ホスト型モデルサービスを商用利用できません。
+<details>
+<summary>チェックポイント粒度</summary>
 
-<sup>6</sup> Krea 2 Community License は収益および安全性/フィルタリング要件を満たす場合のみ商用利用を許可します。それ以外はエンタープライズライセンスが必要です。
+| モデル | Gradient Checkpoint | Interval | Segment Stride | Attention Offload |
+| --- | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓ | ✗ |
+| Anima | ✓ | ✗ | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓ | ✗ |
+| Chroma 1 | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓ | ✗ |
+| DeepFloyd IF | ✓ | ✗ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | ✓ | ✗ | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | ✓ | ✓ | ✓ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | ✓ | ✗ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | ✓ | ✓ | ✓ | ✗ |
+| LTX Video 2 | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓ | ✓ |
+| OmniGen | ✓ | ✗ | ✗ | ✗ |
+| PixArt Sigma | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓ | ✗ |
+| Sana | ✓ | ✓ | ✓ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✗ | ✗ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | ✓ | ✗ | ✗ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓ | ✗ |
+| Wan Video | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | ✓ | ✓ | ✓ | ✗ |
+| Z-Image | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | ✓ | ✗ | ✗ | ✗ |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ |
 
-<sup>7</sup> Kolors のモデルまたは派生物の商用利用には、ライセンサーへの申請と明示的な許可が必要です。
+</details>
 
-<sup>8</sup> AuraFlow は Apache-2.0 の upstream flavour と、別のカスタムライセンスを持つ Pony flavour をサポートします。選択した flavour を確認してください。
+<details>
+<summary>Flow・蒸留・アラインメント</summary>
 
-<sup>9</sup> NVIDIA Open Model License は商用利用を許可しますが、契約、利用許諾ポリシー、輸出管理条件を含みます。
+| モデル | Prediction | Flow Shift | TwinFlow | Self-Flow | LayerSync | Sliders |
+| --- | --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Anima | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Auraflow | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Boogu-Image | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Chroma 1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | sample | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Cosmos3 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| DeepFloyd IF | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| ERNIE-Image | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Flux.1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | autoregressive next-token | ✗ | ✗ | ✗ | ✗ | ✗ |
+| HiDream | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Hunyuan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Kandinsky 5.0 Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Krea2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video 2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Mage-Flow | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| OmniGen | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| PixArt Sigma | epsilon | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Qwen Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| SD 1.x/2.x (Legacy) | epsilon / v-pred | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Diffusion 3 | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Cascade (Stage C) | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Wan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Z-Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| ZLab I1 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
 
-<sup>10</sup> LTX Video 0.9.5 は OpenRAIL-M、LTX Video 2 は商用利用に収益しきい値がある LTX community terms を使用します。
+</details>
 
-<sup>11</sup> Tencent Hunyuan Community License には地域除外と、非常に大規模なサービス向けの商用しきい値があります。
+<details>
+<summary>テキストエンコーダーと VAE タイプ</summary>
 
-<sup>12</sup> この mirror は標準ライセンス本文なしで `license: other` を公開しています。商用利用前に upstream terms を確認してください。
+| モデル | Text Encoders | Text Encoder Params | VAE |
+| --- | --- | --- | --- |
+| ACE-Step | UMT5 Encoder | 0.6B | Music DCAE |
+| Anima | Qwen3 0.6B | 0.6B | Qwen Image VAE |
+| Auraflow | Pile T5 | not specified | AutoencoderKL |
+| Boogu-Image | Qwen3-VL | not specified | AutoencoderKL |
+| Chroma 1 | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Cosmos2 | T5 11B | 11B | Wan VAE |
+| Cosmos3 | Cosmos3 reasoner | not specified | Wan/Cosmos VAE |
+| DeepFloyd IF | T5 XXL v1.1 | 11B | None |
+| ERNIE-Image | ERNIE text encoder | not specified | Flux.2 VAE |
+| Flux.1 | CLIP-L/14 + T5 XXL v1.1 | 123M + 11B | AutoencoderKL |
+| Flux.2 | Mistral-Small-3.1-24B | 24B | Flux.2 VAE |
+| HeartMuLa | None | N/A | HeartCodec tokens |
+| HiDream | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 + Llama | 123M + 694M + 11B + not specified | AutoencoderKL |
+| Hunyuan Video | Hunyuan LLM | not specified | Hunyuan Video 3D VAE |
+| Ideogram 4 | Qwen3-VL-8B-Instruct | 8B | Ideogram AutoEncoder |
+| Kandinsky 5.0 Image | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Flux VAE (AutoencoderKL) |
+| Kandinsky 5.0 Video | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Hunyuan Video VAE |
+| Kwai Kolors | ChatGLM-6B | 6B | AutoencoderKL |
+| Krea2 | Qwen3VL | not specified | Qwen Image VAE |
+| LongCat Image | Qwen2.5-VL | 7B | AutoencoderKL |
+| LongCat Video | Qwen2.5-VL | 7B | Wan VAE |
+| LTX Video | T5 XXL v1.1 | 11B | LTX Video VAE |
+| LTX Video 2 | Gemma3 | not specified | LTX Video 2 VAE |
+| Lumina2 | Gemma2 | 2B | AutoencoderKL |
+| Mage-Flow | Qwen3-VL | not specified | Mage-VAE |
+| OmniGen | Integrated OmniGen encoder | not specified | AutoencoderKL |
+| PixArt Sigma | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Qwen Image | Qwen2.5-VL | 7B | Qwen Image VAE |
+| Sana | Gemma2 2B-IT | 2B | Sana AutoencoderDC |
+| Sana Video | Gemma 2 | 2B | Wan VAE |
+| SD 1.x/2.x (Legacy) | CLIP-L/14 | 123M | AutoencoderKL |
+| Stable Diffusion 3 | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 | 123M + 694M + 11B | AutoencoderKL |
+| Stable Diffusion XL | CLIP-L/14 + CLIP-G/14 | 123M + 694M | AutoencoderKL |
+| Stable Cascade (Stage C) | CLIP-ViT-bigG-14 | 694M | Stable Cascade Stage C VAE |
+| Wan Video | UMT5 | not specified | Wan VAE |
+| Wan S2V | UMT5 | not specified | Wan VAE |
+| Z-Image | Qwen3 4B | 4B | AutoencoderKL |
+| Z-Image Omni | Qwen3 4B | 4B | AutoencoderKL |
+| ZLab I1 | T5Gemma 2B | 2B | AutoencoderKL |
 
-> ℹ️ Wanクイックスタートには2.1 + 2.2ステージプリセットと時間埋め込みトグルが含まれます。Flux Kontextは、Flux.1をベースに構築された編集ワークフローをカバーします。
+</details>
 
-> ⚠️ これらのクイックスタートは生きたドキュメントです。新しいモデルの登場やトレーニングレシピの改善に伴い、時折更新されることがあります。
+*✓ = サポート、✓* = サポートされていますが、full-rank training では通常 DeepSpeed/FSDP2 が必要、✗ = 未サポート。Ref Inputs は既存の reference/edit/I2V conditioning path を示します。`opt` は任意、`req` は edit/I2V flavour で必須です。*
+*TwinFlow は `twinflow_enabled=true` のとき native support です。diffusion models では `diff2flow_enabled=true` と `twinflow_allow_diff2flow=true` も必要です。Self-Flow は CREPA self-flow support です。LayerSync は alignment 用 hidden states を公開する backbone を示します。*
 
 ### 高速パス: Z-Image TurboとFlux Schnell
 
diff --git a/documentation/QUICKSTART.md b/documentation/QUICKSTART.md
index 1f2eee58d..240dacf64 100644
--- a/documentation/QUICKSTART.md
+++ b/documentation/QUICKSTART.md
@@ -2,84 +2,291 @@
 
 **Note**: For more advanced configurations, see the [tutorial](TUTORIAL.md) and [options reference](OPTIONS.md).
 
+## Model Quickstart Guides
+
+| Model | Parameters | Guide |
+| --- | --- | --- |
+| ACE-Step | 3.5B | [ACE_STEP.md](/documentation/quickstart/ACE_STEP.md) |
+| Anima | Not specified | No dedicated guide |
+| Auraflow | 6B | [AURAFLOW.md](/documentation/quickstart/AURAFLOW.md) |
+| Boogu-Image | Not specified | [BOOGU_IMAGE.md](/documentation/quickstart/BOOGU_IMAGE.md) |
+| Chroma 1 | 8.9B | [CHROMA.md](/documentation/quickstart/CHROMA.md) |
+| Cosmos2 | 2B-14B | [COSMOS2IMAGE.md](/documentation/quickstart/COSMOS2IMAGE.md) |
+| Cosmos3 | 16B-65B | [COSMOS3.md](/documentation/quickstart/COSMOS3.md) |
+| DeepFloyd IF | 0.4B-4.3B stages | No dedicated guide |
+| ERNIE-Image | Not specified | [ERNIE.md](/documentation/quickstart/ERNIE.md) |
+| Flux.1 | 8B-12B | [FLUX.md](/documentation/quickstart/FLUX.md)<br>[FLUX_KONTEXT.md](/documentation/quickstart/FLUX_KONTEXT.md) |
+| Flux.2 | 4B-32B | [FLUX2.md](/documentation/quickstart/FLUX2.md) |
+| HeartMuLa | 3B | [HEARTMULA.md](/documentation/quickstart/HEARTMULA.md) |
+| HiDream | 17B (8.5B MoE) | [HIDREAM.md](/documentation/quickstart/HIDREAM.md) |
+| Hunyuan Video | 8.3B | [HUNYUANVIDEO.md](/documentation/quickstart/HUNYUANVIDEO.md) |
+| Ideogram 4 | 9B | [IDEOGRAM4.md](/documentation/quickstart/IDEOGRAM4.md) |
+| Kandinsky 5.0 Image | 6B (lite) | [KANDINSKY5_IMAGE.md](/documentation/quickstart/KANDINSKY5_IMAGE.md) |
+| Kandinsky 5.0 Video | 2B lite, 19B pro | [KANDINSKY5_VIDEO.md](/documentation/quickstart/KANDINSKY5_VIDEO.md) |
+| Kwai Kolors | 2.7B | [KOLORS.md](/documentation/quickstart/KOLORS.md) |
+| Krea2 | Not specified | [KREA2.md](/documentation/quickstart/KREA2.md) |
+| LongCat Image | 6B | [LONGCAT_IMAGE.md](/documentation/quickstart/LONGCAT_IMAGE.md)<br>[LONGCAT_EDIT.md](/documentation/quickstart/LONGCAT_EDIT.md) |
+| LongCat Video | 13.6B | [LONGCAT_VIDEO.md](/documentation/quickstart/LONGCAT_VIDEO.md)<br>[LONGCAT_VIDEO_EDIT.md](/documentation/quickstart/LONGCAT_VIDEO_EDIT.md) |
+| LTX Video | ~2.5B | [LTXVIDEO.md](/documentation/quickstart/LTXVIDEO.md) |
+| LTX Video 2 | 19B | [LTXVIDEO2.md](/documentation/quickstart/LTXVIDEO2.md) |
+| Lumina2 | 2B | [LUMINA2.md](/documentation/quickstart/LUMINA2.md) |
+| Mage-Flow | 4B | [MAGEFLOW.md](/documentation/quickstart/MAGEFLOW.md) |
+| OmniGen | 3.8B | [OMNIGEN.md](/documentation/quickstart/OMNIGEN.md) |
+| PixArt Sigma | 0.6B-0.9B | [SIGMA.md](/documentation/quickstart/SIGMA.md) |
+| Qwen Image | 20B | [QWEN_IMAGE.md](/documentation/quickstart/QWEN_IMAGE.md)<br>[QWEN_EDIT.md](/documentation/quickstart/QWEN_EDIT.md) |
+| Sana | 0.6B-4.8B | [SANA.md](/documentation/quickstart/SANA.md) |
+| Sana Video | 2B | [SANAVIDEO.md](/documentation/quickstart/SANAVIDEO.md) |
+| SD 1.x/2.x (Legacy) | 0.9B | No dedicated guide |
+| Stable Diffusion 3 | 2B-8B | [SD3.md](/documentation/quickstart/SD3.md) |
+| Stable Diffusion XL | 3.5B | [SDXL.md](/documentation/quickstart/SDXL.md) |
+| Stable Cascade (Stage C) | 1B, 3.6B prior | [STABLE_CASCADE_C.md](/documentation/quickstart/STABLE_CASCADE_C.md) |
+| Wan Video | 1.3B-14B | [WAN.md](/documentation/quickstart/WAN.md) |
+| Wan S2V | 14B | [WAN_S2V.md](/documentation/quickstart/WAN_S2V.md) |
+| Z-Image | 6B | [ZIMAGE.md](/documentation/quickstart/ZIMAGE.md) |
+| Z-Image Omni | 6B | [ZIMAGE.md](/documentation/quickstart/ZIMAGE.md) |
+| ZLab I1 | 3B | [ZLAB_i1.md](/documentation/quickstart/ZLAB_i1.md) |
+
 ## Feature Compatibility
 
-For the complete and most accurate feature matrix, refer to the [main README](https://github.com/bghira/SimpleTuner#model-architecture-support).
+The complete compatibility matrix is split by feature area so each table stays readable.
 
-## Model Quickstart Guides
+<details>
+<summary>Training support</summary>
+
+| Model | PEFT LoRA | LyCORIS | Full-Rank | ControlNet | Ref Inputs |
+| --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Anima | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| Chroma 1 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓* | ✗ | audio opt |
+| DeepFloyd IF | ✓ | ✓ | ✓ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓* | ✓ | ✓ opt (Kontext) |
+| Flux.2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| HeartMuLa | ✓ | ✓ | ✓* | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Ideogram 4 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓* | ✗ | ✓ I2I |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Kwai Kolors | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| LongCat Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| LongCat Video | ✓ | ✓ | ✓* | ✗ | ✓ opt/edit |
+| LTX Video | ✓ | ✓ | ✓ | ✗ | ✓ I2V |
+| LTX Video 2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| OmniGen | ✓ | ✓ | ✓ | ✗ | ✗ |
+| PixArt Sigma | ✗ | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| Sana | ✗ | ✓ | ✓ | ✗ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Stable Diffusion XL | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Wan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V/VACE |
+| Wan S2V | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image Omni | ✓ | ✓ | ✓* | ✗ | ✓ opt (Edit) |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ | ✗ |
+
+</details>
+
+<details>
+<summary>Precision level support</summary>
+
+| Model | Quantization | Mixed Precision |
+| --- | --- | --- |
+| ACE-Step | int8 optional | bf16 |
+| Anima | not specified | bf16 |
+| Auraflow | int8/fp8/nf4 optional | bf16 |
+| Boogu-Image | fp8 optional | bf16 |
+| Chroma 1 | int8/fp8/nf4 optional | bf16 |
+| Cosmos2 | int8 optional | bf16 |
+| Cosmos3 | no_change first; int8 optional | bf16 |
+| DeepFloyd IF | not recommended | bf16 |
+| ERNIE-Image | int8 optional | bf16 |
+| Flux.1 | int8/fp8/nf4 optional | bf16 |
+| Flux.2 | int8/fp8/nf4 optional | bf16 |
+| HeartMuLa | int8 optional | bf16 |
+| HiDream | int8/fp8/nf4 optional | bf16 |
+| Hunyuan Video | int8 optional | bf16 |
+| Ideogram 4 | fp8 default, nf4 optional | bf16 |
+| Kandinsky 5.0 Image | int8 optional | bf16 |
+| Kandinsky 5.0 Video | int8 optional | bf16 |
+| Kwai Kolors | not recommended | bf16 |
+| Krea2 | int8 optional | bf16 |
+| LongCat Image | int8/fp8 optional | bf16 |
+| LongCat Video | int8/fp8 optional | bf16 |
+| LTX Video | int8/fp8 optional | bf16 |
+| LTX Video 2 | int8/fp8 optional | bf16 |
+| Lumina2 | int8 optional | bf16 |
+| Mage-Flow | fp8 optional | bf16 |
+| OmniGen | int8/fp8 optional | bf16 |
+| PixArt Sigma | int8 optional | bf16 |
+| Qwen Image | required (int8/nf4) | bf16 |
+| Sana | int8 optional | bf16 |
+| Sana Video | not recommended for full | bf16 |
+| SD 1.x/2.x (Legacy) | int8/nf4 optional | bf16 |
+| Stable Diffusion 3 | int8/fp8/nf4 optional | bf16 |
+| Stable Diffusion XL | int8/nf4 optional | bf16 |
+| Stable Cascade (Stage C) | not supported | fp32 required |
+| Wan Video | int8 optional | bf16 |
+| Wan S2V | int8 optional | bf16 |
+| Z-Image | int8 optional | bf16 |
+| Z-Image Omni | int8 optional | bf16 |
+| ZLab I1 | int8 optional | bf16 |
+
+</details>
+
+<details>
+<summary>Checkpointing granularity</summary>
+
+| Model | Gradient Checkpoint | Interval | Segment Stride | Attention Offload |
+| --- | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓ | ✗ |
+| Anima | ✓ | ✗ | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓ | ✗ |
+| Chroma 1 | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓ | ✗ |
+| DeepFloyd IF | ✓ | ✗ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | ✓ | ✗ | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | ✓ | ✓ | ✓ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | ✓ | ✗ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | ✓ | ✓ | ✓ | ✗ |
+| LTX Video 2 | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓ | ✓ |
+| OmniGen | ✓ | ✗ | ✗ | ✗ |
+| PixArt Sigma | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓ | ✗ |
+| Sana | ✓ | ✓ | ✓ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✗ | ✗ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | ✓ | ✗ | ✗ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓ | ✗ |
+| Wan Video | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | ✓ | ✓ | ✓ | ✗ |
+| Z-Image | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | ✓ | ✗ | ✗ | ✗ |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ |
+
+</details>
+
+<details>
+<summary>Flow, distillation, and alignment</summary>
+
+| Model | Prediction | Flow Shift | TwinFlow | Self-Flow | LayerSync | Sliders |
+| --- | --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Anima | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Auraflow | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Boogu-Image | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Chroma 1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | sample | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Cosmos3 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| DeepFloyd IF | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| ERNIE-Image | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Flux.1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | autoregressive next-token | ✗ | ✗ | ✗ | ✗ | ✗ |
+| HiDream | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Hunyuan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Kandinsky 5.0 Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Krea2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video 2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Mage-Flow | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| OmniGen | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| PixArt Sigma | epsilon | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Qwen Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| SD 1.x/2.x (Legacy) | epsilon / v-pred | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Diffusion 3 | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Cascade (Stage C) | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Wan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Z-Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| ZLab I1 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+
+</details>
+
+<details>
+<summary>Text encoders and VAE types</summary>
+
+| Model | Text Encoders | Text Encoder Params | VAE |
+| --- | --- | --- | --- |
+| ACE-Step | UMT5 Encoder | 0.6B | Music DCAE |
+| Anima | Qwen3 0.6B | 0.6B | Qwen Image VAE |
+| Auraflow | Pile T5 | not specified | AutoencoderKL |
+| Boogu-Image | Qwen3-VL | not specified | AutoencoderKL |
+| Chroma 1 | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Cosmos2 | T5 11B | 11B | Wan VAE |
+| Cosmos3 | Cosmos3 reasoner | not specified | Wan/Cosmos VAE |
+| DeepFloyd IF | T5 XXL v1.1 | 11B | None |
+| ERNIE-Image | ERNIE text encoder | not specified | Flux.2 VAE |
+| Flux.1 | CLIP-L/14 + T5 XXL v1.1 | 123M + 11B | AutoencoderKL |
+| Flux.2 | Mistral-Small-3.1-24B | 24B | Flux.2 VAE |
+| HeartMuLa | None | N/A | HeartCodec tokens |
+| HiDream | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 + Llama | 123M + 694M + 11B + not specified | AutoencoderKL |
+| Hunyuan Video | Hunyuan LLM | not specified | Hunyuan Video 3D VAE |
+| Ideogram 4 | Qwen3-VL-8B-Instruct | 8B | Ideogram AutoEncoder |
+| Kandinsky 5.0 Image | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Flux VAE (AutoencoderKL) |
+| Kandinsky 5.0 Video | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Hunyuan Video VAE |
+| Kwai Kolors | ChatGLM-6B | 6B | AutoencoderKL |
+| Krea2 | Qwen3VL | not specified | Qwen Image VAE |
+| LongCat Image | Qwen2.5-VL | 7B | AutoencoderKL |
+| LongCat Video | Qwen2.5-VL | 7B | Wan VAE |
+| LTX Video | T5 XXL v1.1 | 11B | LTX Video VAE |
+| LTX Video 2 | Gemma3 | not specified | LTX Video 2 VAE |
+| Lumina2 | Gemma2 | 2B | AutoencoderKL |
+| Mage-Flow | Qwen3-VL | not specified | Mage-VAE |
+| OmniGen | Integrated OmniGen encoder | not specified | AutoencoderKL |
+| PixArt Sigma | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Qwen Image | Qwen2.5-VL | 7B | Qwen Image VAE |
+| Sana | Gemma2 2B-IT | 2B | Sana AutoencoderDC |
+| Sana Video | Gemma 2 | 2B | Wan VAE |
+| SD 1.x/2.x (Legacy) | CLIP-L/14 | 123M | AutoencoderKL |
+| Stable Diffusion 3 | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 | 123M + 694M + 11B | AutoencoderKL |
+| Stable Diffusion XL | CLIP-L/14 + CLIP-G/14 | 123M + 694M | AutoencoderKL |
+| Stable Cascade (Stage C) | CLIP-ViT-bigG-14 | 694M | Stable Cascade Stage C VAE |
+| Wan Video | UMT5 | not specified | Wan VAE |
+| Wan S2V | UMT5 | not specified | Wan VAE |
+| Z-Image | Qwen3 4B | 4B | AutoencoderKL |
+| Z-Image Omni | Qwen3 4B | 4B | AutoencoderKL |
+| ZLab I1 | T5Gemma 2B | 2B | AutoencoderKL |
+
+</details>
 
-| Model | Params | PEFT LoRA | Full-Rank | Quantization | Mixed Precision | Grad Checkpoint | Flow Shift | TwinFlow | Self-Flow | LayerSync | Ref Inputs | ControlNet | Sliders† | License | Allows commercial use | Guide |
-| --- | --- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | --- | :---: | --- |
-| PixArt Sigma | 0.6B–0.9B | ✗ | ✓ | int8 optional | bf16 | ✓ | ✗ | ✗ | ✓ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Conditions apply<sup>1</sup> | [SIGMA.md](quickstart/SIGMA.md) |
-| NVLabs Sana | 1.6B–4.8B | ✗ | ✓ | int8 optional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [SANA.md](quickstart/SANA.md) |
-| Kwai Kolors | 2.7B | ✓ | ✓ | not recommended | bf16 | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Conditions apply<sup>7</sup> | [KOLORS.md](quickstart/KOLORS.md) |
-| Stable Diffusion 3 | 2B–8B | ✓ | ✓ | int8/fp8/nf4 optional | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Stability AI Community](https://stability.ai/license) | Conditions apply<sup>2</sup> | [SD3.md](quickstart/SD3.md) |
-| Flux.1 | 8B–12B | ✓ | ✓* | int8/fp8/nf4 optional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Conditions apply<sup>3</sup> | [FLUX.md](quickstart/FLUX.md) |
-| Flux.2 | 32B | ✓ | ✓* | int8/fp8/nf4 optional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Conditions apply<sup>4</sup> | [FLUX2.md](quickstart/FLUX2.md) |
-| Flux Kontext | 8B–12B | ✓ | ✓* | int8/fp8/nf4 optional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) | No<sup>5</sup> | [FLUX_KONTEXT.md](quickstart/FLUX_KONTEXT.md) |
-| Z-Image Turbo | 6B | ✓ | ✓* | int8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [ZIMAGE.md](quickstart/ZIMAGE.md) |
-| Krea2 | - | ✓ | ✓* | int8 optional | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✓ opt | ✗ | ✓ | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | Conditions apply<sup>6</sup> | [KREA2.md](quickstart/KREA2.md) |
-| Mage-Flow | 4B | ✓ | ✓* | int8/fp8 optional | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ edit | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Yes | [MAGEFLOW.md](quickstart/MAGEFLOW.md) |
-| Boogu-Image 0.1 | - | ✓ | ✓* | fp8 optional | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ edit | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [BOOGU_IMAGE.md](quickstart/BOOGU_IMAGE.md) |
-| zlab i1 | 3B | ✓ | ✓ | int8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | Conditions apply<sup>12</sup> | [ZLAB_i1.md](quickstart/ZLAB_i1.md) |
-| Ideogram 4 | 9B | ✓ | ✓* | fp8 default, nf4 optional | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | No<sup>5</sup> | [IDEOGRAM4.md](quickstart/IDEOGRAM4.md) |
-| ERNIE-Image | - | ✓ | ✓* | int8 optional | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [ERNIE.md](quickstart/ERNIE.md) |
-| ACE-Step | 3.5B | ✓ | ✓* | int8 optional | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B) / [MIT](https://huggingface.co/ACE-Step/Ace-Step1.5) | Yes | [ACE_STEP.md](quickstart/ACE_STEP.md) |
-| Chroma 1 | 8.9B | ✓ | ✓* | int8/fp8/nf4 optional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [CHROMA.md](quickstart/CHROMA.md) |
-| Auraflow | 6B | ✓ | ✓* | int8/fp8/nf4 optional | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) / [Pony License](https://huggingface.co/purplesmartai/pony-v7-base/blob/main/LICENSE) | Conditions apply<sup>8</sup> | [AURAFLOW.md](quickstart/AURAFLOW.md) |
-| HiDream I1 | 17B (8.5B MoE) | ✓ | ✓* | int8/fp8/nf4 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [MIT](https://opensource.org/license/mit) | Yes | [HIDREAM.md](quickstart/HIDREAM.md) |
-| OmniGen | 3.8B | ✓ | ✓ | int8/fp8 optional | bf16 | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Yes | [OMNIGEN.md](quickstart/OMNIGEN.md) |
-| Stable Diffusion XL | 2.6B | ✓ | ✓ | not recommended | bf16 | ✓ | ✗ | ✗ | ✗ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Conditions apply<sup>1</sup> | [SDXL.md](quickstart/SDXL.md) |
-| Lumina2 | 2B | ✓ | ✓ | int8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [LUMINA2.md](quickstart/LUMINA2.md) |
-| Cosmos2 | 2B | ✓ | ✓ | not recommended | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) | Yes<sup>9</sup> | [COSMOS2IMAGE.md](quickstart/COSMOS2IMAGE.md) |
-| Cosmos3 | 16B-65B | ✓ | ✓* | no_change first | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | audio opt | ✗ | ✓ | [OpenMDW 1.1](https://github.com/OpenMDW/openmdw/blob/main/1.1/LICENSE.OpenMDW-1.1) | Yes | [COSMOS3.md](quickstart/COSMOS3.md) |
-| LTX Video | ~2.5B | ✓ | ✓ | int8/fp8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [LTX Video OpenRAIL-M](https://huggingface.co/Lightricks/LTX-Video-0.9.5/blob/main/ltx-video-2b-v0.9.5.license.txt) | Conditions apply<sup>10</sup> | [LTXVIDEO.md](quickstart/LTXVIDEO.md) |
-| LTX Video 2 | 19B | ✓ | ✓* | int8/fp8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [LTX-2 Community](https://ltx.io/model/license) | Conditions apply<sup>10</sup> | [LTXVIDEO2.md](quickstart/LTXVIDEO2.md) |
-| Hunyuan Video 1.5 | 8.3B | ✓ | ✓* | int8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [Tencent Hunyuan Community](https://huggingface.co/tencent/HunyuanVideo-1.5/blob/main/LICENSE) | Conditions apply<sup>11</sup> | [HUNYUANVIDEO.md](quickstart/HUNYUANVIDEO.md) |
-| SanaVideo | 2B | ✓ | ✓* | int8/fp8 optional | bf16 | ✓ | ✗ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [SANAVIDEO.md](quickstart/SANAVIDEO.md) |
-| Wan 2.x | 1.3B–14B | ✓ | ✓* | int8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [WAN.md](quickstart/WAN.md) |
-| Wan 2.2 S2V | 14B | ✓ | ✓* | int8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [WAN_S2V.md](quickstart/WAN_S2V.md) |
-| Qwen Image | 20B | ✓ | ✓* | **required** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [QWEN_IMAGE.md](quickstart/QWEN_IMAGE.md) |
-| Qwen Image Edit | 20B | ✓ | ✓* | **required** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [QWEN_EDIT.md](quickstart/QWEN_EDIT.md) |
-| Stable Cascade (C) | 1B, 3.6B prior | ✓ | ✓* | not supported | fp32 (required) | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | No<sup>5</sup> | [STABLE_CASCADE_C.md](quickstart/STABLE_CASCADE_C.md) |
-| Kandinsky 5.0 Image | 6B (lite) | ✓ | ✓* | int8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ I2I | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Yes | [KANDINSKY5_IMAGE.md](quickstart/KANDINSKY5_IMAGE.md) |
-| Kandinsky 5.0 Video | 2B (lite), 19B (pro) | ✓ | ✓* | int8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Yes | [KANDINSKY5_VIDEO.md](quickstart/KANDINSKY5_VIDEO.md) |
-| LongCat-Video | 13.6B | ✓ | ✓* | int8/fp8 optional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Yes | [LONGCAT_VIDEO.md](quickstart/LONGCAT_VIDEO.md) |
-| LongCat-Video Edit | 13.6B | ✓ | ✓* | int8/fp8 optional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Yes | [LONGCAT_VIDEO_EDIT.md](quickstart/LONGCAT_VIDEO_EDIT.md) |
-| LongCat-Image | 6B | ✓ | ✓* | int8/fp8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [LONGCAT_IMAGE.md](quickstart/LONGCAT_IMAGE.md) |
-| LongCat-Image Edit | 6B | ✓ | ✓* | int8/fp8 optional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [LONGCAT_EDIT.md](quickstart/LONGCAT_EDIT.md) |
-
-*✓ = supported, ✓* = requires DeepSpeed/FSDP2 for full-rank, ✗ = not supported, `✓+` indicates checkpointing is recommended due to VRAM pressure. Ref Inputs marks existing reference/edit/I2V conditioning paths; `opt` means optional, `req` means the edit/I2V flavour requires it. TwinFlow ✓ means native support when `twinflow_enabled=true` (diffusion models need `diff2flow_enabled+twinflow_allow_diff2flow`). Self-Flow ✓ means native support for `crepa_enabled=true` with `crepa_feature_source=self_flow`, `use_ema=true`, and `crepa_teacher_block_index` set. LayerSync ✓ means the backbone exposes transformer hidden states for self-alignment; ✗ marks UNet-style backbones without that buffer. †Sliders apply to LoRA and LyCORIS (including full-rank LyCORIS "full"). All models support LyCORIS.*
-
-**License notes:** The commercial-use status covers model weights, derivative checkpoints, fine-tunes, and hosted model use. Generated-output rights can differ; read the linked license text before commercial deployment.
-
-<sup>1</sup> OpenRAIL-style licenses generally permit commercial use with usage restrictions that remain attached to the model and derivatives.
-
-<sup>2</sup> Stability AI Community License is available for qualifying users below the revenue threshold; larger commercial use needs Stability enterprise terms.
-
-<sup>3</sup> Flux.1 varies by flavour: Schnell and LibreFlux are Apache-2.0, while Dev, Krea, and Kontext use BFL non-commercial terms; review FluxBooru upstream metadata before commercial use.
-
-<sup>4</sup> Flux.2 varies by flavour: Klein 4B is Apache-2.0, while Dev and Klein 9B use BFL non-commercial terms.
-
-<sup>5</sup> Public non-commercial model terms do not permit commercial use of weights, derivative checkpoints, or hosted model services without a separate license.
-
-<sup>6</sup> Krea 2 Community License permits commercial use only under its revenue and safety/filtering requirements; otherwise an enterprise license is required.
-
-<sup>7</sup> Kolors commercial model or derivative use requires applying for and receiving explicit permission from the licensor.
-
-<sup>8</sup> AuraFlow supports Apache-2.0 upstream flavours and a Pony flavour with a separate custom license; check the selected flavour.
-
-<sup>9</sup> NVIDIA Open Model License permits commercial use but includes agreement, acceptable-use, and export-control terms.
-
-<sup>10</sup> LTX Video 0.9.5 uses OpenRAIL-M; LTX Video 2 uses LTX community terms with a revenue threshold for commercial use.
-
-<sup>11</sup> Tencent Hunyuan Community License includes territorial exclusions and a commercial threshold for very large services.
-
-<sup>12</sup> This mirror publishes `license: other` without a standard license text; review upstream terms before commercial use.
-
-> ℹ️ Wan quickstart includes 2.1 + 2.2 stage presets and the time-embedding toggle. Flux Kontext covers editing workflows built atop Flux.1.
-
-> ⚠️ These quickstarts are living documents. Expect occasional updates as new models land or training recipes improve.
+*✓ = supported, ✓* = supported but usually requires DeepSpeed/FSDP2 for full-rank training, ✗ = not supported. Ref Inputs marks existing reference/edit/I2V conditioning paths; `opt` means optional and `req` means the edit/I2V flavour requires it.*
+*TwinFlow support is native when `twinflow_enabled=true`; diffusion models still require `diff2flow_enabled=true` plus `twinflow_allow_diff2flow=true`. Self-Flow refers to CREPA self-flow support. LayerSync marks backbones that expose hidden states for alignment.*
 
 ### Fast paths: Z-Image Turbo & Flux Schnell
 
diff --git a/documentation/QUICKSTART.pt-BR.md b/documentation/QUICKSTART.pt-BR.md
index bdce3a6ab..370599c88 100644
--- a/documentation/QUICKSTART.pt-BR.md
+++ b/documentation/QUICKSTART.pt-BR.md
@@ -2,84 +2,291 @@
 
 **Nota**: Para configurações mais avançadas, veja o [tutorial](TUTORIAL.md) e a [referência de opções](OPTIONS.md).
 
+## Guias de início rápido por modelo
+
+| Modelo | Parâmetros | Guia |
+| --- | --- | --- |
+| ACE-Step | 3.5B | [ACE_STEP.pt-BR.md](quickstart/ACE_STEP.pt-BR.md) |
+| Anima | Not specified | Sem guia dedicada |
+| Auraflow | 6B | [AURAFLOW.pt-BR.md](quickstart/AURAFLOW.pt-BR.md) |
+| Boogu-Image | Not specified | [BOOGU_IMAGE.pt-BR.md](quickstart/BOOGU_IMAGE.pt-BR.md) |
+| Chroma 1 | 8.9B | [CHROMA.pt-BR.md](quickstart/CHROMA.pt-BR.md) |
+| Cosmos2 | 2B-14B | [COSMOS2IMAGE.pt-BR.md](quickstart/COSMOS2IMAGE.pt-BR.md) |
+| Cosmos3 | 16B-65B | [COSMOS3.pt-BR.md](quickstart/COSMOS3.pt-BR.md) |
+| DeepFloyd IF | 0.4B-4.3B stages | Sem guia dedicada |
+| ERNIE-Image | Not specified | [ERNIE.pt-BR.md](quickstart/ERNIE.pt-BR.md) |
+| Flux.1 | 8B-12B | [FLUX.pt-BR.md](quickstart/FLUX.pt-BR.md)<br>[FLUX_KONTEXT.pt-BR.md](quickstart/FLUX_KONTEXT.pt-BR.md) |
+| Flux.2 | 4B-32B | [FLUX2.pt-BR.md](quickstart/FLUX2.pt-BR.md) |
+| HeartMuLa | 3B | [HEARTMULA.pt-BR.md](quickstart/HEARTMULA.pt-BR.md) |
+| HiDream | 17B (8.5B MoE) | [HIDREAM.pt-BR.md](quickstart/HIDREAM.pt-BR.md) |
+| Hunyuan Video | 8.3B | [HUNYUANVIDEO.pt-BR.md](quickstart/HUNYUANVIDEO.pt-BR.md) |
+| Ideogram 4 | 9B | [IDEOGRAM4.pt-BR.md](quickstart/IDEOGRAM4.pt-BR.md) |
+| Kandinsky 5.0 Image | 6B (lite) | [KANDINSKY5_IMAGE.pt-BR.md](quickstart/KANDINSKY5_IMAGE.pt-BR.md) |
+| Kandinsky 5.0 Video | 2B lite, 19B pro | [KANDINSKY5_VIDEO.pt-BR.md](quickstart/KANDINSKY5_VIDEO.pt-BR.md) |
+| Kwai Kolors | 2.7B | [KOLORS.pt-BR.md](quickstart/KOLORS.pt-BR.md) |
+| Krea2 | Not specified | [KREA2.pt-BR.md](quickstart/KREA2.pt-BR.md) |
+| LongCat Image | 6B | [LONGCAT_IMAGE.pt-BR.md](quickstart/LONGCAT_IMAGE.pt-BR.md)<br>[LONGCAT_EDIT.pt-BR.md](quickstart/LONGCAT_EDIT.pt-BR.md) |
+| LongCat Video | 13.6B | [LONGCAT_VIDEO.pt-BR.md](quickstart/LONGCAT_VIDEO.pt-BR.md)<br>[LONGCAT_VIDEO_EDIT.pt-BR.md](quickstart/LONGCAT_VIDEO_EDIT.pt-BR.md) |
+| LTX Video | ~2.5B | [LTXVIDEO.pt-BR.md](quickstart/LTXVIDEO.pt-BR.md) |
+| LTX Video 2 | 19B | [LTXVIDEO2.pt-BR.md](quickstart/LTXVIDEO2.pt-BR.md) |
+| Lumina2 | 2B | [LUMINA2.pt-BR.md](quickstart/LUMINA2.pt-BR.md) |
+| Mage-Flow | 4B | [MAGEFLOW.pt-BR.md](quickstart/MAGEFLOW.pt-BR.md) |
+| OmniGen | 3.8B | [OMNIGEN.pt-BR.md](quickstart/OMNIGEN.pt-BR.md) |
+| PixArt Sigma | 0.6B-0.9B | [SIGMA.pt-BR.md](quickstart/SIGMA.pt-BR.md) |
+| Qwen Image | 20B | [QWEN_IMAGE.pt-BR.md](quickstart/QWEN_IMAGE.pt-BR.md)<br>[QWEN_EDIT.pt-BR.md](quickstart/QWEN_EDIT.pt-BR.md) |
+| Sana | 0.6B-4.8B | [SANA.pt-BR.md](quickstart/SANA.pt-BR.md) |
+| Sana Video | 2B | [SANAVIDEO.pt-BR.md](quickstart/SANAVIDEO.pt-BR.md) |
+| SD 1.x/2.x (Legacy) | 0.9B | Sem guia dedicada |
+| Stable Diffusion 3 | 2B-8B | [SD3.pt-BR.md](quickstart/SD3.pt-BR.md) |
+| Stable Diffusion XL | 3.5B | [SDXL.pt-BR.md](quickstart/SDXL.pt-BR.md) |
+| Stable Cascade (Stage C) | 1B, 3.6B prior | [STABLE_CASCADE_C.pt-BR.md](quickstart/STABLE_CASCADE_C.pt-BR.md) |
+| Wan Video | 1.3B-14B | [WAN.pt-BR.md](quickstart/WAN.pt-BR.md) |
+| Wan S2V | 14B | [WAN_S2V.pt-BR.md](quickstart/WAN_S2V.pt-BR.md) |
+| Z-Image | 6B | [ZIMAGE.pt-BR.md](quickstart/ZIMAGE.pt-BR.md) |
+| Z-Image Omni | 6B | [ZIMAGE.pt-BR.md](quickstart/ZIMAGE.pt-BR.md) |
+| ZLab I1 | 3B | [ZLAB_i1.pt-BR.md](quickstart/ZLAB_i1.pt-BR.md) |
+
 ## Compatibilidade de recursos
 
-Para a matriz completa e mais precisa de recursos, consulte o [README principal](https://github.com/bghira/SimpleTuner#model-architecture-support).
+A matriz completa de compatibilidade é dividida por área de recurso para manter cada tabela legível.
 
-## Guias de início rápido por modelo
+<details>
+<summary>Suporte de treinamento</summary>
+
+| Modelo | PEFT LoRA | LyCORIS | Full-Rank | ControlNet | Ref Inputs |
+| --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Anima | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| Chroma 1 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓* | ✗ | audio opt |
+| DeepFloyd IF | ✓ | ✓ | ✓ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓* | ✓ | ✓ opt (Kontext) |
+| Flux.2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| HeartMuLa | ✓ | ✓ | ✓* | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Ideogram 4 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓* | ✗ | ✓ I2I |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Kwai Kolors | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| LongCat Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| LongCat Video | ✓ | ✓ | ✓* | ✗ | ✓ opt/edit |
+| LTX Video | ✓ | ✓ | ✓ | ✗ | ✓ I2V |
+| LTX Video 2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| OmniGen | ✓ | ✓ | ✓ | ✗ | ✗ |
+| PixArt Sigma | ✗ | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| Sana | ✗ | ✓ | ✓ | ✗ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Stable Diffusion XL | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Wan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V/VACE |
+| Wan S2V | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image Omni | ✓ | ✓ | ✓* | ✗ | ✓ opt (Edit) |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ | ✗ |
+
+</details>
+
+<details>
+<summary>Suporte a níveis de precisão</summary>
+
+| Modelo | Quantização | Precisão mista |
+| --- | --- | --- |
+| ACE-Step | int8 optional | bf16 |
+| Anima | not specified | bf16 |
+| Auraflow | int8/fp8/nf4 optional | bf16 |
+| Boogu-Image | fp8 optional | bf16 |
+| Chroma 1 | int8/fp8/nf4 optional | bf16 |
+| Cosmos2 | int8 optional | bf16 |
+| Cosmos3 | no_change first; int8 optional | bf16 |
+| DeepFloyd IF | not recommended | bf16 |
+| ERNIE-Image | int8 optional | bf16 |
+| Flux.1 | int8/fp8/nf4 optional | bf16 |
+| Flux.2 | int8/fp8/nf4 optional | bf16 |
+| HeartMuLa | int8 optional | bf16 |
+| HiDream | int8/fp8/nf4 optional | bf16 |
+| Hunyuan Video | int8 optional | bf16 |
+| Ideogram 4 | fp8 default, nf4 optional | bf16 |
+| Kandinsky 5.0 Image | int8 optional | bf16 |
+| Kandinsky 5.0 Video | int8 optional | bf16 |
+| Kwai Kolors | not recommended | bf16 |
+| Krea2 | int8 optional | bf16 |
+| LongCat Image | int8/fp8 optional | bf16 |
+| LongCat Video | int8/fp8 optional | bf16 |
+| LTX Video | int8/fp8 optional | bf16 |
+| LTX Video 2 | int8/fp8 optional | bf16 |
+| Lumina2 | int8 optional | bf16 |
+| Mage-Flow | fp8 optional | bf16 |
+| OmniGen | int8/fp8 optional | bf16 |
+| PixArt Sigma | int8 optional | bf16 |
+| Qwen Image | required (int8/nf4) | bf16 |
+| Sana | int8 optional | bf16 |
+| Sana Video | not recommended for full | bf16 |
+| SD 1.x/2.x (Legacy) | int8/nf4 optional | bf16 |
+| Stable Diffusion 3 | int8/fp8/nf4 optional | bf16 |
+| Stable Diffusion XL | int8/nf4 optional | bf16 |
+| Stable Cascade (Stage C) | not supported | fp32 required |
+| Wan Video | int8 optional | bf16 |
+| Wan S2V | int8 optional | bf16 |
+| Z-Image | int8 optional | bf16 |
+| Z-Image Omni | int8 optional | bf16 |
+| ZLab I1 | int8 optional | bf16 |
+
+</details>
+
+<details>
+<summary>Granularidade de checkpointing</summary>
+
+| Modelo | Gradient Checkpoint | Interval | Segment Stride | Attention Offload |
+| --- | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓ | ✗ |
+| Anima | ✓ | ✗ | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓ | ✗ |
+| Chroma 1 | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓ | ✗ |
+| DeepFloyd IF | ✓ | ✗ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | ✓ | ✗ | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | ✓ | ✓ | ✓ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | ✓ | ✗ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | ✓ | ✓ | ✓ | ✗ |
+| LTX Video 2 | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓ | ✓ |
+| OmniGen | ✓ | ✗ | ✗ | ✗ |
+| PixArt Sigma | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓ | ✗ |
+| Sana | ✓ | ✓ | ✓ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✗ | ✗ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | ✓ | ✗ | ✗ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓ | ✗ |
+| Wan Video | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | ✓ | ✓ | ✓ | ✗ |
+| Z-Image | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | ✓ | ✗ | ✗ | ✗ |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ |
+
+</details>
+
+<details>
+<summary>Flow, destilação e alinhamento</summary>
+
+| Modelo | Prediction | Flow Shift | TwinFlow | Self-Flow | LayerSync | Sliders |
+| --- | --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Anima | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Auraflow | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Boogu-Image | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Chroma 1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | sample | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Cosmos3 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| DeepFloyd IF | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| ERNIE-Image | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Flux.1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | autoregressive next-token | ✗ | ✗ | ✗ | ✗ | ✗ |
+| HiDream | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Hunyuan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Kandinsky 5.0 Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Krea2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video 2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Mage-Flow | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| OmniGen | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| PixArt Sigma | epsilon | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Qwen Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| SD 1.x/2.x (Legacy) | epsilon / v-pred | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Diffusion 3 | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Cascade (Stage C) | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Wan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Z-Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| ZLab I1 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+
+</details>
+
+<details>
+<summary>Text encoders e tipos de VAE</summary>
+
+| Modelo | Text Encoders | Text Encoder Params | VAE |
+| --- | --- | --- | --- |
+| ACE-Step | UMT5 Encoder | 0.6B | Music DCAE |
+| Anima | Qwen3 0.6B | 0.6B | Qwen Image VAE |
+| Auraflow | Pile T5 | not specified | AutoencoderKL |
+| Boogu-Image | Qwen3-VL | not specified | AutoencoderKL |
+| Chroma 1 | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Cosmos2 | T5 11B | 11B | Wan VAE |
+| Cosmos3 | Cosmos3 reasoner | not specified | Wan/Cosmos VAE |
+| DeepFloyd IF | T5 XXL v1.1 | 11B | None |
+| ERNIE-Image | ERNIE text encoder | not specified | Flux.2 VAE |
+| Flux.1 | CLIP-L/14 + T5 XXL v1.1 | 123M + 11B | AutoencoderKL |
+| Flux.2 | Mistral-Small-3.1-24B | 24B | Flux.2 VAE |
+| HeartMuLa | None | N/A | HeartCodec tokens |
+| HiDream | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 + Llama | 123M + 694M + 11B + not specified | AutoencoderKL |
+| Hunyuan Video | Hunyuan LLM | not specified | Hunyuan Video 3D VAE |
+| Ideogram 4 | Qwen3-VL-8B-Instruct | 8B | Ideogram AutoEncoder |
+| Kandinsky 5.0 Image | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Flux VAE (AutoencoderKL) |
+| Kandinsky 5.0 Video | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Hunyuan Video VAE |
+| Kwai Kolors | ChatGLM-6B | 6B | AutoencoderKL |
+| Krea2 | Qwen3VL | not specified | Qwen Image VAE |
+| LongCat Image | Qwen2.5-VL | 7B | AutoencoderKL |
+| LongCat Video | Qwen2.5-VL | 7B | Wan VAE |
+| LTX Video | T5 XXL v1.1 | 11B | LTX Video VAE |
+| LTX Video 2 | Gemma3 | not specified | LTX Video 2 VAE |
+| Lumina2 | Gemma2 | 2B | AutoencoderKL |
+| Mage-Flow | Qwen3-VL | not specified | Mage-VAE |
+| OmniGen | Integrated OmniGen encoder | not specified | AutoencoderKL |
+| PixArt Sigma | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Qwen Image | Qwen2.5-VL | 7B | Qwen Image VAE |
+| Sana | Gemma2 2B-IT | 2B | Sana AutoencoderDC |
+| Sana Video | Gemma 2 | 2B | Wan VAE |
+| SD 1.x/2.x (Legacy) | CLIP-L/14 | 123M | AutoencoderKL |
+| Stable Diffusion 3 | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 | 123M + 694M + 11B | AutoencoderKL |
+| Stable Diffusion XL | CLIP-L/14 + CLIP-G/14 | 123M + 694M | AutoencoderKL |
+| Stable Cascade (Stage C) | CLIP-ViT-bigG-14 | 694M | Stable Cascade Stage C VAE |
+| Wan Video | UMT5 | not specified | Wan VAE |
+| Wan S2V | UMT5 | not specified | Wan VAE |
+| Z-Image | Qwen3 4B | 4B | AutoencoderKL |
+| Z-Image Omni | Qwen3 4B | 4B | AutoencoderKL |
+| ZLab I1 | T5Gemma 2B | 2B | AutoencoderKL |
+
+</details>
 
-| Modelo | Parâmetros | LoRA PEFT | Lycoris | Full-Rank | Quantização | Precisão mista | Checkpoint de gradiente | Flow Shift | TwinFlow | Self-Flow | LayerSync | Ref Inputs | ControlNet | Sliders† | Licença | Permite uso comercial | Guia |
-| --- | --- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | --- | :---: | --- |
-| PixArt Sigma | 0.6B–0.9B | ✗ | ✓ | ✓ | int8 opcional | bf16 | ✓ | ✗ | ✗ | ✓ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Condições aplicáveis<sup>1</sup> | [SIGMA.md](quickstart/SIGMA.md) |
-| NVLabs Sana | 1.6B–4.8B | ✗ | ✓ | ✓ | int8 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [SANA.md](quickstart/SANA.md) |
-| Kwai Kolors | 2.7B | ✓ | ✓ | ✓ | não recomendado | bf16 | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Condições aplicáveis<sup>7</sup> | [KOLORS.md](quickstart/KOLORS.md) |
-| Stable Diffusion 3 | 2B–8B | ✓ | ✓ | ✓ | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Stability AI Community](https://stability.ai/license) | Condições aplicáveis<sup>2</sup> | [SD3.md](quickstart/SD3.md) |
-| Flux.1 | 8B–12B | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Condições aplicáveis<sup>3</sup> | [FLUX.md](quickstart/FLUX.md) |
-| Flux.2 | 32B | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Condições aplicáveis<sup>4</sup> | [FLUX2.md](quickstart/FLUX2.md) |
-| Flux Kontext | 8B–12B | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) | Não<sup>5</sup> | [FLUX_KONTEXT.md](quickstart/FLUX_KONTEXT.md) |
-| Z-Image Turbo | 6B | ✓ | ✗ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [ZIMAGE.md](quickstart/ZIMAGE.md) |
-| Krea2 | - | ✓ | ✗ | ✓* | int8 opcional | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✓ opt | ✗ | ✓ | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | Condições aplicáveis<sup>6</sup> | [KREA2.md](quickstart/KREA2.pt-BR.md) |
-| Mage-Flow | 4B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ edit | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sim | [MAGEFLOW.md](quickstart/MAGEFLOW.pt-BR.md) |
-| Boogu-Image 0.1 | - | ✓ | ✓ | ✓* | fp8 opcional | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ edit | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [BOOGU_IMAGE.md](quickstart/BOOGU_IMAGE.pt-BR.md) |
-| zlab i1 | 3B | ✓ | ✓ | ✓ | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | Condições aplicáveis<sup>12</sup> | [ZLAB_i1.md](quickstart/ZLAB_i1.pt-BR.md) |
-| Ideogram 4 | 9B | ✓ | ✓ | ✓* | fp8 padrão, nf4 opcional | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | Não<sup>5</sup> | [IDEOGRAM4.md](quickstart/IDEOGRAM4.pt-BR.md) |
-| ERNIE-Image | - | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [ERNIE.md](quickstart/ERNIE.pt-BR.md) |
-| ACE-Step | 3.5B | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B) / [MIT](https://huggingface.co/ACE-Step/Ace-Step1.5) | Sim | [ACE_STEP.md](quickstart/ACE_STEP.md) |
-| Chroma 1 | 8.9B | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [CHROMA.md](quickstart/CHROMA.md) |
-| Auraflow | 6B | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) / [Pony License](https://huggingface.co/purplesmartai/pony-v7-base/blob/main/LICENSE) | Condições aplicáveis<sup>8</sup> | [AURAFLOW.md](quickstart/AURAFLOW.md) |
-| HiDream I1 | 17B (8.5B MoE) | ✓ | ✓ | ✓* | int8/fp8/nf4 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [MIT](https://opensource.org/license/mit) | Sim | [HIDREAM.md](quickstart/HIDREAM.md) |
-| OmniGen | 3.8B | ✓ | ✓ | ✓ | int8/fp8 opcional | bf16 | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sim | [OMNIGEN.md](quickstart/OMNIGEN.md) |
-| Stable Diffusion XL | 2.6B | ✓ | ✓ | ✓ | não recomendado | bf16 | ✓ | ✗ | ✗ | ✗ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Condições aplicáveis<sup>1</sup> | [SDXL.md](quickstart/SDXL.md) |
-| Lumina2 | 2B | ✓ | ✓ | ✓ | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [LUMINA2.md](quickstart/LUMINA2.md) |
-| Cosmos2 | 2B | ✓ | ✓ | ✓ | não recomendado | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) | Sim<sup>9</sup> | [COSMOS2IMAGE.md](quickstart/COSMOS2IMAGE.md) |
-| Cosmos3 | 16B-65B | ✓ | ✓ | ✓* | no_change primeiro | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | audio opt | ✗ | ✓ | [OpenMDW 1.1](https://github.com/OpenMDW/openmdw/blob/main/1.1/LICENSE.OpenMDW-1.1) | Sim | [COSMOS3.md](quickstart/COSMOS3.pt-BR.md) |
-| LTX Video | ~2.5B | ✓ | ✓ | ✓ | int8/fp8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [LTX Video OpenRAIL-M](https://huggingface.co/Lightricks/LTX-Video-0.9.5/blob/main/ltx-video-2b-v0.9.5.license.txt) | Condições aplicáveis<sup>10</sup> | [LTXVIDEO.md](quickstart/LTXVIDEO.md) |
-| LTX Video 2 | 19B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [LTX-2 Community](https://ltx.io/model/license) | Condições aplicáveis<sup>10</sup> | [LTXVIDEO2.md](quickstart/LTXVIDEO2.md) |
-| Hunyuan Video 1.5 | 8.3B | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [Tencent Hunyuan Community](https://huggingface.co/tencent/HunyuanVideo-1.5/blob/main/LICENSE) | Condições aplicáveis<sup>11</sup> | [HUNYUANVIDEO.md](quickstart/HUNYUANVIDEO.md) |
-| SanaVideo | 2B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓ | ✗ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [SANAVIDEO.md](quickstart/SANAVIDEO.pt-BR.md) |
-| Wan 2.x | 1.3B–14B | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [WAN.md](quickstart/WAN.md) |
-| Wan 2.2 S2V | 14B | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [WAN_S2V.md](quickstart/WAN_S2V.md) |
-| Qwen Image | 20B | ✓ | ✓ | ✓* | **obrigatório** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [QWEN_IMAGE.md](quickstart/QWEN_IMAGE.md) |
-| Qwen Image Edit | 20B | ✓ | ✓ | ✓* | **obrigatório** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [QWEN_EDIT.md](quickstart/QWEN_EDIT.md) |
-| Stable Cascade (C) | 1B, 3.6B prior | ✓ | ✓ | ✓* | não suportado | fp32 (obrigatório) | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | Não<sup>5</sup> | [STABLE_CASCADE_C.md](quickstart/STABLE_CASCADE_C.md) |
-| Kandinsky 5.0 Image | 6B (lite) | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ I2I | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sim | [KANDINSKY5_IMAGE.md](quickstart/KANDINSKY5_IMAGE.md) |
-| Kandinsky 5.0 Video | 2B (lite), 19B (pro) | ✓ | ✓ | ✓* | int8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sim | [KANDINSKY5_VIDEO.md](quickstart/KANDINSKY5_VIDEO.md) |
-| LongCat-Video | 13.6B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sim | [LONGCAT_VIDEO.md](quickstart/LONGCAT_VIDEO.md) |
-| LongCat-Video Edit | 13.6B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | Sim | [LONGCAT_VIDEO_EDIT.md](quickstart/LONGCAT_VIDEO_EDIT.md) |
-| LongCat-Image | 6B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [LONGCAT_IMAGE.md](quickstart/LONGCAT_IMAGE.md) |
-| LongCat-Image Edit | 6B | ✓ | ✓ | ✓* | int8/fp8 opcional | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [LONGCAT_EDIT.md](quickstart/LONGCAT_EDIT.md) |
-
-*✓ = suportado, ✓* = requer DeepSpeed/FSDP2 para full-rank, ✗ = não suportado, `✓+` indica que o checkpointing é recomendado devido à pressão de VRAM. Ref Inputs marca caminhos existentes de condicionamento por referência/edição/I2V; `opt` significa opcional e `req` significa obrigatório para o flavour de edição/I2V. TwinFlow ✓ significa suporte nativo quando `twinflow_enabled=true` (modelos de difusão precisam de `diff2flow_enabled+twinflow_allow_diff2flow`). Self-Flow ✓ significa suporte nativo para `crepa_enabled=true` com `crepa_feature_source=self_flow`, `use_ema=true` e `crepa_teacher_block_index` definido. LayerSync ✓ significa que o backbone expõe estados ocultos do transformer para autoalinhamento; ✗ marca backbones estilo UNet sem esse buffer. †Sliders se aplicam a LoRA e LyCORIS (incluindo LyCORIS full-rank “full”).*
-
-**Notas de licença:** O status de uso comercial cobre pesos do modelo, checkpoints derivados, fine-tunes e uso de modelo hospedado. Os direitos sobre saídas geradas podem diferir; leia o texto da licença vinculada antes de uma implantação comercial.
-
-<sup>1</sup> Licenças estilo OpenRAIL geralmente permitem uso comercial com restrições de uso que continuam aplicáveis ao modelo e seus derivados.
-
-<sup>2</sup> A Stability AI Community License está disponível para usuários qualificados abaixo do limite de receita; uso comercial maior exige termos empresariais da Stability.
-
-<sup>3</sup> Flux.1 varia por flavour: Schnell e LibreFlux são Apache-2.0, enquanto Dev, Krea e Kontext usam termos não comerciais da BFL; revise os metadados upstream do FluxBooru antes de uso comercial.
-
-<sup>4</sup> Flux.2 varia por flavour: Klein 4B é Apache-2.0, enquanto Dev e Klein 9B usam termos não comerciais da BFL.
-
-<sup>5</sup> Termos públicos de modelo não comercial não permitem uso comercial de pesos, checkpoints derivados ou serviços hospedados do modelo sem uma licença separada.
-
-<sup>6</sup> A Krea 2 Community License permite uso comercial apenas sob seus requisitos de receita e segurança/filtragem; caso contrário, é necessária uma licença empresarial.
-
-<sup>7</sup> O uso comercial do modelo Kolors ou de seus derivados exige solicitar e receber permissão explícita do licenciante.
-
-<sup>8</sup> AuraFlow aceita flavours upstream Apache-2.0 e um flavour Pony com uma licença personalizada separada; confira o flavour selecionado.
-
-<sup>9</sup> A NVIDIA Open Model License permite uso comercial, mas inclui termos de contrato, uso aceitável e controle de exportação.
-
-<sup>10</sup> LTX Video 0.9.5 usa OpenRAIL-M; LTX Video 2 usa termos comunitários da LTX com limite de receita para uso comercial.
-
-<sup>11</sup> A Tencent Hunyuan Community License inclui exclusões territoriais e um limite comercial para serviços muito grandes.
-
-<sup>12</sup> Este mirror publica `license: other` sem texto de licença padrão; revise os termos upstream antes de uso comercial.
-
-> ℹ️ O quickstart do Wan inclui presets das etapas 2.1 + 2.2 e o toggle de time-embedding. Flux Kontext cobre fluxos de edição construídos sobre o Flux.1.
-
-> ⚠️ Estes quickstarts são documentos vivos. Espere atualizações ocasionais conforme novos modelos chegam ou as receitas de treinamento melhoram.
+*✓ = suportado, ✓* = suportado mas normalmente requer DeepSpeed/FSDP2 para treinamento full-rank, ✗ = não suportado. Ref Inputs marca rotas existentes de condicionamento por referência/edição/I2V; `opt` significa opcional e `req` significa obrigatório para o flavour de edição/I2V.*
+*TwinFlow é nativo quando `twinflow_enabled=true`; modelos de difusão ainda exigem `diff2flow_enabled=true` e `twinflow_allow_diff2flow=true`. Self-Flow se refere ao suporte CREPA self-flow. LayerSync marca backbones que expõem hidden states para alinhamento.*
 
 ### Caminhos rápidos: Z-Image Turbo e Flux Schnell
 
diff --git a/documentation/QUICKSTART.zh.md b/documentation/QUICKSTART.zh.md
index 937889124..47c3366f7 100644
--- a/documentation/QUICKSTART.zh.md
+++ b/documentation/QUICKSTART.zh.md
@@ -2,84 +2,291 @@
 
 **注意**：如需更高级的配置，请参阅[教程](TUTORIAL.md)和[选项参考](OPTIONS.md)。
 
+## 模型快速开始指南
+
+| 模型 | 参数量 | 指南 |
+| --- | --- | --- |
+| ACE-Step | 3.5B | [ACE_STEP.zh.md](quickstart/ACE_STEP.zh.md) |
+| Anima | Not specified | 暂无专用指南 |
+| Auraflow | 6B | [AURAFLOW.zh.md](quickstart/AURAFLOW.zh.md) |
+| Boogu-Image | Not specified | [BOOGU_IMAGE.zh.md](quickstart/BOOGU_IMAGE.zh.md) |
+| Chroma 1 | 8.9B | [CHROMA.zh.md](quickstart/CHROMA.zh.md) |
+| Cosmos2 | 2B-14B | [COSMOS2IMAGE.zh.md](quickstart/COSMOS2IMAGE.zh.md) |
+| Cosmos3 | 16B-65B | [COSMOS3.zh.md](quickstart/COSMOS3.zh.md) |
+| DeepFloyd IF | 0.4B-4.3B stages | 暂无专用指南 |
+| ERNIE-Image | Not specified | [ERNIE.zh.md](quickstart/ERNIE.zh.md) |
+| Flux.1 | 8B-12B | [FLUX.zh.md](quickstart/FLUX.zh.md)<br>[FLUX_KONTEXT.zh.md](quickstart/FLUX_KONTEXT.zh.md) |
+| Flux.2 | 4B-32B | [FLUX2.zh.md](quickstart/FLUX2.zh.md) |
+| HeartMuLa | 3B | [HEARTMULA.zh.md](quickstart/HEARTMULA.zh.md) |
+| HiDream | 17B (8.5B MoE) | [HIDREAM.zh.md](quickstart/HIDREAM.zh.md) |
+| Hunyuan Video | 8.3B | [HUNYUANVIDEO.zh.md](quickstart/HUNYUANVIDEO.zh.md) |
+| Ideogram 4 | 9B | [IDEOGRAM4.zh.md](quickstart/IDEOGRAM4.zh.md) |
+| Kandinsky 5.0 Image | 6B (lite) | [KANDINSKY5_IMAGE.zh.md](quickstart/KANDINSKY5_IMAGE.zh.md) |
+| Kandinsky 5.0 Video | 2B lite, 19B pro | [KANDINSKY5_VIDEO.zh.md](quickstart/KANDINSKY5_VIDEO.zh.md) |
+| Kwai Kolors | 2.7B | [KOLORS.zh.md](quickstart/KOLORS.zh.md) |
+| Krea2 | Not specified | [KREA2.zh.md](quickstart/KREA2.zh.md) |
+| LongCat Image | 6B | [LONGCAT_IMAGE.zh.md](quickstart/LONGCAT_IMAGE.zh.md)<br>[LONGCAT_EDIT.zh.md](quickstart/LONGCAT_EDIT.zh.md) |
+| LongCat Video | 13.6B | [LONGCAT_VIDEO.zh.md](quickstart/LONGCAT_VIDEO.zh.md)<br>[LONGCAT_VIDEO_EDIT.zh.md](quickstart/LONGCAT_VIDEO_EDIT.zh.md) |
+| LTX Video | ~2.5B | [LTXVIDEO.zh.md](quickstart/LTXVIDEO.zh.md) |
+| LTX Video 2 | 19B | [LTXVIDEO2.zh.md](quickstart/LTXVIDEO2.zh.md) |
+| Lumina2 | 2B | [LUMINA2.zh.md](quickstart/LUMINA2.zh.md) |
+| Mage-Flow | 4B | [MAGEFLOW.zh.md](quickstart/MAGEFLOW.zh.md) |
+| OmniGen | 3.8B | [OMNIGEN.zh.md](quickstart/OMNIGEN.zh.md) |
+| PixArt Sigma | 0.6B-0.9B | [SIGMA.zh.md](quickstart/SIGMA.zh.md) |
+| Qwen Image | 20B | [QWEN_IMAGE.zh.md](quickstart/QWEN_IMAGE.zh.md)<br>[QWEN_EDIT.zh.md](quickstart/QWEN_EDIT.zh.md) |
+| Sana | 0.6B-4.8B | [SANA.zh.md](quickstart/SANA.zh.md) |
+| Sana Video | 2B | [SANAVIDEO.zh.md](quickstart/SANAVIDEO.zh.md) |
+| SD 1.x/2.x (Legacy) | 0.9B | 暂无专用指南 |
+| Stable Diffusion 3 | 2B-8B | [SD3.zh.md](quickstart/SD3.zh.md) |
+| Stable Diffusion XL | 3.5B | [SDXL.zh.md](quickstart/SDXL.zh.md) |
+| Stable Cascade (Stage C) | 1B, 3.6B prior | [STABLE_CASCADE_C.zh.md](quickstart/STABLE_CASCADE_C.zh.md) |
+| Wan Video | 1.3B-14B | [WAN.zh.md](quickstart/WAN.zh.md) |
+| Wan S2V | 14B | [WAN_S2V.zh.md](quickstart/WAN_S2V.zh.md) |
+| Z-Image | 6B | [ZIMAGE.zh.md](quickstart/ZIMAGE.zh.md) |
+| Z-Image Omni | 6B | [ZIMAGE.zh.md](quickstart/ZIMAGE.zh.md) |
+| ZLab I1 | 3B | [ZLAB_i1.zh.md](quickstart/ZLAB_i1.zh.md) |
+
 ## 功能兼容性
 
-完整且最准确的功能矩阵，请参阅[主 README](https://github.com/bghira/SimpleTuner#model-architecture-support)。
+完整兼容性矩阵按功能领域拆分，以保持每张表易读。
 
-## 模型快速开始指南
+<details>
+<summary>训练支持</summary>
+
+| 模型 | PEFT LoRA | LyCORIS | 全秩 | ControlNet | Ref Inputs |
+| --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Anima | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| Chroma 1 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓* | ✗ | audio opt |
+| DeepFloyd IF | ✓ | ✓ | ✓ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓* | ✓ | ✓ opt (Kontext) |
+| Flux.2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| HeartMuLa | ✓ | ✓ | ✓* | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Ideogram 4 | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓* | ✗ | ✓ I2I |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V |
+| Kwai Kolors | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| LongCat Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| LongCat Video | ✓ | ✓ | ✓* | ✗ | ✓ opt/edit |
+| LTX Video | ✓ | ✓ | ✓ | ✗ | ✓ I2V |
+| LTX Video 2 | ✓ | ✓ | ✓* | ✗ | ✓ opt |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓* | ✗ | ✓ edit |
+| OmniGen | ✓ | ✓ | ✓ | ✗ | ✗ |
+| PixArt Sigma | ✗ | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓* | ✗ | ✓ req (Edit) |
+| Sana | ✗ | ✓ | ✓ | ✗ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓* | ✓ | ✗ |
+| Stable Diffusion XL | ✓ | ✓ | ✓ | ✓ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Wan Video | ✓ | ✓ | ✓* | ✗ | ✓ I2V/VACE |
+| Wan S2V | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image | ✓ | ✓ | ✓* | ✗ | ✗ |
+| Z-Image Omni | ✓ | ✓ | ✓* | ✗ | ✓ opt (Edit) |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ | ✗ |
+
+</details>
+
+<details>
+<summary>精度级别支持</summary>
+
+| 模型 | 量化 | 混合精度 |
+| --- | --- | --- |
+| ACE-Step | int8 optional | bf16 |
+| Anima | not specified | bf16 |
+| Auraflow | int8/fp8/nf4 optional | bf16 |
+| Boogu-Image | fp8 optional | bf16 |
+| Chroma 1 | int8/fp8/nf4 optional | bf16 |
+| Cosmos2 | int8 optional | bf16 |
+| Cosmos3 | no_change first; int8 optional | bf16 |
+| DeepFloyd IF | not recommended | bf16 |
+| ERNIE-Image | int8 optional | bf16 |
+| Flux.1 | int8/fp8/nf4 optional | bf16 |
+| Flux.2 | int8/fp8/nf4 optional | bf16 |
+| HeartMuLa | int8 optional | bf16 |
+| HiDream | int8/fp8/nf4 optional | bf16 |
+| Hunyuan Video | int8 optional | bf16 |
+| Ideogram 4 | fp8 default, nf4 optional | bf16 |
+| Kandinsky 5.0 Image | int8 optional | bf16 |
+| Kandinsky 5.0 Video | int8 optional | bf16 |
+| Kwai Kolors | not recommended | bf16 |
+| Krea2 | int8 optional | bf16 |
+| LongCat Image | int8/fp8 optional | bf16 |
+| LongCat Video | int8/fp8 optional | bf16 |
+| LTX Video | int8/fp8 optional | bf16 |
+| LTX Video 2 | int8/fp8 optional | bf16 |
+| Lumina2 | int8 optional | bf16 |
+| Mage-Flow | fp8 optional | bf16 |
+| OmniGen | int8/fp8 optional | bf16 |
+| PixArt Sigma | int8 optional | bf16 |
+| Qwen Image | required (int8/nf4) | bf16 |
+| Sana | int8 optional | bf16 |
+| Sana Video | not recommended for full | bf16 |
+| SD 1.x/2.x (Legacy) | int8/nf4 optional | bf16 |
+| Stable Diffusion 3 | int8/fp8/nf4 optional | bf16 |
+| Stable Diffusion XL | int8/nf4 optional | bf16 |
+| Stable Cascade (Stage C) | not supported | fp32 required |
+| Wan Video | int8 optional | bf16 |
+| Wan S2V | int8 optional | bf16 |
+| Z-Image | int8 optional | bf16 |
+| Z-Image Omni | int8 optional | bf16 |
+| ZLab I1 | int8 optional | bf16 |
+
+</details>
+
+<details>
+<summary>检查点粒度</summary>
+
+| 模型 | Gradient Checkpoint | Interval | Segment Stride | Attention Offload |
+| --- | :---: | :---: | :---: | :---: |
+| ACE-Step | ✓ | ✓ | ✓ | ✗ |
+| Anima | ✓ | ✗ | ✗ | ✗ |
+| Auraflow | ✓ | ✓ | ✓ | ✗ |
+| Boogu-Image | ✓ | ✓ | ✓ | ✗ |
+| Chroma 1 | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | ✓ | ✓ | ✓ | ✗ |
+| Cosmos3 | ✓ | ✓ | ✓ | ✗ |
+| DeepFloyd IF | ✓ | ✗ | ✗ | ✗ |
+| ERNIE-Image | ✓ | ✓ | ✓ | ✗ |
+| Flux.1 | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | ✓ | ✗ | ✗ | ✗ |
+| HiDream | ✓ | ✓ | ✓ | ✗ |
+| Hunyuan Video | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | ✓ | ✓ | ✓ | ✗ |
+| Kandinsky 5.0 Image | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | ✓ | ✗ | ✗ | ✗ |
+| Krea2 | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | ✓ | ✓ | ✓ | ✗ |
+| LTX Video 2 | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | ✓ | ✓ | ✓ | ✗ |
+| Mage-Flow | ✓ | ✓ | ✓ | ✓ |
+| OmniGen | ✓ | ✗ | ✗ | ✗ |
+| PixArt Sigma | ✓ | ✓ | ✓ | ✗ |
+| Qwen Image | ✓ | ✓ | ✓ | ✗ |
+| Sana | ✓ | ✓ | ✓ | ✗ |
+| Sana Video | ✓ | ✓ | ✓ | ✗ |
+| SD 1.x/2.x (Legacy) | ✓ | ✗ | ✗ | ✗ |
+| Stable Diffusion 3 | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | ✓ | ✗ | ✗ | ✗ |
+| Stable Cascade (Stage C) | ✓ | ✓ | ✓ | ✗ |
+| Wan Video | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | ✓ | ✓ | ✓ | ✗ |
+| Z-Image | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | ✓ | ✗ | ✗ | ✗ |
+| ZLab I1 | ✓ | ✓ | ✓ | ✗ |
+
+</details>
+
+<details>
+<summary>Flow、蒸馏与对齐</summary>
+
+| 模型 | Prediction | Flow Shift | TwinFlow | Self-Flow | LayerSync | Sliders |
+| --- | --- | :---: | :---: | :---: | :---: | :---: |
+| ACE-Step | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Anima | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Auraflow | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Boogu-Image | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Chroma 1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Cosmos2 | sample | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Cosmos3 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| DeepFloyd IF | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| ERNIE-Image | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| Flux.1 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Flux.2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| HeartMuLa | autoregressive next-token | ✗ | ✗ | ✗ | ✗ | ✗ |
+| HiDream | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Hunyuan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Ideogram 4 | flow matching | ✓ | ✗ | ✗ | ✗ | ✓ |
+| Kandinsky 5.0 Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kandinsky 5.0 Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Kwai Kolors | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Krea2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LongCat Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| LTX Video 2 | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Lumina2 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Mage-Flow | flow matching | ✓ | ✓ | ✗ | ✓ | ✓ |
+| OmniGen | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| PixArt Sigma | epsilon | ✗ | ✗ | ✓ | ✓ | ✓ |
+| Qwen Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Sana Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| SD 1.x/2.x (Legacy) | epsilon / v-pred | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Diffusion 3 | flow matching | ✓ (SLG) | ✓ | ✓ | ✓ | ✓ |
+| Stable Diffusion XL | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Stable Cascade (Stage C) | epsilon | ✗ | ✗ | ✗ | ✗ | ✓ |
+| Wan Video | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Wan S2V | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+| Z-Image | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| Z-Image Omni | flow matching | ✓ | ✓ | ✓ | ✓ | ✓ |
+| ZLab I1 | flow matching | ✓ | ✗ | ✓ | ✓ | ✓ |
+
+</details>
+
+<details>
+<summary>文本编码器与 VAE 类型</summary>
+
+| 模型 | Text Encoders | Text Encoder Params | VAE |
+| --- | --- | --- | --- |
+| ACE-Step | UMT5 Encoder | 0.6B | Music DCAE |
+| Anima | Qwen3 0.6B | 0.6B | Qwen Image VAE |
+| Auraflow | Pile T5 | not specified | AutoencoderKL |
+| Boogu-Image | Qwen3-VL | not specified | AutoencoderKL |
+| Chroma 1 | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Cosmos2 | T5 11B | 11B | Wan VAE |
+| Cosmos3 | Cosmos3 reasoner | not specified | Wan/Cosmos VAE |
+| DeepFloyd IF | T5 XXL v1.1 | 11B | None |
+| ERNIE-Image | ERNIE text encoder | not specified | Flux.2 VAE |
+| Flux.1 | CLIP-L/14 + T5 XXL v1.1 | 123M + 11B | AutoencoderKL |
+| Flux.2 | Mistral-Small-3.1-24B | 24B | Flux.2 VAE |
+| HeartMuLa | None | N/A | HeartCodec tokens |
+| HiDream | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 + Llama | 123M + 694M + 11B + not specified | AutoencoderKL |
+| Hunyuan Video | Hunyuan LLM | not specified | Hunyuan Video 3D VAE |
+| Ideogram 4 | Qwen3-VL-8B-Instruct | 8B | Ideogram AutoEncoder |
+| Kandinsky 5.0 Image | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Flux VAE (AutoencoderKL) |
+| Kandinsky 5.0 Video | Qwen2.5-VL + CLIP-L/14 | 7B + 123M | Hunyuan Video VAE |
+| Kwai Kolors | ChatGLM-6B | 6B | AutoencoderKL |
+| Krea2 | Qwen3VL | not specified | Qwen Image VAE |
+| LongCat Image | Qwen2.5-VL | 7B | AutoencoderKL |
+| LongCat Video | Qwen2.5-VL | 7B | Wan VAE |
+| LTX Video | T5 XXL v1.1 | 11B | LTX Video VAE |
+| LTX Video 2 | Gemma3 | not specified | LTX Video 2 VAE |
+| Lumina2 | Gemma2 | 2B | AutoencoderKL |
+| Mage-Flow | Qwen3-VL | not specified | Mage-VAE |
+| OmniGen | Integrated OmniGen encoder | not specified | AutoencoderKL |
+| PixArt Sigma | T5 XXL v1.1 | 11B | AutoencoderKL |
+| Qwen Image | Qwen2.5-VL | 7B | Qwen Image VAE |
+| Sana | Gemma2 2B-IT | 2B | Sana AutoencoderDC |
+| Sana Video | Gemma 2 | 2B | Wan VAE |
+| SD 1.x/2.x (Legacy) | CLIP-L/14 | 123M | AutoencoderKL |
+| Stable Diffusion 3 | CLIP-L/14 + CLIP-G/14 + T5 XXL v1.1 | 123M + 694M + 11B | AutoencoderKL |
+| Stable Diffusion XL | CLIP-L/14 + CLIP-G/14 | 123M + 694M | AutoencoderKL |
+| Stable Cascade (Stage C) | CLIP-ViT-bigG-14 | 694M | Stable Cascade Stage C VAE |
+| Wan Video | UMT5 | not specified | Wan VAE |
+| Wan S2V | UMT5 | not specified | Wan VAE |
+| Z-Image | Qwen3 4B | 4B | AutoencoderKL |
+| Z-Image Omni | Qwen3 4B | 4B | AutoencoderKL |
+| ZLab I1 | T5Gemma 2B | 2B | AutoencoderKL |
+
+</details>
 
-| 模型 | 参数量 | PEFT LoRA | Lycoris | 全秩 | 量化 | 混合精度 | 梯度检查点 | Flow Shift | TwinFlow | Self-Flow | LayerSync | Ref Inputs | ControlNet | Sliders† | 许可证 | 允许商用 | 指南 |
-| --- | --- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | --- | :---: | --- |
-| PixArt Sigma | 0.6B–0.9B | ✗ | ✓ | ✓ | int8 可选 | bf16 | ✓ | ✗ | ✗ | ✓ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | 有条件<sup>1</sup> | [SIGMA.md](quickstart/SIGMA.md) |
-| NVLabs Sana | 1.6B–4.8B | ✗ | ✓ | ✓ | int8 可选 | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [SANA.md](quickstart/SANA.md) |
-| Kwai Kolors | 2.7B | ✓ | ✓ | ✓ | 不推荐 | bf16 | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | 有条件<sup>7</sup> | [KOLORS.md](quickstart/KOLORS.md) |
-| Stable Diffusion 3 | 2B–8B | ✓ | ✓ | ✓ | int8/fp8/nf4 可选 | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Stability AI Community](https://stability.ai/license) | 有条件<sup>2</sup> | [SD3.md](quickstart/SD3.md) |
-| Flux.1 | 8B–12B | ✓ | ✓ | ✓* | int8/fp8/nf4 可选 | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 有条件<sup>3</sup> | [FLUX.md](quickstart/FLUX.md) |
-| Flux.2 | 32B | ✓ | ✓ | ✓* | int8/fp8/nf4 可选 | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) / [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 有条件<sup>4</sup> | [FLUX2.md](quickstart/FLUX2.md) |
-| Flux Kontext | 8B–12B | ✓ | ✓ | ✓* | int8/fp8/nf4 可选 | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✓ | ✓ | [BFL Non-Commercial](https://bfl.ai/legal/non-commercial-license-terms) | 否<sup>5</sup> | [FLUX_KONTEXT.md](quickstart/FLUX_KONTEXT.md) |
-| Z-Image Turbo | 6B | ✓ | ✗ | ✓* | int8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [ZIMAGE.md](quickstart/ZIMAGE.md) |
-| Krea2 | - | ✓ | ✗ | ✓* | int8 可选 | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✓ opt | ✗ | ✓ | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | 有条件<sup>6</sup> | [KREA2.md](quickstart/KREA2.zh.md) |
-| Mage-Flow | 4B | ✓ | ✓ | ✓* | int8/fp8 可选 | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ edit | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | 是 | [MAGEFLOW.md](quickstart/MAGEFLOW.zh.md) |
-| Boogu-Image 0.1 | - | ✓ | ✓ | ✓* | fp8 可选 | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ edit | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [BOOGU_IMAGE.md](quickstart/BOOGU_IMAGE.zh.md) |
-| zlab i1 | 3B | ✓ | ✓ | ✓ | int8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | 有条件<sup>12</sup> | [ZLAB_i1.md](quickstart/ZLAB_i1.zh.md) |
-| Ideogram 4 | 9B | ✓ | ✓ | ✓* | fp8 默认，nf4 可选 | bf16 | ✓+ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | 否<sup>5</sup> | [IDEOGRAM4.md](quickstart/IDEOGRAM4.zh.md) |
-| ERNIE-Image | - | ✓ | ✓ | ✓* | int8 可选 | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [ERNIE.md](quickstart/ERNIE.zh.md) |
-| ACE-Step | 3.5B | ✓ | ✓ | ✓* | int8 可选 | bf16 | ✓ | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B) / [MIT](https://huggingface.co/ACE-Step/Ace-Step1.5) | 是 | [ACE_STEP.md](quickstart/ACE_STEP.md) |
-| Chroma 1 | 8.9B | ✓ | ✓ | ✓* | int8/fp8/nf4 可选 | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [CHROMA.md](quickstart/CHROMA.md) |
-| Auraflow | 6B | ✓ | ✓ | ✓* | int8/fp8/nf4 可选 | bf16 | ✓+ | ✓ (SLG) | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) / [Pony License](https://huggingface.co/purplesmartai/pony-v7-base/blob/main/LICENSE) | 有条件<sup>8</sup> | [AURAFLOW.md](quickstart/AURAFLOW.md) |
-| HiDream I1 | 17B (8.5B MoE) | ✓ | ✓ | ✓* | int8/fp8/nf4 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ | ✓ | [MIT](https://opensource.org/license/mit) | 是 | [HIDREAM.md](quickstart/HIDREAM.md) |
-| OmniGen | 3.8B | ✓ | ✓ | ✓ | int8/fp8 可选 | bf16 | ✓ | ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | 是 | [OMNIGEN.md](quickstart/OMNIGEN.md) |
-| Stable Diffusion XL | 2.6B | ✓ | ✓ | ✓ | 不推荐 | bf16 | ✓ | ✗ | ✗ | ✗ | ✓ | ✗ | ✓ | ✓ | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | 有条件<sup>1</sup> | [SDXL.md](quickstart/SDXL.md) |
-| Lumina2 | 2B | ✓ | ✓ | ✓ | int8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [LUMINA2.md](quickstart/LUMINA2.md) |
-| Cosmos2 | 2B | ✓ | ✓ | ✓ | 不推荐 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) | 是<sup>9</sup> | [COSMOS2IMAGE.md](quickstart/COSMOS2IMAGE.md) |
-| Cosmos3 | 16B-65B | ✓ | ✓ | ✓* | no_change first | bf16 | ✓ | ✓ | ✗ | ✗ | ✗ | audio opt | ✗ | ✓ | [OpenMDW 1.1](https://github.com/OpenMDW/openmdw/blob/main/1.1/LICENSE.OpenMDW-1.1) | 是 | [COSMOS3.md](quickstart/COSMOS3.zh.md) |
-| LTX Video | ~2.5B | ✓ | ✓ | ✓ | int8/fp8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [LTX Video OpenRAIL-M](https://huggingface.co/Lightricks/LTX-Video-0.9.5/blob/main/ltx-video-2b-v0.9.5.license.txt) | 有条件<sup>10</sup> | [LTXVIDEO.md](quickstart/LTXVIDEO.md) |
-| LTX Video 2 | 19B | ✓ | ✓ | ✓* | int8/fp8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [LTX-2 Community](https://ltx.io/model/license) | 有条件<sup>10</sup> | [LTXVIDEO2.md](quickstart/LTXVIDEO2.md) |
-| Hunyuan Video 1.5 | 8.3B | ✓ | ✓ | ✓* | int8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [Tencent Hunyuan Community](https://huggingface.co/tencent/HunyuanVideo-1.5/blob/main/LICENSE) | 有条件<sup>11</sup> | [HUNYUANVIDEO.md](quickstart/HUNYUANVIDEO.md) |
-| SanaVideo | 2B | ✓ | ✓ | ✓* | int8/fp8 可选 | bf16 | ✓ | ✗ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [SANAVIDEO.md](quickstart/SANAVIDEO.zh.md) |
-| Wan 2.x | 1.3B–14B | ✓ | ✓ | ✓* | int8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [WAN.md](quickstart/WAN.md) |
-| Wan 2.2 S2V | 14B | ✓ | ✓ | ✓* | int8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [WAN_S2V.md](quickstart/WAN_S2V.md) |
-| Qwen Image | 20B | ✓ | ✓ | ✓* | **必需** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [QWEN_IMAGE.md](quickstart/QWEN_IMAGE.md) |
-| Qwen Image Edit | 20B | ✓ | ✓ | ✓* | **必需** (int8/nf4) | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [QWEN_EDIT.md](quickstart/QWEN_EDIT.md) |
-| Stable Cascade (C) | 1B, 3.6B prior | ✓ | ✓ | ✓* | 不支持 | fp32 (必需) | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | 否<sup>5</sup> | [STABLE_CASCADE_C.md](quickstart/STABLE_CASCADE_C.md) |
-| Kandinsky 5.0 Image | 6B (lite) | ✓ | ✓ | ✓* | int8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✗ | ✓ I2I | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | 是 | [KANDINSKY5_IMAGE.md](quickstart/KANDINSKY5_IMAGE.md) |
-| Kandinsky 5.0 Video | 2B (lite), 19B (pro) | ✓ | ✓ | ✓* | int8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ I2V | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | 是 | [KANDINSKY5_VIDEO.md](quickstart/KANDINSKY5_VIDEO.md) |
-| LongCat-Video | 13.6B | ✓ | ✓ | ✓* | int8/fp8 可选 | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ opt | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | 是 | [LONGCAT_VIDEO.md](quickstart/LONGCAT_VIDEO.md) |
-| LongCat-Video Edit | 13.6B | ✓ | ✓ | ✓* | int8/fp8 可选 | bf16 | ✓+ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [MIT](https://opensource.org/license/mit) | 是 | [LONGCAT_VIDEO_EDIT.md](quickstart/LONGCAT_VIDEO_EDIT.md) |
-| LongCat-Image | 6B | ✓ | ✓ | ✓* | int8/fp8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✗ | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [LONGCAT_IMAGE.md](quickstart/LONGCAT_IMAGE.md) |
-| LongCat-Image Edit | 6B | ✓ | ✓ | ✓* | int8/fp8 可选 | bf16 | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ req | ✗ | ✓ | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [LONGCAT_EDIT.md](quickstart/LONGCAT_EDIT.md) |
-
-*✓ = 支持，✓* = 全秩训练需要 DeepSpeed/FSDP2，✗ = 不支持，`✓+` 表示由于 VRAM 压力建议启用检查点。Ref Inputs 仅标记现有参考/编辑/I2V 条件路径；`opt` 表示可选，`req` 表示该编辑/I2V flavour 需要它。TwinFlow ✓ 表示当 `twinflow_enabled=true` 时原生支持（扩散模型需要 `diff2flow_enabled+twinflow_allow_diff2flow`）。Self-Flow ✓ 表示原生支持 `crepa_enabled=true`、`crepa_feature_source=self_flow`、`use_ema=true` 且设置 `crepa_teacher_block_index`。LayerSync ✓ 表示骨干网络暴露 transformer 隐藏状态用于自对齐；✗ 标记没有该缓冲区的 UNet 风格骨干网络。†Sliders 适用于 LoRA 和 LyCORIS（包括全秩 LyCORIS "full"）。*
-
-**许可证说明：** 商用状态覆盖模型权重、派生 checkpoint、fine-tune 和托管模型使用。生成输出的权利可能不同；商业部署前请以链接的许可证正文为准。
-
-<sup>1</sup> OpenRAIL 风格许可证通常允许商用，但使用限制仍适用于模型和派生物。
-
-<sup>2</sup> Stability AI Community License 适用于低于收入门槛且符合条件的用户；更大规模商用需要 Stability 企业条款。
-
-<sup>3</sup> Flux.1 随 flavour 不同而不同：Schnell 和 LibreFlux 为 Apache-2.0，Dev、Krea 和 Kontext 使用 BFL 非商用条款；FluxBooru 商用前请检查 upstream metadata。
-
-<sup>4</sup> Flux.2 随 flavour 不同而不同：Klein 4B 为 Apache-2.0，Dev 和 Klein 9B 使用 BFL 非商用条款。
-
-<sup>5</sup> 公开的非商用模型条款不允许在没有单独许可证的情况下商用权重、派生 checkpoint 或托管模型服务。
-
-<sup>6</sup> Krea 2 Community License 只在满足收入和安全/过滤要求时允许商用；否则需要企业许可证。
-
-<sup>7</sup> Kolors 模型或派生物的商用需要向许可方申请并获得明确许可。
-
-<sup>8</sup> AuraFlow 支持 Apache-2.0 upstream flavour，以及带有单独自定义许可证的 Pony flavour；请检查所选 flavour。
-
-<sup>9</sup> NVIDIA Open Model License 允许商用，但包含协议、可接受使用和出口管制条款。
-
-<sup>10</sup> LTX Video 0.9.5 使用 OpenRAIL-M；LTX Video 2 使用带商用收入门槛的 LTX community terms。
-
-<sup>11</sup> Tencent Hunyuan Community License 包含地域排除，以及针对超大规模服务的商用门槛。
-
-<sup>12</sup> 此 mirror 发布 `license: other`，但没有标准许可证正文；商用前请检查 upstream terms。
-
-> 注：Wan 快速开始包含 2.1 + 2.2 阶段预设和时间嵌入切换。Flux Kontext 涵盖基于 Flux.1 构建的编辑工作流程。
-
-> 警告：这些快速开始指南是持续更新的文档。随着新模型的发布或训练方案的改进，预计会有不定期更新。
+*✓ = 支持，✓* = 支持但 full-rank training 通常需要 DeepSpeed/FSDP2，✗ = 不支持。Ref Inputs 标记现有 reference/edit/I2V conditioning paths；`opt` 表示可选，`req` 表示 edit/I2V flavour 必需。*
+*TwinFlow 在 `twinflow_enabled=true` 时为原生支持；diffusion models 仍需要 `diff2flow_enabled=true` 和 `twinflow_allow_diff2flow=true`。Self-Flow 指 CREPA self-flow support。LayerSync 标记公开 hidden states 用于 alignment 的 backbones。*
 
 ### 快速通道：Z-Image Turbo 和 Flux Schnell
 
diff --git a/documentation/quickstart/index.es.md b/documentation/quickstart/index.es.md
index 624b548ea..b850bbbed 100644
--- a/documentation/quickstart/index.es.md
+++ b/documentation/quickstart/index.es.md
@@ -18,10 +18,10 @@ Guías paso a paso para entrenar cada arquitectura de modelo compatible.
 | **Lumina2** | 2B | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [Guía de Lumina2](LUMINA2.md) |
 | **HiDream** | 17B MoE | [MIT](https://opensource.org/license/mit) | Sí | [Guía de HiDream](HIDREAM.md) |
 | **Z-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [Guía de Z-Image](ZIMAGE.md) |
-| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | Aplican condiciones<sup>6</sup> | [Guía de Krea2](KREA2.es.md) |
+| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | Sí<sup>6</sup> | [Guía de Krea2](KREA2.es.md) |
 | **Mage-Flow** | 4B | [MIT](https://opensource.org/license/mit) | Sí | [Guía de Mage-Flow](MAGEFLOW.es.md) |
 | **Boogu-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [Guía de Boogu-Image](BOOGU_IMAGE.es.md) |
-| **zlab i1** | 3B | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | Aplican condiciones<sup>12</sup> | [Guía de zlab i1](ZLAB_i1.es.md) |
+| **zlab i1** | 3B | [MIT](https://opensource.org/license/mit) | Sí | [Guía de zlab i1](ZLAB_i1.es.md) |
 | **Ideogram 4** | 9B | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | No<sup>5</sup> | [Guía de Ideogram 4](IDEOGRAM4.es.md) |
 | **ERNIE-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sí | [Guía de ERNIE](ERNIE.md) |
 
@@ -42,8 +42,8 @@ Guías paso a paso para entrenar cada arquitectura de modelo compatible.
 | Modelo | Parámetros | Licencia | Permite uso comercial | Guía |
 | ------- | ------------ | --- | :---: | ------- |
 | **Stable Diffusion XL** | 3.5B | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Aplican condiciones<sup>1</sup> | [Guía de SDXL](SDXL.md) |
-| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Aplican condiciones<sup>7</sup> | [Guía de Kolors](KOLORS.md) |
-| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | No<sup>5</sup> | [Guía de Cascade](STABLE_CASCADE_C.md) |
+| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Abandonware<sup>7</sup> | [Guía de Kolors](KOLORS.md) |
+| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | Abandonware<sup>7</sup> | [Guía de Cascade](STABLE_CASCADE_C.md) |
 
 ### Edición de imágenes
 
@@ -78,9 +78,9 @@ Guías paso a paso para entrenar cada arquitectura de modelo compatible.
 
 <sup>5</sup> Los términos públicos no comerciales no permiten uso comercial de pesos, checkpoints derivados o servicios alojados del modelo sin una licencia separada.
 
-<sup>6</sup> La Krea 2 Community License permite uso comercial solo bajo sus requisitos de ingresos y seguridad/filtrado; de lo contrario se requiere una licencia empresarial.
+<sup>6</sup> La Krea 2 Community License permite uso comercial bajo su límite de ingresos (menos de $1M anuales) y sus requisitos de seguridad/filtrado; de lo contrario se requiere una licencia empresarial.
 
-<sup>7</sup> El uso comercial del modelo Kolors o sus derivados requiere solicitar y recibir permiso explícito del licenciante.
+<sup>7</sup> Abandonware significa que el proveedor original dejó el modelo atrás y no hay una vía fiable para pedir permiso; cada usuario debe decidir si acepta ese riesgo.
 
 <sup>8</sup> AuraFlow admite flavours upstream Apache-2.0 y un flavour Pony con una licencia personalizada separada; revisa el flavour seleccionado.
 
@@ -90,7 +90,6 @@ Guías paso a paso para entrenar cada arquitectura de modelo compatible.
 
 <sup>11</sup> La Tencent Hunyuan Community License incluye exclusiones territoriales y un umbral comercial para servicios muy grandes.
 
-<sup>12</sup> Este mirror publica `license: other` sin un texto de licencia estándar; revisa los términos upstream antes de uso comercial.
 
 ## Modelos de audio
 
diff --git a/documentation/quickstart/index.hi.md b/documentation/quickstart/index.hi.md
index 583dad27f..56a108939 100644
--- a/documentation/quickstart/index.hi.md
+++ b/documentation/quickstart/index.hi.md
@@ -18,10 +18,10 @@
 | **Lumina2** | 2B | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [Lumina2 गाइड](LUMINA2.md) |
 | **HiDream** | 17B MoE | [MIT](https://opensource.org/license/mit) | हाँ | [HiDream गाइड](HIDREAM.md) |
 | **Z-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [Z-Image गाइड](ZIMAGE.md) |
-| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | शर्तें लागू<sup>6</sup> | [Krea2 गाइड](KREA2.hi.md) |
+| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | हाँ<sup>6</sup> | [Krea2 गाइड](KREA2.hi.md) |
 | **Mage-Flow** | 4B | [MIT](https://opensource.org/license/mit) | हाँ | [Mage-Flow गाइड](MAGEFLOW.hi.md) |
 | **Boogu-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [Boogu-Image गाइड](BOOGU_IMAGE.hi.md) |
-| **zlab i1** | 3B | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | शर्तें लागू<sup>12</sup> | [zlab i1 गाइड](ZLAB_i1.hi.md) |
+| **zlab i1** | 3B | [MIT](https://opensource.org/license/mit) | हाँ | [zlab i1 गाइड](ZLAB_i1.hi.md) |
 | **Ideogram 4** | 9B | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | नहीं<sup>5</sup> | [Ideogram 4 गाइड](IDEOGRAM4.hi.md) |
 | **ERNIE-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | हाँ | [ERNIE गाइड](ERNIE.md) |
 
@@ -42,8 +42,8 @@
 | मॉडल | पैरामीटर | लाइसेंस | व्यावसायिक उपयोग की अनुमति | गाइड |
 | ------- | ------------ | --- | :---: | ------- |
 | **Stable Diffusion XL** | 3.5B | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | शर्तें लागू<sup>1</sup> | [SDXL गाइड](SDXL.md) |
-| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | शर्तें लागू<sup>7</sup> | [Kolors गाइड](KOLORS.md) |
-| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | नहीं<sup>5</sup> | [Cascade गाइड](STABLE_CASCADE_C.md) |
+| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Abandonware<sup>7</sup> | [Kolors गाइड](KOLORS.md) |
+| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | Abandonware<sup>7</sup> | [Cascade गाइड](STABLE_CASCADE_C.md) |
 
 ### छवि संपादन
 
@@ -78,9 +78,9 @@
 
 <sup>5</sup> Public non-commercial model terms अलग license के बिना weights, derivative checkpoints, या hosted model services के commercial use की अनुमति नहीं देते।
 
-<sup>6</sup> Krea 2 Community License केवल revenue और safety/filtering requirements के तहत commercial use की अनुमति देती है; अन्यथा enterprise license चाहिए।
+<sup>6</sup> Krea 2 Community License revenue cap (annual revenue $1M से कम) और safety/filtering requirements के तहत commercial use की अनुमति देती है; अन्यथा enterprise license चाहिए।
 
-<sup>7</sup> Kolors model या derivatives का commercial use करने के लिए licensor से explicit permission माँगनी और प्राप्त करनी होती है।
+<sup>7</sup> Abandonware का मतलब है कि original vendor ने model को effectively पीछे छोड़ दिया है और permission लेने का reliable path नहीं है; end users को तय करना होगा कि यह risk स्वीकार्य है या नहीं।
 
 <sup>8</sup> AuraFlow Apache-2.0 upstream flavours और अलग custom license वाले Pony flavour को support करता है; selected flavour देखें।
 
@@ -90,7 +90,6 @@
 
 <sup>11</sup> Tencent Hunyuan Community License में territorial exclusions और बहुत बड़े services के लिए commercial threshold शामिल है।
 
-<sup>12</sup> यह mirror standard license text के बिना `license: other` publish करता है; commercial use से पहले upstream terms देखें।
 
 ## ऑडियो मॉडल
 
diff --git a/documentation/quickstart/index.ja.md b/documentation/quickstart/index.ja.md
index 672275d6d..9c94fdfb0 100644
--- a/documentation/quickstart/index.ja.md
+++ b/documentation/quickstart/index.ja.md
@@ -18,10 +18,10 @@
 | **Lumina2** | 2B | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [Lumina2 ガイド](LUMINA2.md) |
 | **HiDream** | 17B MoE | [MIT](https://opensource.org/license/mit) | はい | [HiDream ガイド](HIDREAM.md) |
 | **Z-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [Z-Image ガイド](ZIMAGE.md) |
-| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | 条件付き<sup>6</sup> | [Krea2 ガイド](KREA2.ja.md) |
+| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | はい<sup>6</sup> | [Krea2 ガイド](KREA2.ja.md) |
 | **Mage-Flow** | 4B | [MIT](https://opensource.org/license/mit) | はい | [Mage-Flow ガイド](MAGEFLOW.ja.md) |
 | **Boogu-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [Boogu-Image ガイド](BOOGU_IMAGE.ja.md) |
-| **zlab i1** | 3B | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | 条件付き<sup>12</sup> | [zlab i1 ガイド](ZLAB_i1.ja.md) |
+| **zlab i1** | 3B | [MIT](https://opensource.org/license/mit) | はい | [zlab i1 ガイド](ZLAB_i1.ja.md) |
 | **Ideogram 4** | 9B | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | いいえ<sup>5</sup> | [Ideogram 4 ガイド](IDEOGRAM4.ja.md) |
 | **ERNIE-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | はい | [ERNIE ガイド](ERNIE.md) |
 
@@ -42,8 +42,8 @@
 | モデル | パラメータ | ライセンス | 商用利用 | ガイド |
 | ------- | ------------ | --- | :---: | ------- |
 | **Stable Diffusion XL** | 3.5B | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | 条件付き<sup>1</sup> | [SDXL ガイド](SDXL.md) |
-| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | 条件付き<sup>7</sup> | [Kolors ガイド](KOLORS.md) |
-| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | いいえ<sup>5</sup> | [Cascade ガイド](STABLE_CASCADE_C.md) |
+| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Abandonware<sup>7</sup> | [Kolors ガイド](KOLORS.md) |
+| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | Abandonware<sup>7</sup> | [Cascade ガイド](STABLE_CASCADE_C.md) |
 
 ### 画像編集
 
@@ -78,9 +78,9 @@
 
 <sup>5</sup> 公開されている非商用モデル条件では、別ライセンスなしに重み、派生チェックポイント、ホスト型モデルサービスを商用利用できません。
 
-<sup>6</sup> Krea 2 Community License は収益および安全性/フィルタリング要件を満たす場合のみ商用利用を許可します。それ以外はエンタープライズライセンスが必要です。
+<sup>6</sup> Krea 2 Community License は、収益上限（年間 $1M 未満）と安全性/フィルタリング要件を満たす場合に商用利用を許可します。それ以外はエンタープライズライセンスが必要です。
 
-<sup>7</sup> Kolors のモデルまたは派生物の商用利用には、ライセンサーへの申請と明示的な許可が必要です。
+<sup>7</sup> Abandonware は、元のベンダーが実質的にモデルを放置しており、許可を得る信頼できる経路がないことを意味します。そのリスクを受け入れるかはエンドユーザーの判断です。
 
 <sup>8</sup> AuraFlow は Apache-2.0 の upstream flavour と、別のカスタムライセンスを持つ Pony flavour をサポートします。選択した flavour を確認してください。
 
@@ -90,7 +90,6 @@
 
 <sup>11</sup> Tencent Hunyuan Community License には地域除外と、非常に大規模なサービス向けの商用しきい値があります。
 
-<sup>12</sup> この mirror は標準ライセンス本文なしで `license: other` を公開しています。商用利用前に upstream terms を確認してください。
 
 ## 音声モデル
 
diff --git a/documentation/quickstart/index.md b/documentation/quickstart/index.md
index cf8064802..df163cdc6 100644
--- a/documentation/quickstart/index.md
+++ b/documentation/quickstart/index.md
@@ -18,10 +18,10 @@ Step-by-step guides for training each supported model architecture.
 | **Lumina2** | 2B | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [Lumina2 Guide](LUMINA2.md) |
 | **HiDream** | 17B MoE | [MIT](https://opensource.org/license/mit) | Yes | [HiDream Guide](HIDREAM.md) |
 | **Z-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [Z-Image Guide](ZIMAGE.md) |
-| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | Conditions apply<sup>6</sup> | [Krea2 Guide](KREA2.md) |
+| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | Yes<sup>6</sup> | [Krea2 Guide](KREA2.md) |
 | **Mage-Flow** | 4B | [MIT](https://opensource.org/license/mit) | Yes | [Mage-Flow Guide](MAGEFLOW.md) |
 | **Boogu-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [Boogu-Image Guide](BOOGU_IMAGE.md) |
-| **zlab i1** | 3B | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | Conditions apply<sup>12</sup> | [zlab i1 Guide](ZLAB_i1.md) |
+| **zlab i1** | 3B | [MIT](https://opensource.org/license/mit) | Yes | [zlab i1 Guide](ZLAB_i1.md) |
 | **Ideogram 4** | 9B | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | No<sup>5</sup> | [Ideogram 4 Guide](IDEOGRAM4.md) |
 | **ERNIE-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Yes | [ERNIE Guide](ERNIE.md) |
 
@@ -42,8 +42,8 @@ Step-by-step guides for training each supported model architecture.
 | Model | Parameters | License | Allows commercial use | Guide |
 | ------- | ------------ | --- | :---: | ------- |
 | **Stable Diffusion XL** | 3.5B | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Conditions apply<sup>1</sup> | [SDXL Guide](SDXL.md) |
-| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Conditions apply<sup>7</sup> | [Kolors Guide](KOLORS.md) |
-| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | No<sup>5</sup> | [Cascade Guide](STABLE_CASCADE_C.md) |
+| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Abandonware<sup>7</sup> | [Kolors Guide](KOLORS.md) |
+| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | Abandonware<sup>7</sup> | [Cascade Guide](STABLE_CASCADE_C.md) |
 
 ### Image Editing
 
@@ -78,9 +78,9 @@ Step-by-step guides for training each supported model architecture.
 
 <sup>5</sup> Public non-commercial model terms do not permit commercial use of weights, derivative checkpoints, or hosted model services without a separate license.
 
-<sup>6</sup> Krea 2 Community License permits commercial use only under its revenue and safety/filtering requirements; otherwise an enterprise license is required.
+<sup>6</sup> Krea 2 Community License permits commercial use under its revenue cap (under $1M annual revenue) and safety/filtering requirements; otherwise an enterprise license is required.
 
-<sup>7</sup> Kolors commercial model or derivative use requires applying for and receiving explicit permission from the licensor.
+<sup>7</sup> Abandonware means the original vendor has effectively left the model behind and there is no reliable permission path; end users must decide whether that risk is acceptable.
 
 <sup>8</sup> AuraFlow supports Apache-2.0 upstream flavours and a Pony flavour with a separate custom license; check the selected flavour.
 
@@ -90,7 +90,6 @@ Step-by-step guides for training each supported model architecture.
 
 <sup>11</sup> Tencent Hunyuan Community License includes territorial exclusions and a commercial threshold for very large services.
 
-<sup>12</sup> This mirror publishes `license: other` without a standard license text; review upstream terms before commercial use.
 
 ## Audio Models
 
diff --git a/documentation/quickstart/index.pt-BR.md b/documentation/quickstart/index.pt-BR.md
index a21bc0667..1f37312d8 100644
--- a/documentation/quickstart/index.pt-BR.md
+++ b/documentation/quickstart/index.pt-BR.md
@@ -18,10 +18,10 @@ Guias passo a passo para treinar cada arquitetura de modelo suportada.
 | **Lumina2** | 2B | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [Guia Lumina2](LUMINA2.md) |
 | **HiDream** | 17B MoE | [MIT](https://opensource.org/license/mit) | Sim | [Guia HiDream](HIDREAM.md) |
 | **Z-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [Guia Z-Image](ZIMAGE.md) |
-| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | Condições aplicáveis<sup>6</sup> | [Guia Krea2](KREA2.pt-BR.md) |
+| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | Sim<sup>6</sup> | [Guia Krea2](KREA2.pt-BR.md) |
 | **Mage-Flow** | 4B | [MIT](https://opensource.org/license/mit) | Sim | [Guia Mage-Flow](MAGEFLOW.pt-BR.md) |
 | **Boogu-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [Guia Boogu-Image](BOOGU_IMAGE.pt-BR.md) |
-| **zlab i1** | 3B | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | Condições aplicáveis<sup>12</sup> | [Guia zlab i1](ZLAB_i1.pt-BR.md) |
+| **zlab i1** | 3B | [MIT](https://opensource.org/license/mit) | Sim | [Guia zlab i1](ZLAB_i1.pt-BR.md) |
 | **Ideogram 4** | 9B | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | Não<sup>5</sup> | [Guia Ideogram 4](IDEOGRAM4.pt-BR.md) |
 | **ERNIE-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | Sim | [Guia ERNIE](ERNIE.md) |
 
@@ -42,8 +42,8 @@ Guias passo a passo para treinar cada arquitetura de modelo suportada.
 | Modelo | Parâmetros | Licença | Permite uso comercial | Guia |
 | ------- | ------------ | --- | :---: | ------ |
 | **Stable Diffusion XL** | 3.5B | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | Condições aplicáveis<sup>1</sup> | [Guia SDXL](SDXL.md) |
-| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Condições aplicáveis<sup>7</sup> | [Guia Kolors](KOLORS.md) |
-| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | Não<sup>5</sup> | [Guia Cascade](STABLE_CASCADE_C.md) |
+| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Abandonware<sup>7</sup> | [Guia Kolors](KOLORS.md) |
+| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | Abandonware<sup>7</sup> | [Guia Cascade](STABLE_CASCADE_C.md) |
 
 ### Edição de Imagem
 
@@ -78,9 +78,9 @@ Guias passo a passo para treinar cada arquitetura de modelo suportada.
 
 <sup>5</sup> Termos públicos de modelo não comercial não permitem uso comercial de pesos, checkpoints derivados ou serviços hospedados do modelo sem uma licença separada.
 
-<sup>6</sup> A Krea 2 Community License permite uso comercial apenas sob seus requisitos de receita e segurança/filtragem; caso contrário, é necessária uma licença empresarial.
+<sup>6</sup> A Krea 2 Community License permite uso comercial sob seu limite de receita (menos de $1M anuais) e requisitos de segurança/filtragem; caso contrário, é necessária uma licença empresarial.
 
-<sup>7</sup> O uso comercial do modelo Kolors ou de seus derivados exige solicitar e receber permissão explícita do licenciante.
+<sup>7</sup> Abandonware significa que o fornecedor original efetivamente deixou o modelo para trás e não há um caminho confiável para pedir permissão; cada usuário deve decidir se aceita esse risco.
 
 <sup>8</sup> AuraFlow aceita flavours upstream Apache-2.0 e um flavour Pony com uma licença personalizada separada; confira o flavour selecionado.
 
@@ -90,7 +90,6 @@ Guias passo a passo para treinar cada arquitetura de modelo suportada.
 
 <sup>11</sup> A Tencent Hunyuan Community License inclui exclusões territoriais e um limite comercial para serviços muito grandes.
 
-<sup>12</sup> Este mirror publica `license: other` sem texto de licença padrão; revise os termos upstream antes de uso comercial.
 
 ## Modelos de Áudio
 
diff --git a/documentation/quickstart/index.zh.md b/documentation/quickstart/index.zh.md
index 0cd567a19..dc5271eb9 100644
--- a/documentation/quickstart/index.zh.md
+++ b/documentation/quickstart/index.zh.md
@@ -18,10 +18,10 @@
 | **Lumina2** | 2B | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [Lumina2 指南](LUMINA2.md) |
 | **HiDream** | 17B MoE | [MIT](https://opensource.org/license/mit) | 是 | [HiDream 指南](HIDREAM.md) |
 | **Z-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [Z-Image 指南](ZIMAGE.md) |
-| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | 有条件<sup>6</sup> | [Krea2 指南](KREA2.zh.md) |
+| **Krea2** | - | [Krea 2 Community](https://www.krea.ai/krea-2-licensing) | 是<sup>6</sup> | [Krea2 指南](KREA2.zh.md) |
 | **Mage-Flow** | 4B | [MIT](https://opensource.org/license/mit) | 是 | [Mage-Flow 指南](MAGEFLOW.zh.md) |
 | **Boogu-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [Boogu-Image 指南](BOOGU_IMAGE.zh.md) |
-| **zlab i1** | 3B | [Unspecified](https://huggingface.co/bghira/zlab-i1-diffusers) | 有条件<sup>12</sup> | [zlab i1 指南](ZLAB_i1.zh.md) |
+| **zlab i1** | 3B | [MIT](https://opensource.org/license/mit) | 是 | [zlab i1 指南](ZLAB_i1.zh.md) |
 | **Ideogram 4** | 9B | [Ideogram 4 Non-Commercial](https://huggingface.co/ideogram-ai/ideogram-4-nf4/blob/main/LICENSE.md) | 否<sup>5</sup> | [Ideogram 4 指南](IDEOGRAM4.zh.md) |
 | **ERNIE-Image** | - | [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0) | 是 | [ERNIE 指南](ERNIE.md) |
 
@@ -42,8 +42,8 @@
 | 模型 | 参数 | 许可证 | 允许商用 | 指南 |
 | ------- | ------------ | --- | :---: | ------- |
 | **Stable Diffusion XL** | 3.5B | [OpenRAIL++](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md) | 有条件<sup>1</sup> | [SDXL 指南](SDXL.md) |
-| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | 有条件<sup>7</sup> | [Kolors 指南](KOLORS.md) |
-| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | 否<sup>5</sup> | [Cascade 指南](STABLE_CASCADE_C.md) |
+| **Kolors** | 5B | [Kwai Kolors License](https://huggingface.co/terminusresearch/kwai-kolors-1.0/blob/main/MODEL_LICENSE) | Abandonware<sup>7</sup> | [Kolors 指南](KOLORS.md) |
+| **Stable Cascade** | - | [Stable Cascade NC Community](https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE) | Abandonware<sup>7</sup> | [Cascade 指南](STABLE_CASCADE_C.md) |
 
 ### 图像编辑
 
@@ -78,9 +78,9 @@
 
 <sup>5</sup> 公开的非商用模型条款不允许在没有单独许可证的情况下商用权重、派生 checkpoint 或托管模型服务。
 
-<sup>6</sup> Krea 2 Community License 只在满足收入和安全/过滤要求时允许商用；否则需要企业许可证。
+<sup>6</sup> Krea 2 Community License 在满足收入上限（年收入低于 $1M）和安全/过滤要求时允许商用；否则需要企业许可证。
 
-<sup>7</sup> Kolors 模型或派生物的商用需要向许可方申请并获得明确许可。
+<sup>7</sup> Abandonware 表示原供应商实际上已放弃维护该模型，且没有可靠的许可申请路径；最终用户需要自行判断是否接受该风险。
 
 <sup>8</sup> AuraFlow 支持 Apache-2.0 upstream flavour，以及带有单独自定义许可证的 Pony flavour；请检查所选 flavour。
 
@@ -90,7 +90,6 @@
 
 <sup>11</sup> Tencent Hunyuan Community License 包含地域排除，以及针对超大规模服务的商用门槛。
 
-<sup>12</sup> 此 mirror 发布 `license: other`，但没有标准许可证正文；商用前请检查 upstream terms。
 
 ## 音频模型