Skip to content
Merged

merge #2994

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
138 commits
Select commit Hold shift + click to select a range
3637aa1
fix(data): harden distributed padding semantics
hjinnkim Jul 27, 2026
fa2a934
fix(data): materialize automatic oversubscription repeats
hjinnkim Jul 27, 2026
436464f
Normalize configured API base URLs
cupkk Jul 27, 2026
1196eab
Fix checkpoint rotation after successful saves
hjinnkim Jul 28, 2026
25cd246
Fix RamTorch prefetch-order save race
hjinnkim Jul 28, 2026
37aaa22
segmented checkpointing for better cache hits / latency
Jul 28, 2026
c7bd2f8
Merge pull request #2920 from bghira/feature/segmented-checkpointing
bghira Aug 2, 2026
cc19962
Support Hugging Face Hub attention kernels
Aug 2, 2026
12caf81
Improve audio validation metadata handling
Aug 2, 2026
f354d2a
Validate HiDream mixed precision settings
Aug 2, 2026
d176aed
Map HunyuanVideo flavours to Diffusers repos
Aug 2, 2026
1772e84
Improve MageFlow loading defaults
Aug 2, 2026
abeb85d
Add Wan latent I2V conditioning
Aug 2, 2026
4f2ea19
Fix audio metadata CI regressions
Aug 2, 2026
e3fc491
Fix Kandinsky5 pipeline compatibility
Aug 2, 2026
0740e96
Fix LongCat pipeline compatibility
Aug 2, 2026
0c79339
Update ACE-Step example preset
Aug 2, 2026
50015a2
Update Stable Cascade example preset
Aug 2, 2026
ffd415a
Update Cosmos example preset
Aug 2, 2026
69420ff
Update HeartMula example preset
Aug 2, 2026
dc9a868
Update HiDream example preset
Aug 2, 2026
85ce38d
Update Kandinsky5 Image example presets
Aug 2, 2026
d412c20
Update Kandinsky5 Video example preset
Aug 2, 2026
56d1b0e
Update LongCat Image example preset
Aug 2, 2026
51c0779
Update LTXVideo2 example preset
Aug 2, 2026
fe81853
Update OmniGen example preset
Aug 2, 2026
bb4077a
Update PixArt example preset
Aug 2, 2026
002cabb
Update Wan example preset
Aug 2, 2026
1cb0bec
Add Anima example config
Aug 2, 2026
25e76d0
Add DeepFloyd IF example config
Aug 2, 2026
439b1e3
Add Kolors example config
Aug 2, 2026
29884ab
Add SD1x DreamShaper example config
Aug 2, 2026
e67b36a
Add LongCat Video example config
Aug 2, 2026
34783b0
Add LTXVideo 0.9.5 example config
Aug 2, 2026
8bf7728
Add SanaVideo example config
Aug 2, 2026
c7d57ab
Add Wan S2V example config
Aug 2, 2026
76766ad
Address Hub attention kernel review feedback
Aug 2, 2026
66944ff
Merge pull request #2924 from bghira/agent/support-hf-hub-attention-k…
bghira Aug 2, 2026
3e29a58
Merge pull request #2897 from hjinnkim/bugfix/oversubscribed-step-pad…
bghira Aug 2, 2026
321457a
Merge pull request #2919 from cupkk/fix-api-base-url-trailing-slashes
bghira Aug 2, 2026
b9908bf
Merge pull request #2928 from bghira/agent/map-hunyuanvideo-flavour-r…
bghira Aug 3, 2026
a055ee9
Merge pull request #2929 from bghira/agent/improve-mageflow-loading
bghira Aug 3, 2026
8951f09
Add Qwen text encoder path override
Aug 3, 2026
e250515
Merge pull request #2983 from bghira/agent/add-wan-s2v-example-config
bghira Aug 3, 2026
492a83b
Merge pull request #2982 from bghira/agent/add-sanavideo-example-config
bghira Aug 3, 2026
5b465a4
Merge pull request #2981 from bghira/agent/add-ltxvideo-095-example-c…
bghira Aug 3, 2026
c9601e5
Merge pull request #2980 from bghira/agent/add-longcat-video-example-…
bghira Aug 3, 2026
a7d7fe6
Merge pull request #2975 from bghira/agent/update-wan-example-preset
bghira Aug 3, 2026
3f31716
Merge pull request #2976 from bghira/agent/add-anima-example-config
bghira Aug 3, 2026
f66b286
Merge pull request #2978 from bghira/agent/add-kolors-example-config
bghira Aug 3, 2026
45977e6
Merge pull request #2979 from bghira/agent/add-sd1x-dreamshaper-examp…
bghira Aug 3, 2026
d611e3b
Merge pull request #2977 from bghira/agent/add-deepfloyd-if-example-c…
bghira Aug 3, 2026
a06e0ad
Merge pull request #2974 from bghira/agent/update-pixart-example-preset
bghira Aug 3, 2026
493b195
Merge pull request #2973 from bghira/agent/update-omnigen-example-preset
bghira Aug 3, 2026
51c3db3
Merge pull request #2972 from bghira/agent/update-ltxvideo2-example-p…
bghira Aug 3, 2026
e9251e3
Merge pull request #2971 from bghira/agent/update-longcat-image-examp…
bghira Aug 3, 2026
79fde2e
Merge pull request #2970 from bghira/agent/update-kandinsky5-video-ex…
bghira Aug 3, 2026
42fecf3
Merge pull request #2969 from bghira/agent/update-kandinsky5-image-ex…
bghira Aug 3, 2026
ecd66d3
Merge pull request #2968 from bghira/agent/update-hidream-example-preset
bghira Aug 3, 2026
0a3caf8
Merge pull request #2967 from bghira/agent/update-heartmula-example-p…
bghira Aug 3, 2026
fcd0f5a
Merge pull request #2966 from bghira/agent/update-cosmos-example-preset
bghira Aug 3, 2026
e69c9e4
Merge pull request #2965 from bghira/agent/update-stable-cascade-exam…
bghira Aug 3, 2026
d44115c
Merge pull request #2964 from bghira/agent/update-acestep-example-preset
bghira Aug 3, 2026
2464754
Address audio validation review comments
Aug 3, 2026
8d59043
Merge pull request #2926 from bghira/agent/improve-audio-validation-m…
bghira Aug 3, 2026
f25e0cd
Merge pull request #2927 from bghira/agent/validate-hidream-precision
bghira Aug 3, 2026
c3294a4
Address Wan latent conditioning review comments
Aug 3, 2026
acf7293
Merge pull request #2931 from bghira/agent/add-wan-latent-i2v-conditi…
bghira Aug 3, 2026
57a545c
Merge pull request #2963 from bghira/agent/fix-longcat-pipeline-compa…
bghira Aug 3, 2026
2d6df12
Merge pull request #2962 from bghira/agent/fix-kandinsky5-pipeline-co…
bghira Aug 3, 2026
43e3f72
Harden Qwen override warning test
Aug 3, 2026
943d837
test(data): cover conditioning duplication and empty-bucket splits
hjinnkim Aug 3, 2026
df64748
fix(data): only restore a checkpointed shard when every rank has one
hjinnkim Aug 3, 2026
5d4d32c
fix(data): keep post-split shard length when filtering a sample
hjinnkim Aug 3, 2026
2211669
fix(training): write LoRA checkpoints in PEFT naming
hjinnkim Aug 3, 2026
e368e9a
Merge pull request #2985 from bghira/agent/add-qwen-text-encoder-path
bghira Aug 3, 2026
9cef101
Add segmented checkpointing base controls
Aug 2, 2026
615ba82
Address segmented checkpointing base review feedback
Aug 3, 2026
bea1607
Merge pull request #2932 from bghira/agent/segmented-checkpointing-base
bghira Aug 3, 2026
c5fbbc5
Add ACE-Step segmented checkpointing support
Aug 2, 2026
3cfb159
Clarify segmented checkpointing test helper
Aug 3, 2026
f737799
Add AuraFlow segmented checkpointing support
Aug 2, 2026
aebc5f3
Forward AuraFlow ControlNet attention kwargs in checkpoints
Aug 3, 2026
020314e
Add Boogu Image segmented checkpointing support
Aug 2, 2026
cec1c1a
Address Boogu checkpointing review comments
Aug 3, 2026
58eb19e
Add Chroma segmented checkpointing support
Aug 2, 2026
3531725
Address Chroma checkpointing review comments
Aug 3, 2026
7dfe469
Merge pull request #2936 from bghira/agent/segmented-checkpointing-ch…
bghira Aug 3, 2026
9051366
Bump version from 4.5.2 to 4.6.0
bghira Aug 3, 2026
6f57cbb
Add Cosmos segmented checkpointing support
Aug 2, 2026
8e9047f
Address Cosmos checkpointing review comment
Aug 3, 2026
a97b54e
Add Cosmos 3 segmented checkpointing support
Aug 2, 2026
ef6cf14
Add ERNIE segmented checkpointing support
Aug 2, 2026
6ec5fc5
Add Flux segmented checkpointing support
Aug 2, 2026
3316163
Forward Flux attention offload through checkpoint wrappers
Aug 3, 2026
2b1a0de
Add Flux.2 segmented checkpointing support
Aug 2, 2026
485b02d
Wrap Flux2 metal attention in offload context
Aug 3, 2026
e691bd2
Add HiDream segmented checkpointing support
Aug 2, 2026
cc9a8ba
Add HunyuanVideo segmented checkpointing support
Aug 2, 2026
d15a886
Add Ideogram segmented checkpointing support
Aug 2, 2026
07490ca
Add Kandinsky 5 segmented checkpointing support
Aug 2, 2026
5f47e52
Add Kolors ControlNet checkpointing compatibility
Aug 2, 2026
5a7eafa
Add Krea 2 segmented checkpointing support
Aug 2, 2026
690fbaf
Add LongCat segmented checkpointing support
Aug 2, 2026
5453d4b
Add LTXVideo segmented checkpointing support
Aug 2, 2026
8067336
Add LTXVideo2 segmented checkpointing support
Aug 2, 2026
ad114fe
Add Lumina2 segmented checkpointing support
Aug 2, 2026
450ff37
Add MageFlow segmented checkpointing support
Aug 2, 2026
3d12413
Add PixArt segmented checkpointing support
Aug 2, 2026
7cd94e4
Add Qwen Image segmented checkpointing support
Aug 2, 2026
f141c4e
Add Sana segmented checkpointing support
Aug 2, 2026
4fb941d
Add SanaVideo segmented checkpointing support
Aug 2, 2026
fa6597b
Use offloaded checkpointing for SanaVideo unsloth backend
Aug 3, 2026
f0eaa92
Add SD3 segmented checkpointing support
Aug 2, 2026
2265f19
Add Stable Cascade segmented checkpointing support
Aug 2, 2026
1e28e25
Clarify Stable Cascade checkpoint setter types
Aug 3, 2026
0d51ef4
Add Wan segmented checkpointing support
Aug 2, 2026
4088ddc
Add Wan checkpointing scope test
Aug 3, 2026
b9d4118
Add Z-Image segmented checkpointing support
Aug 2, 2026
b51487d
Disable Z-Image segmented path for FFN backends
Aug 3, 2026
aa39320
Add ZLab I1 segmented checkpointing support
Aug 2, 2026
3504e55
Merge pull request #2961 from bghira/agent/segmented-checkpointing-zl…
bghira Aug 3, 2026
d3f5031
Merge pull request #2918 from hjinnkim/bugfix/auto-repeat-gradient-ac…
bghira Aug 3, 2026
848be65
Merge pull request #2986 from hjinnkim/work/f2-resume-topology
bghira Aug 3, 2026
49fbd93
Merge pull request #2987 from hjinnkim/work/f3-filter-shard-length
bghira Aug 3, 2026
2891e79
Write RamTorch prefetch orders once per node
hjinnkim Aug 3, 2026
155c137
add licensing info to feature matrix
Aug 3, 2026
41d5c5f
Document model license statuses
Aug 3, 2026
7aa7288
Merge pull request #2991 from bghira/agent/add-model-license-matrix
bghira Aug 3, 2026
66da4d4
Refactor quickstart compatibility tables
Aug 3, 2026
4f7a3ac
Merge origin/main into license docs branch
Aug 3, 2026
91649f8
Merge pull request #2992 from bghira/agent/readme-license-table
bghira Aug 3, 2026
0af578c
(#2990) make state dict loader definitions more robust
Aug 3, 2026
b21a141
Merge pull request #2993 from bghira/pr/2990
bghira Aug 3, 2026
2b79ce6
Address Copilot checkpoint review comments
Aug 3, 2026
58fbf15
Merge pull request #2989 from hjinnkim/fix/checkpoint-rotation-off-by…
bghira Aug 3, 2026
1a7b204
Merge branch 'main' into fix/ramtorch-prefetch-save-race
bghira Aug 3, 2026
05f1b2d
Merge pull request #2988 from hjinnkim/fix/ramtorch-prefetch-save-race
bghira Aug 3, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
70 changes: 45 additions & 25 deletions README.es.md
Original file line number Diff line number Diff line change
Expand Up @@ -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

Expand Down
70 changes: 45 additions & 25 deletions README.hi.md
Original file line number Diff line number Diff line change
Expand Up @@ -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}

Expand Down
70 changes: 45 additions & 25 deletions README.ja.md
Original file line number Diff line number Diff line change
Expand Up @@ -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

Expand Down
Loading
Loading