ComfyUI custom nodes providing unified image and mask resizing with support for multiple scaling modes, aspect-ratio preservation, center crop alignment, and stable tensor-based mask transformations, and more.
ComfyUI LTX Director fork with Motion Brush control for LTX 2.3 workflows
A professional node pack by **Magos Digital Studio** for DWPose & NLF skeleton editor, retargeter, and renderer for ComfyUI.
Remote GPU automation, docs, and workflow references for LTX 2.3 Text or Image plus Audio to Video with ComfyUI
LTX-2.3 is an open-source generative video architecture based on the Diffusion Transformer (DiT). The model delivers commercial-grade generation quality (on par with Google Veo 3) but without the strict limitations of closed ecosystems. The project supports both fully autonomous local inference and hybrid cloud processing.
Houdini/Solaris Hydra render delegate that turns USD scenes into AI-generated video via ComfyUI (LTX-2.3 22B distilled). Deterministic CPU rasterizer, conditioned on your shaded render, with generate-once convergence and full image-sequence output.
Timeline-based video editor for ComfyUI with scenes, project assets, gallery, images as keyframes, render staging, and takes for iterative long-form generation.
Codex skill for LTX-2.3 production prompts: T2V/I2V/A2V/V2V, Prompt Relay, dialogue/lipsync, keyframes, and workflow routing.
PyTorch implementation of "Sound Sparks Motion" paper
Native MLX inference on Apple silicon: LTX-2.3 and LTX-2.5 video with audio, GMNet SDR-to-HDR still expansion, Krea 2 and FLUX.2 Klein still-image generation and editing
Open-source benchmark for evaluating AI agents on talking-head video LoRA pipelines
A semantic relabeling research experiment investigating concept drift in the LTX-2.3 diffusion model through intentional dataset mislabeling.
To associate your repository with the ltx-2-3 topic, visit your repo's landing page and select "manage topics."