HunyuanVideo-1.5 Distill Models
Details
Download Files
About this version
Model description
Update your ComfyUI to the latest (Github version) => cd to ComfyUI directory -> terminal -> git pull -> restart ComfyUI
Lightx2v 4-Steps ( works only with lightx2v inference for now https://huggingface.co/lightx2v/Hy1.5-Quantized-Models/tree/main | Black screen issue with sage attention, regular distilled versions: No issues)
CFG 1 Steps 50 [ Steps & duration tests https://civitai.com/posts/24588281 ]
Workflows in the zip files (i2v & t2v) + download links (text encoders, vae, clip vision, upscalers)
Type: Lightweight, open-source video generation model (Diffusion Transformer, 8.3B parameters)
Capabilities: High-quality text-to-video (T2V) and image-to-video (I2V) synthesis
Efficiency Features: Selective and Sliding Tile Attention for faster inference on consumer GPUs
Additional Support: Bilingual prompts, integrated super-resolution to 1080p
Performance: State-of-the-art visual quality and motion coherence among open-source models
These models are redistributed here for the sake of convenience.