Hugging Face 热门模型第 29 名：FastVideo/FastH3-Omni-Comfy，162 赞，近期下载 264401 次。
标签：diffusion-single-file, comfyui, minimax-h3, fasth3-omni, reference-to-video, base_model:FastVideo/FastVideo-FastH3-Omni-8-Step-V1, base_model:finetune:FastVideo/FastVideo-FastH3-Omni-8-Step-V1, license:other, region:us
README：
FastH3 Omni for ComfyUI
ComfyUI-ready BF16 and INT8 ConvRot diffusion models for the final FastH3 Omni release. Generate video and synchronized audio from a prompt and ordered image, video and audio references.
Release collection · BF16 release · ComfyUI
Install the model files
Choose one diffusion model and place it in ComfyUI/models/diffusion_models/:
| File in this repository |
Format |
diffusion_models/fasth3_omniref_8step_pruned_bf16.safetensors |
BF16 diffusion model |
diffusion_models/fasth3_omniref_8step_pruned_int8_convrot.safetensors |
INT8 ConvRot diffusion model |
Install one text encoder and one video VAE, plus the audio VAE:
ComfyUI/models/
├── text_encoders/
│ ├── qwen3vl_32b_minimax_h3_bf16.safetensors
│ ├── qwen3vl_32b_minimax_h3_int8_convrot.safetensors
│ └── qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
└── vae/
├── minimax_h3_audio_vae_fp32.safetensors
├── minimax_h3_video_vae_fp16.safetensors
└── minimax_h3_video_vae_int8_convrot.safetensors
These files are available in this repository's text_encoders/ and vae/ folders. The text encoders include the vision tower needed for references. Accelerated NVFP4 text encoding requires Blackwell hardware; choose BF16 or INT8 for other devices.
For additional diffusion formats, see FP8 ComfyUI and NVFP4 QAD ComfyUI.
Generate video and audio
Use a current ComfyUI build with native MiniMax-H3 support and the MiniMax H3 Reference to Video conditioning node. Supply matching text-encoder, video-VAE and audio-VAE components.
- Eight sampling steps, guidance 1.0.
- Video shift 12.0 and audio shift 3.0.
- Reference inputs use
, and `` tags in the prompt.
- The audio VAE is required for synchronized audio output.
ComfyUI uses its own model layout, sampler and runtime kernels; outputs can differ from FastVideo and UniServe.
Other runtimes
Local AI resources
Run FastH3 Omni on DGX Spark or RTX 5090 through FastVideo using the FastVideo-format NVFP4 QAD weights. Start with the FastVideo cookbook and FastH3 Omni recipe builder; use the Spark recipe or RTX 5090 recipe and the local inference guide for the AdaLN table, offload and decoder setup.
FP8 weights are a separate FastVideo variant; the FP8 recipe for RTX 4090 illustrates the non-FP4 path with layerwise offload and compatible BF16 encoder components. Use each runtime's matching checkpoint format.
Acknowledgements
FastH3 Omni was built in close collaboration with Nuva Lab, which co-developed the model with FastVideo, defined and curated the omni reference dataset, and brought production-grounded creative video workflows to FastH3. For dedicated production deployment, fine-tuning on your own data and a creative agent on top, see Nuva Lab's FastH3-Omni page.
Thanks also to the NVIDIA FastGen team.
License
Use of these weights is governed by the MiniMax-H3 Community License Agreement.
Bundled ComfyUI tooling retains its own licenses in conversion/upstream/.
The original belongs to Hugging Face 热门模型 and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.
Studio