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 <Picture 1>, <Video 1> and <Audio 1> 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

UniServe — GB200/B200, RTX PRO 6000 Blackwell and Hopper: use the BF16 release and deployment guide.
FastVideo local AI — DGX Spark and RTX 5090: use the FastVideo-format NVFP4 QAD model and local inference guide.

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/.