---
title: FastH3-Omni-FP8-Comfy
canonical_url: "https://www.modelscope.cn/models/FastVideo/FastH3-Omni-FP8-Comfy"
md_url: "https://www.modelscope.cn/models/FastVideo/FastH3-Omni-FP8-Comfy.md"
repository: FastVideo/FastH3-Omni-FP8-Comfy
last_updated: 2026-10-21
license: other
base_model:
  - FastVideo/FastVideo-FastH3-Omni-8-Step-V1
base_model_relation: finetune
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 153
stars: 0
tags:
  - comfyui
  - diffusion-single-file
  - minimax-h3
  - fasth3-omni
  - reference-to-video
  - fp8
---

# FastH3-Omni-FP8-Comfy

> FastH3-Omni-FP8-Comfy - FastVideo 在 ModelScope 开源的模型。FastH3 Omni FP8 for ComfyUI

FastVideo/FastH3-Omni-FP8-Comfy 是 ModelScope 魔搭社区上的机器学习模型，采用 other 许可，基于 FastVideo/FastVideo-FastH3-Omni-8-Step-V1 构建。

- **Repository**: FastVideo/FastH3-Omni-FP8-Comfy
- **License**: other
- **Base model**: FastVideo/FastVideo-FastH3-Omni-8-Step-V1
- **Tags**: comfyui, diffusion-single-file, minimax-h3, fasth3-omni, reference-to-video, fp8
- **Downloads**: 153
- **Stars**: 0
- **Last updated**: 2026-10-21

Source: https://www.modelscope.cn/models/FastVideo/FastH3-Omni-FP8-Comfy

---

# FastH3 Omni FP8 for ComfyUI

The ComfyUI-native FP8 diffusion model for FastH3 Omni. It generates video with synchronized 32-kHz stereo audio from a prompt and ordered image, video and audio references in eight sampling steps.

[Release collection](https://huggingface.co/collections/FastVideo/fasth3-omniref) · [BF16 release](https://huggingface.co/FastVideo/FastVideo-FastH3-Omni-8-Step-V1) · [Shared ComfyUI components](https://huggingface.co/FastVideo/FastH3-OmniRef-Comfy)

## Install

Place `fasth3_omniref_fp8_comfy.safetensors` in:

```text
ComfyUI/models/diffusion_models/fasth3_omniref_fp8_comfy.safetensors
```

Download a compatible text encoder, video VAE and audio VAE from [FastH3 Omni Comfy](https://huggingface.co/FastVideo/FastH3-OmniRef-Comfy) and place them in `ComfyUI/models/text_encoders/` and `ComfyUI/models/vae/`. The audio VAE and the text encoder's reference-vision support are required. Select a text-encoder format supported by your GPU.

FP8 uses ComfyUI’s native quantization layout and kernels. Quantized output can differ from BF16. This is the ComfyUI format; use the separate FastVideo-format model for FastVideo inference.

## Generate video and audio

Use a current [ComfyUI](https://github.com/Comfy-Org/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](https://huggingface.co/FastVideo/FastVideo-FastH3-Omni-8-Step-V1) and [deployment guide](https://github.com/hao-ai-lab/uniserve/blob/main/docs/minimax_h3/minimax_h3.md).
- **FastVideo local AI — DGX Spark and RTX 5090:** use the [FastVideo-format NVFP4 QAD model](https://huggingface.co/FastVideo/FastH3-OmniRef-NVFP4-QAD) and [local inference guide](https://github.com/hao-ai-lab/FastVideo/blob/main/docs/inference/fasth3_omniref.md).

## Local AI resources

Run FastH3 Omni on **DGX Spark or RTX 5090 through FastVideo** using the [FastVideo-format NVFP4 QAD weights](https://huggingface.co/FastVideo/FastH3-OmniRef-NVFP4-QAD). Start with the [FastVideo cookbook](https://haoailab.com/FastVideo/cookbook/) and [FastH3 Omni recipe builder](https://haoailab.com/FastVideo/cookbook/minimax-h3/fasth3-omniref/); use the [Spark recipe](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_fasth3_omniref_spark.yaml) or [RTX 5090 recipe](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_fasth3_omniref_rtx5090.yaml) and the [local inference guide](https://github.com/hao-ai-lab/FastVideo/blob/main/docs/inference/fasth3_omniref.md) for the AdaLN table, offload and decoder setup.

[FP8 weights](https://huggingface.co/FastVideo/FastH3-OmniRef-FP8) are a separate FastVideo variant; the [FP8 recipe for RTX 4090](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_fasth3_omniref_rtx4090.yaml) 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](https://nuvalab.ai/fasth3/), 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](https://nuvalab.ai/fasth3/).

Thanks also to the NVIDIA FastGen team.

## License

Use of these weights is governed by the [MiniMax-H3 Community License Agreement](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE).
Bundled ComfyUI tooling retains its own licenses in `conversion/upstream/`.