| --- |
| license: other |
| license_name: minimax-h3-community-license-agreement |
| license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE |
| base_model: FastVideo/FastVideo-FastH3-Omni-8-Step-V1 |
| tags: |
| - video-generation |
| - reference-to-video |
| - text-to-audio-video |
| - fastvideo |
| - minimax-h3 |
| - fasth3-omni |
| - fp8 |
| --- |
| |
| # FastH3 Omni FP8 |
|
|
| FP8 diffusion weights for FastH3 Omni, the eight-evaluation reference-conditioned video-and-audio model. This is the FastVideo-format FP8 variant of the [BF16 release](https://huggingface.co/FastVideo/FastVideo-FastH3-Omni-8-Step-V1). |
|
|
| [Release collection](https://huggingface.co/collections/FastVideo/fasth3-omniref) · [FastVideo inference guide](https://github.com/hao-ai-lab/FastVideo/blob/main/docs/inference/fasth3_omniref.md) |
|
|
| ## Use with FastVideo |
|
|
| Follow the [FastH3 Omni device and memory guide](https://github.com/hao-ai-lab/FastVideo/blob/main/docs/inference/fasth3_omniref.md#device-profiles). The FP8 transformer is useful on GPUs without FP4 tensor cores, including RTX 4090 and Hopper, and on Blackwell when FP8 is preferred. The RTX 4090 profile uses layerwise transformer offload and the dense video VAE. |
|
|
| The bundled text encoder is NVFP4 and needs Blackwell FP4 kernels. On non-FP4 hardware, compose the transformer with compatible BF16 text-encoder components from MiniMax-H3 rather than selecting that bundled encoder. The guide explains model-directory composition and memory requirements. |
|
|
| For UniServe deployments on GB200/B200, RTX PRO 6000 Blackwell or Hopper, start from the [BF16 release](https://huggingface.co/FastVideo/FastVideo-FastH3-Omni-8-Step-V1) and follow the [UniServe guide](https://github.com/hao-ai-lab/uniserve/blob/main/docs/minimax_h3/minimax_h3.md). For Spark and RTX 5090 local inference, use the [NVFP4 QAD variant](https://huggingface.co/FastVideo/FastH3-OmniRef-NVFP4-QAD) with FastVideo's matching profiles. |
|
|
| ## Contents |
|
|
| | Component | Purpose | |
| | --- | --- | |
| | `transformer_ref/` | FP8 reference-conditioned transformer with BF16 sensitive components | |
| | `transformer/` | Alternate directory containing the same transformer weights | |
| | `text_encoder/` | NVFP4 Qwen3-VL text and vision encoder; Blackwell only | |
| | `vae/`, `audio_vae/` | Video and audio VAEs | |
| | `scheduler/`, `audio_scheduler/`, `processor/`, `tokenizer/` | Sampling and input processing | |
| | `fastvideo_inference.json` | Eight-evaluation FastH3 Omni inference configuration | |
| | `adaln_table.pt` | Precomputed modulation table for the supplied schedule | |
|
|
| FP8 quantization changes numerical output relative to BF16. These weights use the FastVideo FP8 layout; use the [FP8 ComfyUI variant](https://huggingface.co/FastVideo/FastH3-OmniRef-FP8-Comfy) for ComfyUI. |
|
|
| ## 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. |
|
|
| ## License |
|
|
| Use of these weights is governed by the [MiniMax-H3 Community License Agreement](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE). |
|
|
