| --- |
| license: other |
| base_model: FastVideo/FastVideo-FastH3-8-Step-V2 |
| tags: [video-generation, text-to-video, audio, fastvideo, nvfp4] |
| --- |
| # FastH3 V2, 8-step, NVFP4 for one GPU |
|
|
| FastH3 V2 (8 distilled steps, video with synchronized audio) packaged for a single Blackwell GPU (RTX 5090, |
| RTX PRO 6000) or a DGX Spark. |
|
|
| - **Transformer:** FastH3 V2 (50 blocks). MLP linears keep the calibrated NVFP4 weights and activation scales from |
| [FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4](https://huggingface.co/FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4); |
| attention projections and sparse-attention gates are also stored in NVFP4. |
| - **Text encoder:** NVFP4 Qwen3-VL trimmed to the 50 layers H3 reads. |
| - **VAE:** LynnReal lightweight video VAE with Kijai's INT8 weights; H3 audio VAE. |
| - **Sampling:** `fastvideo_inference.json` holds the 8-step DMD schedule, which FastVideo reads automatically. |
|
|
| ## Machines with less than 64 GB of system RAM |
|
|
| The 50 AdaLN timestep projections are 26 GB in BF16. `transformer/adaln_tables.pt` (155 MB) holds their precomputed |
| outputs for the 8-step schedule, so FastVideo can skip loading them: |
|
|
| ```python |
| import os |
| from huggingface_hub import hf_hub_download |
| |
| os.environ["FASTVIDEO_H3_ADALN_TABLE"] = hf_hub_download( |
| "FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4-Consumer", "transformer/adaln_tables.pt") |
| ``` |
|
|
| The table covers only the shipped schedule (`fastvideo_inference.json`); FastVideo raises an error for other timesteps. |
|
|
| For multi-GPU data-center serving, use [FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4](https://huggingface.co/FastVideo/FastVideo-FastH3-8-Step-V2-NVFP4). |
| Smaller, faster experimental variant: [FastVideo/FastVideo-FastH3-Trim-8-Step-NVFP4](https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-8-Step-NVFP4). |
|
|
