Instructions to use FastVideo/FastVideo-FastH3-Trim-Comfy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use FastVideo/FastVideo-FastH3-Trim-Comfy with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
|
Download README.md from FastVideo/FastVideo-FastH3-Trim-Comfy: direct link, hf CLI and curl.
- Browser
- Download file 2.25 kB
-
https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-Comfy/resolve/main/README.md
- Command line
-
hf download hf://FastVideo/FastVideo-FastH3-Trim-Comfy/README.md
-
curl -L -o README.md https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-Comfy/resolve/main/README.md
2.25 kB
| license: other | |
| license_name: minimax-h3-community-license-agreement | |
| license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE | |
| tags: | |
| - comfyui | |
| - diffusion-single-file | |
| base_model: | |
| - MiniMaxAI/MiniMax-H3 | |
| - FastVideo/FastVideo-FastH3-Trim-8-Step | |
| # FastVideo FastH3 Trim | |
| Repackaged model files for ComfyUI. | |
| Original model repository: https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-8-Step | |
| FastH3 Trim is an experimental pruned FastH3 model: 42 transformer blocks instead of 50 and a rank-16 timestep | |
| conditioning, sampled in 8 steps. It is 4.2Γ smaller than base H3 and faster than FastH3 V2. | |
| Use the **FastVideo FastH3: Text to Video** template (ComfyUI 0.36.0 or later) and pick one of the files below in | |
| its `UNETLoader`. Keep the template's sampler settings: 8 steps, `res_multistep`, `simple`, and the | |
| `MiniMaxH3SigmaShift` node at 10 (video) and 3 (audio). | |
| | Diffusion model | Size | Use it on | | |
| |---|---:|---| | |
| | `fastvideo_fasth3_trim_8step_nvfp4.safetensors` | 11.9 GB | NVIDIA Blackwell: RTX 50 series, RTX PRO 6000, DGX Spark | | |
| | `fastvideo_fasth3_trim_8step_fp8.safetensors` | 19.7 GB | NVIDIA Ada and newer: RTX 40 series | | |
| | `fastvideo_fasth3_trim_8step_int8_convrot.safetensors` | 18.9 GB | Any recent NVIDIA GPU; matches the template's default format | | |
| | `fastvideo_fasth3_trim_8step_bf16.safetensors` | 37.5 GB | Reference quality, or for converting to other formats | | |
| Place the files in the following folders: | |
| ``` | |
| π ComfyUI/ | |
| βββ π models/ | |
| βββ π diffusion_models/ | |
| β βββ fastvideo_fasth3_trim_8step_bf16.safetensors | |
| β βββ fastvideo_fasth3_trim_8step_fp8.safetensors | |
| β βββ fastvideo_fasth3_trim_8step_int8_convrot.safetensors | |
| β βββ fastvideo_fasth3_trim_8step_nvfp4.safetensors | |
| βββ π text_encoders/ | |
| β βββ qwen3vl_32b_minimax_h3_bf16.safetensors | |
| β βββ qwen3vl_32b_minimax_h3_int8_convrot.safetensors | |
| β βββ qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors | |
| βββ π vae/ | |
| β βββ minimax_h3_audio_vae_fp32.safetensors | |
| β βββ minimax_h3_video_vae_fp16.safetensors | |
| β βββ minimax_h3_video_vae_int8_convrot.safetensors | |
| ``` | |