Diffusion Single File
comfyui
aryan5v's picture
Upload README.md with huggingface_hub
8a01321 verified
|
Raw History Blame Contribute Delete
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:
```
πŸ“‚ ComfyUI/
└── πŸ“‚ models/
β”œβ”€β”€ πŸ“‚ diffusion_models/
β”‚ β”œβ”€β”€ fastvideo_fasth3_trim_8step_bf16.safetensors
β”‚ β”œβ”€β”€ fastvideo_fasth3_trim_8step_fp8.safetensors
β”‚ β”œβ”€β”€ fastvideo_fasth3_trim_8step_int8_convrot.safetensors
β”‚ └── fastvideo_fasth3_trim_8step_nvfp4.safetensors
β”œβ”€β”€ πŸ“‚ text_encoders/
β”‚ β”œβ”€β”€ qwen3vl_32b_minimax_h3_bf16.safetensors
β”‚ β”œβ”€β”€ qwen3vl_32b_minimax_h3_int8_convrot.safetensors
β”‚ └── qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
β”œβ”€β”€ πŸ“‚ vae/
β”‚ β”œβ”€β”€ minimax_h3_audio_vae_fp32.safetensors
β”‚ β”œβ”€β”€ minimax_h3_video_vae_fp16.safetensors
β”‚ └── minimax_h3_video_vae_int8_convrot.safetensors
```