requirements.txt
| 1 | # MiniMax-H3 Turbo LoRA 4-step generator. |
| 2 | # The base model / VAE / text-encoder module definitions come from a ComfyUI |
| 3 | # checkout (see generate.py header): git clone + checkout 14b05228, then install |
| 4 | # ComfyUI's own requirements. The packages below are what generate.py itself |
| 5 | # needs on top of that. |
| 6 | torch>=2.4 |
| 7 | safetensors>=0.4 |
| 8 | imageio>=2.34 |
| 9 | imageio-ffmpeg>=0.5 |
| 10 | numpy>=1.24 |
| 11 | |