HunyuanVideo is a video generation model trained by Tencent. We provide advanced VRAM management for this model, including three stages:
| VRAM required | Example script | Frames | Resolution | Note |
|---|---|---|---|---|
| 80G | hunyuanvideo_80G.py | 129 | 720*1280 | No VRAM management. |
| 24G | hunyuanvideo_24G.py | 129 | 720*1280 | The video is consistent with the original implementation, but it requires 5%~10% more time than hunyuanvideo_80G.py |
| 6G | hunyuanvideo_6G.py | 129 | 512*384 | The base model doesn't support low resolutions. We recommend users to use some LoRA (example) trained using low resolutions. |
Video generated by hunyuanvideo_80G.py and hunyuanvideo_24G.py:
video_girl.mp4
Video generated by hunyuanvideo_6G.py using this LoRA:
video_walking.mp4
Video to video generated by hunyuanvideo_v2v_6G.py using this LoRA: