HunyuanVideo

HunyuanVideo

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.

HunyuanVideo-I2V is the image-to-video generation version of HunyuanVideo. We also provide advanced VRAM management for this model.

VRAM required	Example script	Frames	Resolution	Note
80G	hunyuanvideo_i2v_80G.py	129	720p	No VRAM management.
24G	hunyuanvideo_i2v_24G.py	129	720p	The video is consistent with the original implementation, but it requires 5%~10% more time than hunyuanvideo_80G.py

Gallery

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:

video_to_video.mp4

Video generated by hunyuanvideo_i2v_80G.py and hunyuanvideo_i2v_24G.py:

video_720p.mp4