HunyuanCustom
Tencent Hunyuan multimodal custom video generation — describe, act, swap people
Tencent Hunyuan multimodal custom video generation: describe images, act scenes, swap people.
AI video generation, digital humans, and video restoration.
Key features
- Subject-consistent video generation from text, image, audio, video
- Single and multi-subject customization
- Audio-driven and video-driven customization modes
- Single GPU with 8GB VRAM support; ComfyUI integration
Good for
- Virtual human advertisements and virtual try-on
- Video editing by swapping subjects from a reference image
Stack & tags
video-customizationsubject-consistencyimage-to-videoaudio-drivenvideo-editingcomfyuiopen-weights
Similar open-source projects
Hyperframes
★ 55,468Write HTML. Render video. Built for agents — HeyGen's open-source video framework
Hypit
★ 18,649Clone any viral video with AI agents — swap the face, the words, the B-roll, ship 100 variants