fudan-generative-vision/hallo2
Generates long 4K portrait animations from a single image and audio, with optional text prompts for expression control
View on index · View in 3D Map
Related repos
- Audio-driven synthesis for portrait image animation
- Generates mathematical animations from text prompts
- Generative engine for creating interactive 3D worlds
- multi-subject image generation with controllable identity and style
- AI model for generating photos in different styles while keeping your face recognizable
- animate portraits with fine-grained control over head, mouth, and eyes
- turns static character images into controllable animations
- Turn images into cinematic videos with 33 facial expressions and 400+ motion combinations
- AI tool for turning cartoon images or sketches into smooth animations
- audio-driven talking head video generation using diffusion models
