cvlab-kaist/VideoMaMa
Video matting via generative prior
View on index · View in 3D Map
Related repos
- Multimodal foundation models for video understanding
- Interactive image matting using stable diffusion
- subject-consistent video generation using text, images, and audio
- Video and image annotation tool for computer vision projects
- Turn images into cinematic videos with 33 facial expressions and 400+ motion combinations
- ComfyUI nodes for steering videos with image batches
- open source cinematic video generation with diffusion models
- LTX-Video, open source code for a model that generates videos from prompts or images using diffusion transformers
- Reframes image editing as video generation
- Synthesize video with camera control from one input
