InfiniteTalk-GGUF

Note: All model files below must be downloaded via the LM Downloader client. If you do not have the client, Download >>>

InfiniteTalk is an innovative sparse-frame video dubbing large model developed by Meituan. It can synthesize a new video with accurate lip synchronization and coordinated head movements, body postures, and facial expressions based on the input video and audio. This model supports the generation of infinitely long videos, has strong stability, and has fewer hand and body distortion issues compared to MultiTalk, with better lip synchronization. Additionally, it can also convert images and audio into videos as inputs. Note: InfiniteTalk has two models: single-person speech and multi-person conversation.