LongCat-Video-Avatar 1.5
Open-source audio-driven avatar video generation model built on LongCat-Video. It supports audio-text-to-video, audio-image-text-to-video, and video continuation with Whisper-Large lip synchronization, long-video stability, single/multi-stream audio, stylized-domain support, and 8-step distilled inference.
Modality
audio+text+image+video->video
License
mit
Open source
Yes
Open LongCat-Video-Avatar 1.5 in AIniverse
Compare versions, read real ratings, save to your stack.
Open in App