InfiniteTalk: Unlimited-length Sound-driven Video Generation

详情

模型描述

InfiniteTalk with native support in ComfyUI, the best open-source lip-sync model.

Supports image-to-video generation from audio of unlimited length through looping, with customizable action descriptions.

YouTube: https://www.youtube.com/@EtherPandaAI

Experience link: https://www.runninghub.ai/post/2025797778844164097/?inviteCode=rh-v1493

此模型生成的图像