InfiniteTalk: Audio-Driven Full-Body Video Dubbing

Upload a source Image and target audio. Generate a full-body dubbed video with synchronized motion while preserving the original identity, background, and camera movement.

About

InfiniteTalk: Audio-Driven Full-Body Video Dubbing turns a single image and one or more audio tracks into a lip‑synced, full‑body video while preserving the original identity, background, and camera motion. The core of the pipeline is WanInfiniteTalkToVideo, which fuses features from the loaded Wan2.1 I2V model with an audio embedding to drive body and facial motion. Step1 - Load Models prepares the UNet and VAE (UNETLoader, VAELoader) for image‑to‑video synthesis, and loads text and audio backbones (CLIPLoader with CLIPTextEncode for camera/stage prompts, and AudioEncoderLoader with AudioEncoderEncode for voice features).

What you provide

  • Reading the workflow

Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.

Try in Cloud
Output
Example
Courtyard reunion, two speakers

Questions & answers