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.

概要

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).

入力するもの

  • ワークフローを読み込み中

ComfyUI で実行できます。 このワークフローはこのページでは実行できません。すべてが読み込まれた状態でComfy Cloudで開くか、ご自身のComfyUI用にダウンロードしてください。

Cloudで試す
出力
例
Courtyard reunion, two speakers

よくある質問