InfiniteTalk: Audio-Portrait to Lip-Synced Video in ComfyUI
μΈλΆ μ 보
νμΌ λ€μ΄λ‘λ (1)
μ΄ λ²μ μ λν΄
λͺ¨λΈ μ€λͺ
π Create realistic talking avatar videos from a single portrait and voice input β with accurate lip-sync and identity-stable animation.
βΆοΈ Run Directly in Cloud:
https://www.runcomfy.com/comfyui-workflows/comfyui-infinitetalk-workflow-audio-portrait-to-lip-synced-video?utm_source=civitai
π‘ Overview
InfiniteTalk is a ComfyUI workflow that generates lip-synced talking videos from a single image and voice input. Powered by the MultiTalk AI model, it produces fluid, identity-stable portrait clips with natural speech motion and prompt-driven customizable animation.
Ideal for content creators, educators, marketers, and anyone who needs realistic talking avatars without filming.
β¨ Key Features
Single Image + Audio: Just provide a portrait and a voice clip β the workflow handles the rest.
Accurate Lip-Sync: Natural mouth movements precisely synchronized to the audio input.
Identity Preservation: Facial structure, expression style, and appearance remain consistent throughout.
Prompt-Driven Customization: Fine-tune animation behavior and visual style with text prompts.
π Getting Started
Upload a portrait image β clear, well-lit, forward-facing works best.
Provide an audio clip β speech or narration you want the avatar to speak.
Generate β the workflow produces a lip-synced video with the original audio muxed in.
Click the "Run Directly" link above to bypass local setup and test this workflow immediately in your browser.