smthemex/ComfyUI_Sonic
A ComfyUI custom node for audio-driven portrait animation using the Sonic method with Whisper and Stable Video Diffusion models.
Not currently ranked — collecting fresh signals.
star history
This repository provides a ComfyUI integration for Sonic, a portrait animation technique that animates a person’s face driven by audio input. It leverages OpenAI’s Whisper-tiny model for audio processing and Stability AI’s Stable Video Diffusion (SVD) model for video generation. Users can input a portrait image and audio to generate synchronized talking-head animations.
Frequently asked
- What is smthemex/ComfyUI_Sonic?
- A ComfyUI custom node for audio-driven portrait animation using the Sonic method with Whisper and Stable Video Diffusion models.
- Is ComfyUI_Sonic open source?
- Yes — smthemex/ComfyUI_Sonic is open source, released under the MIT license.
- What language is ComfyUI_Sonic written in?
- smthemex/ComfyUI_Sonic is primarily written in Python.
- How popular is ComfyUI_Sonic?
- smthemex/ComfyUI_Sonic has 1.1k stars on GitHub.
- Where can I find ComfyUI_Sonic?
- smthemex/ComfyUI_Sonic is on GitHub at https://github.com/smthemex/ComfyUI_Sonic.