# smthemex/ComfyUI_Sonic

Sonic is a method about ' Shifting Focus to Global Audio Perception in Portrait Animation',you can use it in comfyUI

Repository: https://github.com/smthemex/ComfyUI_Sonic
Canonical: https://ross.abutalabs.com/products/comfyui_sonic
Language: Python
License: MIT
License Family: permissive
Last push: 2026-05-04T00:21:41+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 80, release rhythm 35, longevity 40
- inputs: {"age_days": 572, "days_push": 122, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1140, forks 109 (observed 2026-08-28T04:03:44.335398+00:00)

## What it is
A ComfyUI custom node implementing the Sonic method for audio-driven portrait animation, generating talking-head videos from a single portrait image and an audio clip. It uses Stable Video Diffusion, Whisper audio features, and face detection models to animate lips and head motion in sync with audio.

## Use cases
- generate a talking head video from a photo and audio
- animate a portrait to match speech audio
- create lip-synced avatar videos in ComfyUI
- make an AI presenter from a single image
- audio-driven face animation workflow
- turn voiceover into a portrait video

## When to choose
- you already use ComfyUI and want audio-driven portrait animation
- you need a talking-head video from one image plus audio
- you want a node-based workflow for lip-sync generation

## When to avoid
- you need a standalone CLI or web app rather than a ComfyUI node
- you lack a GPU or the multi-GB SVD checkpoints
- you need full-body video generation or high-fidelity long-form video

## Facets
- artifact type: plugin
- maturity: active
- function: video-processing, audio-processing, machine-learning, speech-recognition, computer-vision
- domain: artificial-intelligence, media
- platform: python, cross-platform
- tags: comfyui, custom-node, talking-head, portrait-animation, lip-sync, audio-driven, svd, stable-video-diffusion, whisper, video, audio, gpu

## Member repositories
- smthemex/ComfyUI_Sonic (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:44.335398+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:35:48.717964+00:00, confidence not recorded.
  - readme: https://github.com/smthemex/ComfyUI_Sonic (fetched 2026-08-28T04:03:44.335398+00:00, sha d31409bddcf7)
- Data as of 2026-08-30T08:39:29.467469+00:00.