https://github.com/benda1989/Sonic_ComfyUI
component for text to long video in ComfyUI
https://github.com/benda1989/Sonic_ComfyUI
comfyui cosyvoice2 sonic
Last synced: about 2 months ago
JSON representation
component for text to long video in ComfyUI
- Host: GitHub
- URL: https://github.com/benda1989/Sonic_ComfyUI
- Owner: benda1989
- Created: 2025-02-24T02:53:05.000Z (about 2 months ago)
- Default Branch: main
- Last Pushed: 2025-02-24T03:04:45.000Z (about 2 months ago)
- Last Synced: 2025-02-24T04:20:33.225Z (about 2 months ago)
- Topics: comfyui, cosyvoice2, sonic
- Language: Python
- Homepage:
- Size: 908 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-comfyui - **GKK·Sonic**
README
# ComfyUI_Sonic
[Sonic](https://github.com/jixiaozhong/Sonic) is a method about ' Shifting Focus to Global Audio Perception in Portrait Animation',
You can produce video as long as you want by text with this comfyUI compentent# Installation
In the ./ComfyUI/custom_node directory, run the following:
```sh
git clone https://github.com/benda1989/Sonic_ComfyUI.git
cd Sonic_ComfyUI
pip install -r requirements.txt
```# Model
Download model same as [Sonic](https://github.com/jixiaozhong/Sonic), and file tree looks like this:
```
-- ComfyUI/models/sonic/
|-- audio2bucket.pth
|-- audio2token.pth
|-- unet.pth
|-- yoloface_v5m.pt
|-- whisper-tiny/
|--config.json
|--model.safetensors
|--preprocessor_config.json
|-- RIFE/
|--flownet.pkl
-- ComfyUI/models/checkpoints
├── svd_xt.safetensors or svd_xt_1_1.safetensors
```# Example
## 1 Base usage, audio to video
## 2 Adv usage, text to video

example gpu usage
# Thanks
[Sonic](https://github.com/jixiaozhong/Sonic)
[ComfyUI_Sonic](https://github.com/smthemex/ComfyUI_Sonic)