---
license: unknown
---
this model for https://github.com/smthemex/ComfyUI_Sonic  <br>
I upload here for easily personal use in the runpod <br>
Original work go to this dev. custom node <br>

```
save and extract zip file in the models folder

Download zip file and unet.pt 
curl -L -o Sonic.zip https://huggingface.co/iimate/sonicunet-backup/resolve/main/Sonic.zip

--  ComfyUI/models/sonic/
    |-- audio2bucket.pth
    |-- audio2token.pth
    |-- unet.pth
    |-- yoloface_v5m.pt
    |-- whisper-tiny/
        |--config.json
        |--model.safetensors
        |--preprocessor_config.json
    |-- RIFE/
        |--flownet.pkl
```

In stall unzip tool in linux
```
apt update && apt install unzip -y
```
unzip !
```
unzip Sonic.zip
```


Download this model into ComfyUI/checkpoint https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1/tree/main <br>
```
wget --header="Authorization: Bearer hf_YourTokenHere" \
"https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1/resolve/main/svd_xt_1_1.safetensors"
```

or  <br>
This one https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt/tree/main <br>
```
wget --header="Authorization: hf_YourTokenHere" \
"https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt/resolve/main/svd_xt_image_decoder.safetensors"
```

pip install opencv-python <br>