Style transfer

Run this model on Replicate:

https://replicate.com/fofr/style-transfer

Or run it in ComfyUI:

https://github.com/fofr/cog-style-transfer/blob/main/style-transfer-ui.json

You’ll need the following custom nodes:

• ComfyUI IPAdapter Plus
• ComfyUI Essentials
• ComfyUI ControlNet Aux

Developing locally

Clone this repository:

git clone --recurse-submodules https://github.com/fofr/cog-style-transfer.git && cd cog-style-transfer/ComfyUI

Create python venv and activate

python3 -m venv . && source bin/activate

Install the required dependencies

pip install -r requirements.txt

Download dreamshaperXL_lightningDPMSDE.safetensors to models/checkpoints

wget https://huggingface.co/gingerlollipopdx/ModelsXL/resolve/main/dreamshaperXL_lightningDPMSDE.safetensors?download=true -O models/checkpoints/dreamshaperXL_lightningDPMSDE.safetensors

Download CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors to models/clip_vision

wget https://huggingface.co/h94/IP-Adapter/resolve/main/models/image_encoder/model.safetensors?download=true -O models/checkpoints/CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors

Download ip-adapter-plus_sdxl_vit-h.safetensors to models/ipadapter

wget https://huggingface.co/h94/IP-Adapter/resolve/main/sdxl_models/ip-adapter-plus_sdxl_vit-h.safetensors?download=true -O models/ipadapter/ip-adapter-plus_sdxl_vit-h.safetensors

Download depth-zoe-xl-v1.0-controlnet.safetensors to models/controlnet

wget https://huggingface.co/SargeZT/controlnet-sd-xl-1.0-depth-16bit-zoe/resolve/main/depth-zoe-xl-v1.0-controlnet.safetensors?download=true -O models/controlnet/depth-zoe-xl-v1.0-controlnet.safetensors

Run the following script to install all the custom nodes:

./scripts/clone_plugins.sh

Finally, install it, run it and enjoy it!

python3 main.py

Running the Web UI from your Cog container

1. GPU Machine: Start the Cog container and expose port 8188:

sudo cog run -p 8188 bash

Running this command starts up the Cog container and let's you access it

2. Inside Cog Container: Now that we have access to the Cog container, we start the server, binding to all network interfaces:

cd ComfyUI/
python main.py --listen 0.0.0.0

3. Local Machine: Access the server using the GPU machine's IP and the exposed port (8188): http://<gpu-machines-ip>:8188

When you goto http://<gpu-machines-ip>:8188 you'll see the classic ComfyUI web form!