This repo contains the code from my YouTube tutorial on building a Python API to connect Gradio and Comfy UI for AI image generation with Stable Diffusion models.
https://github.com/SharCodin/comfy-gradio-api.git
This project shows:
- How to connect a Gradio front-end interface to a Comfy UI backend
- Sending workflow data as API requests
- Updating generation parameters dynamically
- Displaying generated images in Gradio
- Adding text and image inputs
- Using a smartphone camera for image inputs
By the end, you'll understand the basics of building a Python API and connecting a user interface with an AI workflow.
To run the code:
- Clone the repo
- Install dependencies (
pip install requests Pillow gradio numpy
) - Modify the Comfy UI installation path
- Open
python image_to_image.py
and modify theINPUT_DIR
andOUTPUT_DIR
and' folder path image_to_image.py: resized_image.save(os.path.join(INPUT_DIR, "test_api.jpg"))The "test_api.jpg" is equal to the image of wlopsimple_api.json loading node's "image": "test_api.jpg" - Open the localhost link to view in Gradio interface
The main files:
image_to_image.py
- Contains Gradio UI and API logicwlopsimple_api.json
- Saved Comfy UI workflow
Let me know if you have any other questions!