What is this?

A simple workflow that takes your input image and uses it as a character reference to generate new images of the same character. It helps keep the character’s [face / hairstyle / outfit / colors] consistent across different poses and scenes. You can change the outfit or just take the head as reference.

How to use

1. Load the workflow in ComfyUI.

2. Install the required models and custom nodes.

3. Upload your reference image in the [Load Image].

4. Write your prompt for the pose or scene you want.

5. Press Run to generate.

It does support 2 character!
I also add lora node, you can load lora inside subgraph.

Credit to Electrongirl