This workflow can split the image into 2 regions based on a drawn mask. Both regions are sampled interchangeably allowing each region to use different LoRA models. As a result, LoRA in one region have 0 influence on the other. To ensure that regions stay consistent with each other, OpenPose ControlNet is used. This also allows for interaction between the characters. You can, though don't need to provide your own OpenPose images, you can extract them from photos or generate them on the spot. The main limitation is how well the preprocessor can detect the pose in the image. For that reason providing your own image will still give the best quality, but of course requires more effort.

If you need something for more characters than 2, try my Region LoRA PLUS workflow.

Why use this version over PLUS for 2 characters?

In PLUS, you need to draw a mask for each region, while here you draw just one and the second region is taken as the unmasked area, so the border between them is pixel-perfect and it's easier to achieve an artifact-less image.

The workflow includes a second pass, an upscaler and many QoL features.

More specific instructions inside

Requires:

• WAS's Comprehensive Node Suite - ComfyUI
• ComfyUI Impact Pack
• ComfyUI Inspire Pack
• ComfyUI-Custom-Scripts
• comfyui_controlnet_aux

(with ComfyUI Manager go to Manager -> Install Missing Node