This is and attempt to apply LoRA, Openpose and Masked conditioning. The main idea is to controll two characters defined by LoRA. This time around using the regional prompting by ComfyUI-Fluxtapoz

Remember to install all required custom nodes! Or install the ComfyUI Manager and click "Install Missing Custom Nodes". Make sure to have a recent version of pytorch.

On first launch make sure to:

> Load checkpoint;

> Specify LoRAs (if you use only one, bypass the second lora loader);

> Add global prompt to CLIP global +;

> Add prompts for characters L and R;

> Load ControlNET  openpose model

> Load images for controlNET and regional prompting (for the latter, use the mask editor);

> Load upscaling model;

> Adjust the initial latent resolution and latent upscaling factor (default: x1.5);

// > Load SAM and Ultralitics for the face detailer; //TODO?

The workflow is not stable and needs the tokens/loras/controlnet weights to be adjusted for each model and lora individually!