HighCWu/ControlLoRA

combine different conditions

JunMa11 opened this issue · 1 comments

Hi @HighCWu ,

Thanks for sharing the great work.

Does ControlLoRA support combine multiple conditional inputs during inference?

For example, I independently trained

  • one canny edge map ControlLoRA model
  • one semantic segmentation map ControlLoRA model

During inference, can I use the edge map and segmentation map simultaneously to guide the generation process?

Adding multiple ControlLoRA in the processor should work. Because its internal principle includes LoRA. But recently I've been busy with other things and haven't had time to update the code. My README.md contains an experiment of mixing ControlLoRA and LoRA, which basically verifies the feasibility