AdCnPipeline with inpainting

[HamnaAkram]

How to use the AdCnPipeline with inpainting?

I initialized the call as

pipe = AdCnPipeline.from_pretrained("stablediffusionapi/counterfeit-v30", torch_dtype=torch.float16, controlnet=controlnet)

but now how to activate inpainting?

[wly-ai-bj]

I met the same question. And how to load control image into pipeline? For example, we want to repair hand, we only need to load hand control image, not full body. So the hand control processer should be after the hand detector. But the hand detector can't edit.

[JemiloII]

You'll need to pass the hand detector as far as I know to detect the hands, by default it uses the face detector.