Difference between Controlnet inpainting for SD2 and SD3

Firstly great work with adding SD3 support on diffusers!

I was trying to run the SD3 controlnet inpainting script : [https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/controlnet_sd3/pipeline_stable_diffusion_3_controlnet_inpainting.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/controlnet_sd3/pipeline_stable_diffusion_3_controlnet_inpainting.py) and realized that its doesn't have the concept of an init_image like [https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py).

I want to inpaint part of an image using a canny edge image (as my control). How would I do this in SD3?

Thanks in advance!

Vergleiche src/diffusers/pipelines/controlnet_sd3/pipeline_stable_diffusion_3_controlnet_inpainting.py mit src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py und konzentriere dich darauf, wie init_image gehandhabt wird. Bestimme den erwarteten SD3-Workflow für die Kombination von Inpainting mit einem Canny-Kontrollbild, und definiere die für dieses Verhalten erforderliche Implementierung und Validierung.

Vom Indexierungsmodell aus dem Issue-Text verfasst.