Is it possible to use with Stable Diffusion XL?
Is it possible to use it as it is? Is a specific support required?
Any updates on this? Plan / Roadmap @lllyasviel
use HuggingFace Diffuser's training script https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sdxl.md
https://huggingface.co/stabilityai/control-lora
Anyone working on this for the ControlNet repo? I guess we would need to change the config so that tool_add_control.py works. And has someone tried to train it on the link https://github.com/lllyasviel/ControlNet/issues/461#issuecomment-1722415410 ?
I have managed to create a ControlNet checkpoint for Stable Diffusion XL (sd_xl). It is not a beautiful implementation. It seems that the UnetModel in ldm/modules/diffusionmodules/openaimodel.py is outdated to use the config from sd_xl. The sd_xl implementation can be found in https://github.com/Stability-AI/generative-models/blob/main/sgm/modules/diffusionmodules/openaimodel.py
I am not sure if anyone is intereseted in this. Maybe this repository is not being used anymore and people are using more diffusers or generative-models