What is ControlNet?
ControlNet is a group of neural networks that can control the artistic and structural aspects of image generation. The popular ControlNet models include canny, depth, openpose, etc. You can install ControlNet in Stable Diffusion Webui as an extension.
How to install Controlnet in Stable Diffusion Webui?
1. If you don’t have Stable Diffusion Webui installed, go to Install stable diffusion webui on Windows.
2. Run “stable-diffusion-webui/webui-user.bat” to open Stable Diffusion Webui in a browser at http://127.0.0.1:7860/.
3. Click Extensions tab at the top. Then click “Install from URL” tab. Enter https://github.com/Mikubill/sd-webui-controlnet.git
to “URL for extension’s git repository”. Click Install.
4. Go to sd_controlnet_collection to download ControlNet models, for example, “t2i-adapter_xl_canny.safetensors.” Put it at “stable-diffusion-webui\extensions\sd-webui-controlnet\models” directory.
5. Close your Webui console and browser. Rerun Webui. You will see the ControlNet section at the left bottom area of the screen. Now we test it how it works.
6. Select a checkpoint from the drop down on the top area of the screen. In txt2image tab, enter your prompt.
7. Expand the ControlNet section, drag your reference image inside the ControlNet first single image. Check “Enable.“
8. In Control Type, check “Canny,” the Preprocessor will fill with “canny.” In Model, select “t2i-adapter_xl_canny.safetensors.”
9. Click Generate button, you will see the generated image is impacted by the input image in ControlNet.