sd-webui-controlnet

WebUI extension for ControlNet. Note: (WIP), so don't expect seed reproducibility - as updates may change things.

Go to file

Kohya S b89a575b28 make diff in advance		2023-02-16 08:28:42 +09:00
annotator	fix: unload models when switching preprocessor	2023-02-15 13:03:35 +00:00
models	Create cldm_v21.yaml	2023-02-15 17:22:02 +09:00
samples	docs: remove poc smaple	2023-02-15 02:01:13 +00:00
scripts	Update cldm.py	2023-02-16 06:52:06 +09:00
.gitignore	feat: make canny mode works	2023-02-13 07:05:22 +00:00
README.md	docs: minor fix	2023-02-15 21:18:04 +00:00
extract_controlnet.py	feat: make canny mode works	2023-02-13 07:05:22 +00:00
extract_controlnet_diff.py	make diff in advance	2023-02-16 08:28:42 +09:00
install.py	fix: impl transfer control from original repo	2023-02-15 20:06:23 +00:00
preload.py	add additional models path in settings tab	2023-02-15 03:59:29 -05:00

README.md

sd-webui-controlnet

(WIP) WebUI extension for ControlNet

This extension is for AUTOMATIC1111's Stable Diffusion web UI, allows the Web UI to add ControlNet to the original Stable Diffusion model to generate images. The addition is on-the-fly, the merging is not required.

ControlNet is a neural network structure to control diffusion models by adding extra conditions.

Thanks & Inspired: kohya-ss/sd-webui-additional-networks

Limits

Dragging large file on the Web UI may freeze the entire page. It is better to use the upload file option instead.
Just like WebUI's hijack, we used some interpolate to accept arbitrary size configure (see scripts/cldm.py)
Processor thresholds are set in scripts/processor.py. Change it if needed.
Transfer control is disabled by default currently. This option is experimental and may change in the future.

Install

Some users may need to install the cv2 library before using it: pip install opencv-python

Install prettytable if you want to use img2seg preprocessor: pip install prettytable

Open "Extensions" tab.
Open "Install from URL" tab in the tab.
Enter URL of this repo to "URL for extension's git repository".
Press "Install" button.
Reload/Restart Web UI.

Usage

Put the ControlNet models (.pt, .pth, .ckpt or .safetensors) inside the sd-webui-controlnet/models folder.
Open "txt2img" or "img2img" tab, write your prompts.
Press "Refresh models" and select the model you want to use. (If nothing appears, try reload/restart the webui)
Upload your image and select preprocessor, done.

Currently it supports both full models and trimmed models. Use extract_controlnet.py to extract controlnet from original .pth file.

Pretrained Models: https://huggingface.co/lllyasviel/ControlNet/tree/main/models