A Stable Diffusion desktop frontend with inpainting, img2img and more!
https://user-images.githubusercontent.com/6392321/191858568-0550f52d-e89c-4b37-aa07-23df605b4807.mp4
pip
). The dependencies include :
PyQt5
, numpy
, pytorch
, Pillow
, opencv-python
, requests
, flask
, diffusers
, transformers
, protobuf
, qasync
, httpx
Package versions given in "requirements.txt" may, depending on environment, need to be supplemented by:
Note that if you want to run StableDiffusion on Windows locally, use requirements-localgpu-win64.txt
pip install -r requirements-localgpu-win64.txt
Note: On linux, if you encounter Could not load the Qt platform plugin "xcb"
error, run this:
pip uninstall opencv-python (solve a xcb compatibility issue)
pip install opencv-python-headless (solve a xcb compatibility issue)
Create a huggingface account and an access token, if you haven't done so already. Request access to the StableDiffusion model at CompVis/stable-diffusion-v1-4.
Clone this repository and run python unstablefusion.py
Install the dependencies (see the previous section)
Open this notebook and run it (you need to enter your huggingface token when asked).
When you run the last cell, you will be given a url like this:
copy this URL.
Run python unstablefusion.py
In the runtime section, select server and enter the address you copied in the server field. Like this:
Select Color
button)prompt
text field and press the Generate button
(inpainting and reimagining work similarly)undo
/redo
button or pressing Control+Z
/Control+Shift+Z
on your keyboard. In fact most other functions are bound to keys as well (you can configure them in keys.json
file)Increase Size
/Decrease Size
buttons adjust the size of the image by adding/removing extra space in the margins (and not by scaling, this is useful when you want to add more detail around an image)Show Scratchpad
button. This window is capable of doing everything the main window can (using keyboard shortcuts only). The selected box in scratch pad will be mirrored and scaled into the selected box in the main window.
This is useful when trying to import another generated/local image into the main image.Admittedly, the UI for advanced inpainting is a little unintuitive. Here is how to works:
Save Mask
button. From now on, the current mask and current selected box will be used for inpainting no matter how you change the box/image (until you press Forget Mask
button)Autofill
button, or manually paint the target area or paste any image from scratchpad. Since this initial image will be used to initialize the masked part, it will heavily affect the final result. Therefore by controlling this initial image, you can modify the final result to your will.