new feature: Stable Diffusion image generation

[chrisrude]

@Skrownerve

Sending/receiving images: Oobabooga has extensions for generating images with SD, as well as recognizing images. I would love for our bots to be able to do these things. Even if not able to generate images, being able to search for/send images/GIFS would also be neat. I just don't know how it is done.

I've actually been working on this for a while! The first version of the feature is now committed, and should be included in the next release. I think it's pretty cool.

It even has a fancy UI to let the user regenerate the image until they're happy with it, since SD can be hit-or-miss sometimes. And it's fun for everyone to see all the options that get created.

I want to give it some more bake time and internal testing before cutting a release (plus needing to document it, etc). But if anyone wants a preview, feel free to pull master and give it a shot! Let me know any feedback in this thread.

[chrisrude]

Specifically, it requires the AUTOMATIC1111 UI to be running.

It needs a little more work before I'm happy with it though, specifically it has a hard time on knowing when an image request is being made. I'm planning to play with some zero-shot classifiers to see if one would help, but using one would add to the install footprint.

[Skrownerve]

How does one run the cutting-edge version? I'm trying everything I can think of, but I can't get pip to install anything but 0.1.3 and cloning the project doesn't seem to work either.

EDIT: I got it to work by doing pip uninstall oobabot and then doing pip install https://github.com/chrisrude/oobabot/archive/6deb9f3.zip

This installs the specified commit instead of the PyPi package.

[TruthSearchers]

Still confused a lil bit of how to do it

[chrisrude]

0.1.4 is out! Should be simpler now to install the latest by using:

pip install oobabot --upgrade