Stable Diffusion - non-humans

This is my attempt to document how to generate non-humans with stable diffusions. This is early version and so many thing are incomplete or might be missing outright.

This includes fantasy creatures (like elves, dryads or goblins), mechanical people (robots, dolls), kemonomimi (catgirls...), as well as others (e.g mushroom girls). I mostly cover girls (as these interest me), but I'm open to adding boys and others. Out of scope are furries and possibly some horror-only creatures.

For current listing of currently included girl creatures (more are welcome), see non human girl list. Note that not all might be possible to generate yet.

Resources

• models that work for generating non-humans
• embeds: textual inversions, LORAs, VAEs - extensions for the models

TODO: Guides

• prompting - tips how to find the right words for your prompt
• dynamic prompts - how to generate multiple variations (be it girls or backgrounds) with single prompt
• upscaling - how to make the picture bigger
• making variations of same image
• stable diffusion limitations - what doesn't seem stable diffusion to be able to do yet

TODO: Social networks

Contributing

Any help is welcome. (:

Until I figure out better way you can send me message on discord: denzil#9930

I do have this as git repository, so if you know git hosting that wouldn't have problems with links to NSFW content, let me know.

License

This work is licensed under the Creative Commons Attribution-ShareAlike 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by-sa/4.0/ or send a letter to Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.