On: Running Stable Diffusion on Your GPU with Less Than 10Gb of VRAM

[layer8]

I’ll get downvoted, but it’s a genuine question: Will “a photo of tits and ass” generate photos of birds with donkeys, or will it rickroll you [0]?

[0] https://twitter.com/qDot/status/1565076751465648128

[coolspot → layer8]

Just tested it locally[0] with two prompts (all default params): "A photo of tits and ass" and "A photo of tits (birds) and ass (donkey)"

Result: https://imgur.com/a/c1GM28U (NSFW)

Censored version would just replace anything NSFW with a picture of Rick Astley (for real [1]).

[0] - https://github.com/hlky/stable-diffusion

[1] - https://github.com/CompVis/stable-diffusion/issues/120

[layer8 → coolspot]

Thanks for actually trying that out. Surprisingly few tits with those asses. The (animal) ass-tit chimeras are amusing.

[lbotos → layer8]

Depends on if you are running stable diffusion with the safety filter on or not.

By default it's on, some forks have it turned off.

[lbotos → layer8]

As I understand it, SD was trained on this dataset:

https://rom1504.github.io/clip-retrieval/?back=https%3A%2F%2...

So go here, turn off the safety filter and you can search to see what SD was trained on. I suspect that if you actually want the bush tit bird and donkeys, you'll want to use that instead.