What model is used for ai-text-to-image-generator?
Could we self-host it?
https://perchance.org/ai-text-to-image-generatorOpen linkView original on lemmy.worldSyndicated from the fediverse. Read and engage on the original instance.
View original on lemmy.worldhttps://perchance.org/ai-text-to-image-generatorOpen linkView original on lemmy.world
8 replies
Please refer to this post about the model.
Interesting. I asked for a snowy forest, no people, and I ONLY get people. Standing in a snowy forest, yes, but not what I asked for.
try not mentioning people
Yeah, did that first. "snowy forest"...
You need to put the people as a negative prompt. Not sure how to do that in this UI. but it's possible in automatic 1111
Yep, did that too...
more info here: https://lemmy.world/post/9542946
For self hosting, you can look at Automatic1111, it's not the same web-interface though, A1111 is fair bit more complex.