Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I read that you have to give longer prompts to Stable diffusion.

This is my bison astronaut:

https://i.imgur.com/ohIuG6F.png

The prompt was:

"A bison as an astronaut, tone mapped, shiny, intricate, cinematic lighting, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by terry moore and greg rutkowski and alphonse mucha"



Not sure how you got that from stable diffusion. This is the kind of thing I get - just a bison.

https://i.postimg.cc/bw1R10gB/A-bison-as-an-astronaut-tone-m...


I've found that sometimes you need a lot of attempts to get good results. Here's a run I just did, I'd say the top left result is OK, the bottom 2 are wrong/misinterpretations, and the top right result is fantastic: https://i.imgur.com/l8BsWvI.png


Img2img and inpainting is usually a lot easier to get cool results (with a lot of control on your end) with in my view.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: