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

I've been pretty underwhelmed by stable diffusion so far (admittedly even this much would have seemed like magic to me 10 years ago).

First thing I asked it for was a picture of a dragon. I've subsequently a few different models and all sorts of prompt engineering (but perhaps I still haven't found the right one?)... I cannot get it to draw something anatomically coherent.

Are there some tricks I am missing? Do I need to run it through a pipeline of further steps to refine the mangled creature into something that makes sense?



go try Midjourney on Discord, I'm sure it can "draw" you a dragon just fine ;)


I have done exactly that... the results were basically the same as I get from DiffusionBee app for stable diffusion

i.e. regions of the image are locally impressive, it has understood the prompt well, but the overall picture is incoherent... the head or one or more legs may be missing, or legs or wings sprout from odd places

like, it gets the 'texture' spot on but the 'structure' is off


So I was wondering if it needs a more complicated procedure? Lateral thinking?

Should I be asking it for a picture of a cat in the style and setting I want and then use image-to-image to replace the cat with a dragon?




Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

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

Search: