6
What is happening with the text to image generator right now? (lemmy.world)
submitted 9 months ago by to c/perchance@lemmy.world
10 comments fedilink hide all child comments
 

What is going on with the image generator right now? Prompts seem to be hit and miss with the AI following only following the main prompt and completely ignoring anything in the negative prompt. It's even messing up with the main prompt. Another thing is that it is generating pictures with a plain white background despite me specifying the environment and surroundings in detail in the main prompt, on top of that the images are no where near as good as they were a few weeks ago and it keeps generating anime or bad cartoon images which I do not want and did not specify in my prompts or art styles. I mainly use oil painting realism or professional photo so seeing the anime and cartoon styles is really frustrating, is this going to be fixed?, is something being updated right now that's causing all this? Is anyone else experiencing the above with the text to image generator?

you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 9 months ago

I am experiencing exactly the same disappointing results. Used to be I could generate really outstandingly different results than on a run-of-the-mill AI generator that made virtually nothing but cartoons, anime and manga. The previous version of perchance allowed for great looking Art Deco, vintage pulp covers, academic and social realism images resembling real artistic results and so on ... something else than cartoon anime. Now it is almost nothing but cartoonish stuff, very unrealistic. I've also read in other comments that Perchance no longer uses Stable Diffusion, though what that exactly means is somewhat beyond me, only that it now gives different results, very very different results. A real shame because up till a few weeks ago (almost a month now I think) Perchance was truly outstanding and different.

  • permalink
  • fedilink
  • source
    •