I understand the new model is new. I also understand the intent of progressive AI is to learn from the prompts, and that detailed prompts offer less variables. That being said, the batches generated under "Pro Photo" filter provide little to no variation at all. They all look the same no matter how the prompt is altered.
3 Comments
DDragon@lemmy.world · 2 pts · 1y
I do not like the new model doesn't know celebrity faces also. It knows will Smith but not Jack Nicholson, not anyone like the old model knew every celebrity almost. Please put old model back ðŸ˜
Idhan@lemmy.world · 1 pts · 1y
Try this generator, the styles are much more effective: https://perchance.org/opentext2imagegenerator
ccufcc@lemmy.world · 1 pts · 1y
It will learn from the prompt?