Flux:I often use 3D character training and generation to evaluate the performance of models. Through this Flux model, I found that the performance of <a target="_blank" rel="ugc" href="http://Flux.Dev">Flux.Dev</a> in this evaluation still lags significantly behind Dalle-3 from two years ago. The biggest issue is the inability to reproduce complex body language.---Anna and elsa have the same training intensity, what can I say, anna is just shy, you just need to repeat the call in the prompt, something like "anna, anna,(anna:1.4)," also works for the other arousal words.We have to admit that for SD1.5, the only way to get some kind of complex effect is to train or use a lot of time to tweak the prompt, and we're really looking forward to a version of stable diffusion with comprehension similar to Dalle3.

Frozen anna elsa -Dall-E 3

Did I mention this was just a random experiment?I grabbed some images on DALL·E 3, and these images clearly show Elsa’s features, which made me very satisfied. So I trained this part of the material together with Elsa’s image in the movie.

Files with SHA256: fc0136f1099754ada09cc550b653fdb647283ece71c2e4ce01a0b853b39d34c5