Comment on 1.58-bit FLUX
kwilson@lemmy.world 4 weeks ago
I’m not an expert on AI, but I’m surprised the comparison photos are so similiar. I was expecting the models to come with completely different images each time. The sky in the dragon pics specially looks like copied and pasted.
Even_Adder@lemmy.dbzer0.com 4 weeks ago
The hope is that they’re similar. The pictures on the right are from a smaller version of the model that the pictures on the left are from. This shows that even though they shrank the model, it still understands the same prompt.
kwilson@lemmy.world 4 weeks ago
yeah I get that, I’m just surprised that both times the image is so similar. both times the dragon looks right, both time the sky looks mostly the same, stuff that isn’t part of the prompt you know.
The same prompt can sometimes give you completely different pictures, that still comply with the prompt, on the same model
felsiq@lemmy.zip 4 weeks ago
The text is only part of the initial info the model uses to create the image - the settings and the random number seed are other parts that are relevant here because they’d be the same for both images. The seed in particular is why these images look so similar - normally when you give the same prompt twice, the seed is randomized so the model starts from two different points. Here, each model starts from the same point and works the same way, just with different amounts of data, so a lot of the details are shared.
kwilson@lemmy.world 4 weeks ago
yeah I get that, I’m just surprised that both times the image is so similar. both times the dragon looks right, both time the sky looks mostly the same, stuff that isn’t part of the prompt you know.
The same prompt can sometimes give you completely different pictures, that still comply with the prompt, on the same model