FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

Post by vessenes » Thu, Oct 03, 2024, 8:01 PM UTC

whywhywhywhy wrote: post #64

vessenes wrote: post #28

Flux is so frustrating to me. Really good prompt adherence, strong ability to keep track of multiple parts of a scene, it's technically very impressive. However it seems to have had no training on art-art. I can't get it to generate even something that looks like Degas, for instance. And, I can't even fine tune a painterly art style of any sort into Flux dev. I get that there was working, living artist backlash at SD…

>However it seems to have had no training on art-art. I can't get it to generate even something that looks like Degas, for instance It feels like they just removed names from the datasets to make it worse at recreating famous people and artists.

Post by vessenes » Thu, Oct 03, 2024, 8:03 PM UTC

throwup238 wrote: post #37

vessenes wrote: post #28

Flux is so frustrating to me. Really good prompt adherence, strong ability to keep track of multiple parts of a scene, it's technically very impressive. However it seems to have had no training on art-art. I can't get it to generate even something that looks like Degas, for instance. And, I can't even fine tune a painterly art style of any sort into Flux dev. I get that there was working, living artist backlash at SD…

I’ve had the same problem with photography styles, even though the photographer I’m going for is Prokudin-Gorskii who used emulsion plates in the 1910s and the entire Library of Congress collection is in the public domain. I’m curious how they even managed to remove them from the training data since the entire LoC is such an easy dataset to access.

Post by dagaci » Thu, Oct 03, 2024, 8:18 PM UTC

vessenes wrote: post #82

skort wrote: post #75

Earlier quoted context omitted.

>but, it's a real loss. Both in terms of human knowledge of, say composition, emotion, and so on, but also for style diversity But that real art still exists, and can still be found, so what exactly is the loss here?

We may differ on our take about the usefulness of diffusion models, but I'd say it's a loss in that many of the visuals humans will see in the next ten years are going to be generated by these models, and I for one wish they weren't just trained on weeb shit.

Post by davidbarker » Thu, Oct 03, 2024, 8:43 PM UTC

vessenes wrote: post #80

crystal_revenge wrote: post #49

Earlier quoted context omitted.

I've had a similar experience, incredible at generating a very specific style of image, but not great at generating anything with a specific style. I suspect we'll see the answer to this is LoRAs. Two examples that stick out are: - Flux Tarot v1 [0] - Flux Amateur Photography [1] Both of these do a great job of combining all the benefits of Flux with custom styles that seem to work quite well. [0] https://huggingface…

I like those, and there's an electroshock lora that's just awesome out there. That said, Tarot and others like it are "illustrator" type styles with extra juice. I have not successfully trained a LoRa for any painting style, Flux does not seem to know about painting.

Post by vessenes » Thu, Oct 03, 2024, 8:44 PM UTC

dagaci wrote: post #85

vessenes wrote: post #82

Earlier quoted context omitted.

We may differ on our take about the usefulness of diffusion models, but I'd say it's a loss in that many of the visuals humans will see in the next ten years are going to be generated by these models, and I for one wish they weren't just trained on weeb shit.

Just think that before 1995 (and in reality, decades later than that) most of the world would never have access to 99% of the worlds art. And between 1995 and 2022 the amount of Art produced surpasses the cumulative output of all other periods of human history.