Re:The open weight Flux text to image model is next level
by warkdarrior on Thursday August 01, 2024 @04:12PM
(#41133083)
Have those artists given permission for their styles to be slurped up into a model?
Re:The open weight Flux text to image model is next level
by GaggiX on Thursday August 01, 2024 @04:25PM
(#41133230)
Give me a sec, I will contact Edgar Degas with my telegraph.
Re:The open weight Flux text to image model is next level
by vessenes on Thursday August 01, 2024 @07:47PM
(#41134833)
Truly an API call I would pay for
Re:The open weight Flux text to image model is next level
by vessenes on Thursday August 01, 2024 @07:46PM
(#41134832)
Florentine art schools would like a word - they’ve been teaching painters by having them copy masters since the 16th century.
Re:The open weight Flux text to image model is next level
by astrange on Friday August 02, 2024 @04:07AM
(#41136986)
It's "just" another diffusion model, although a very good one. Those people are probably in there even if its text encoder doesn't know about them. So you can find them with textual inversion.
Re:The open weight Flux text to image model is next level
by whywhywhywhy on Friday August 02, 2024 @05:05AM
(#41137217)
>Flux cannot respond to requests asking for paintings in the style of David Hockney, Norman Rockwell
Does it respond to any names? I noticed SD3 removed all names to prevent recreating famous people but as a side effect lost the very powerful ability to infer styles from artist names too.
I’d bet that fine art training would further improve the compositional skills of the model, plus it would open up a range of uses that are (to me at least) a bit more interesting than just illustrations.