Today we are introducing Stable Diffusion 3.5. This open release includes multiple model variants, including Stable Diffusion 3.5 Large and Stable Diffusion 3.5 Large Turbo.
    • Scrubbles@poptalk.scrubbles.techEnglish
      10·
      14 days ago

      Yeah whenever they release one it’s more like, great, so about 8 months until the actual good models start coming out from all of the new merges and checkpoints

  • Domi@lemmy.secnd.meEnglish
    3·
    13 days ago

    I like how their first image is a woman laying in the grass after their SD3 fiasco.

    Did anyone try it? How does it compare to Flux?

    • Even_Adder@lemmy.dbzer0.comOPEnglish
      2·
      13 days ago

      I haven’t tried it, but the outputs are pretty oversaturated, but don’t look that bad. It also should be more easily trainable than Flux, since they released models that weren’t distilled. You can see what people have uploaded to Civitai so far if you filter by SD 3.5.

    • ReallyActuallyFrankenstein@lemmynsfw.comEnglish
      2·
      12 days ago

      I’m barely experimenting with local SD lately due to life commitments, but using some of the free tools online I’ve found it actually has impressive prompt adherence, including relational wording and text in quotes.