On the Description box of the image generator there is a little i which says "Add brackets around text (like this) or ((even more)) to get the AI to pay more attention to it". Is this limited to 2 sets of brackets or does it continue, that having (((something))) makes the AI pay even more attention and then 4 sets even more and so on?

all 10 comments

sorted by: hot top controversial new old
[–] [S] 2 points 1 year ago (6 children)

Wait, are you saying everything here https://perchance.org/tutorial is not used anymore?

  • source
  • hideshow 6 child comments
  • [–] 1 point 1 year ago (5 children)

    That was written for Stable Diffusion. The new generator is Flux.1-Schnell based.

  • source
  • parent
  • hideshow 5 child comments
  • [–] 0 points 1 year ago* (3 children)

    WE NOW USE FLUX? When did that happen?

    Hm, it says SD.

  • source
  • parent
  • hideshow 3 child comments
  • [–] [S] 1 point 1 year ago

    Oh, so the brackets, including one or two, do nothing. Right, got you, thanks.

  • source
  • [–] 1 point 1 year ago

    I believe it's kinda outdated. The new model prefers full sentences with details, rather than a word with brackets.

  • source
  • [–] 0 points 1 year ago*

    FLUX.1 uses natural language. Write full sentences as if describing the image to a human artist. Avoid tag-style keywords, brackets, or weight syntax like (tag:1.3). Avoid Stable Diffusion-style prompt features such as ((tag)), (tag:1.3), BREAK, AND, or OR. These are not supported and will be ignored by FLUX.1.

  • source