you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 1 year ago (1 child)

Seems pretty good for fp16, might be quite a bit faster with an fp8 workflow.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 2 points 1 year ago

    Yeah, I’ve discovered if you lower resolution and steps to ~4 you can prototype a prompt on blurry images.

    Once you’ve got something with a good layout 40 steps works better

    I’m a bit disappointed in Qwen image’s prompt processing, it’s good, but it does not have good knowledge and will swap people out if you ask for real people.

  • source
  • parent