First time playing with an SDXL model. These are made with SDXL Unstable Diffusers ☛ YamerMIX and the ones that are completely human on top use Regional Prompter as well. The prompts were all along the lines of

full body ADDCOMM
a photograph of a beautiful naked woman, beautiful face, breasts ADDROW
a photograph of a female cyborg

with no negative prompt.

  • 3hrtd@lemmynsfw.comEnglish
    1·
    10 months ago

    Prompts seem much simpler compared to what I imagine it’d take standard SD to come up with images like this. Would you say SDXL is much easier to use/get the results you want compared to standard SD?

    • chellebelle@lemmynsfw.comOPMEnglish
      1·
      10 months ago

      I’d heard it was harder, but that may be with the base model. It’s certainly been much easier so far when using SDXL Unstable Diffusers ☛ YamerMIX ! It doesn’t work with tools like ControlNet, though, so it’s limited to prompting and img2img. It might work for some limited use cases in Deforum that don’t require ControlNet, like zooming with high strength. It’s hard to get good videos in Deforum without zooming, though. (I’m trying to make videos with Deforum now.)