Basically the title. I’m looking for a way to start generating an image, use ControlNet halfway though the generation to detect the pose and stabilize it for the remaining steps. Is there any way to do this? Any help would be appreciated!

  • jasparagus@lemmy.world
    link
    fedilink
    English
    arrow-up
    2
    ·
    edit-2
    1 year ago

    There’s a way to do this in Auto1111 (sort of):

    1. generate an image with part of your steps
    2. Enable openpose
    3. Add the partially generated pixel image
    4. Set controlnet to start at the halfway point, etc.
    5. re-generate the image with the same settings

    This feels pretty janky, though. I think you could do it better (and in one shot) in comfyUI by processing the partially generated latent, feeding that result to a controlnet preprocessor node, then adding the resulting controlnet conditioning plus the original half-finished latent to a new ksampler node. You’d then finish generation (continuing from the original latent) at whatever step you split off.

  • EverythingDonut@lemmy.dbzer0.com
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    Isn’t there a starting step/ending step parameter you can just use on controlnet with Autmatic1111? It uses percentage of the generation so just set the start to .5.

    • Hubi@feddit.deOP
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      Yeah, that’s what I tried first, but it won’t work without an image or pose already loaded into the ControlNet tab.

      • EverythingDonut@lemmy.dbzer0.com
        link
        fedilink
        English
        arrow-up
        2
        ·
        1 year ago

        oooh now I see the conundrum. You are basically trying to find a way to sort of bake openpose into the image generation process… yeah I’m not sure how to do that other than what was suggested below or coding an extension for it.