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.worldEnglish
    2·
    11 months 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.