AIBooru
This post belongs to a parent (learn more) « hide

This image is unavailable on AIBooru. Go to AIBooru or disable safe mode to view (learn more).

Original Commentary AI Metadata

Used one of my old prompts with a high clip skip (7) as an exploration of clip skip and sampler differences. A high clip skip gives the image fewer "passes" leading to a product that is "less refined." Note that this does not make the image worse. It's just different, and sometimes it will be a difference that you want. Note that the pics on the right all look like sketches and drawings. If that's an effect you are attempting to generate by modifying the prompt, consider doing a quick preview with a clip skip array on an x/y plot instead.

Some of the black and white images have colored eyes and lips because "restore faces" was checked.

Prompt masterpiece, best quality, photorealistic painting of a princess, portrait, low-cut dress, cleavage, large breasts
Negative prompt lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, (((framed))), (((picture frame))), (((gallery)))
Sampler Unknown
Seed 2594444486
Steps 28
Cfg Scale 10
Model Hash 925997e9
  • Comments
    •
    redjoe23
    [hidden]

    Ocean3 said:

    Recently seen some models mention a 'needed' use of different clip skip variables and I wanted to know more about them. Happened to come across this example, thanks 👌

    Glad I could help. If you're going to be working with CLIP a lot, I recommend adding it to your main interface. Go into WebUI settings| User interace| Quicksettings list: Add CLIP_stop_at_last_layers (put a comma between each argument here). Refresh and it'll be up top next to your model selector.

  • 1
  • Reply