This post belongs to a parent (learn more) « hide
Resized to 39% of original (view original)
original generated by antlers_anon using antlersmix_2
Original Commentary AI Metadata

Size: 768x1280,
Model: (anything * 0.95 + sd-1.5 * 0.05) * 0.8 + hassan-1.4 * 0.2,
Denoising strength: 0.6

Prompt sketch drawing of petite cute nude (child:1.2) girl wearing oversized (military jacket:1.3), (pussy:1.2), (nipples:1.2), thigh-highs, detailed face+eyes, parted lips, pussy, falling snow, small breasts, blonde hair, curly hair, aroused, (by Greg Rutkowski:1.2), (by Alphonse Mucha:0.8), (by Ken Sugimori:1.2)
Negative prompt censorship, ugly, old, amateur drawing, odd, fat, lowres, text, error, worst quality, low quality, jpeg artifacts, signature, watermark, username, (blurry:1.3), out of focus, cropped, out of frame, (cloned face:1.3), (mutilated:1.3), (deformed:1.3), (gross proportions:1.3), (disfigured:1.3), (mutated hands:1.3), (poorly drawn hands:1.3), bad anatomy, (bad hands:1.3), missing fingers, extra digit, (extra fingers:1.3), fewer digits, poorly drawn face, (poorly drawn feet:1.3), (fused fingers:1.4), long neck, extra limbs, broken limb, asymmetrical eyes, black and white, monochrome, adult, large breasts, tall, photography
Sampler DPM++ SDE Karras
Seed 2404193104
Steps 20
Cfg Scale 16
Model Hash 98e5995f
  • Comments
    •
    antlers anon
    [hidden]

    avrix said:

    I'd love to know what hypernet was used with this!

    I'm almost entirely sure I didn't use anything more than the mentioned model. Did you try using it with the prompt? I can try generating it again to see if I didn't mess up while copying the settings. I'll report back once I'm near my pc.

    0 Reply
    kaisu1
    [hidden]

    avrix said:

    Thanks. Yeah, I tried same prompt, same model mix, same seed, I found I wasn't even able to get close to a similar anime style output.

    Can you give me the hash of the models you used? My result hash is different, might be slightly different models

    0 Reply
    avrix
    [hidden]

    @antlers_anon are you sure there's no hypernetwork you've selected in your settings tab, or TI that's being used to generate this image?

    I tried to generate this with your provided mix__2.ckpt with all of the exact same settings (prompt, sampler, CFG scale, seed) and it still results in a fairly realistic non-anime style.

    If nothing else, would you be willing to share your embeddings folder and hypernetworks folder? (just a screenshot would probably do as well?)

    edit: looks like the firstpass width/height was set to 0x0, so it was just straight-up going for 768x1280 for initial resolution. I ended up finding that it gets pretty close, especially if I use kl-f8-anime2.vae instead of novelai/anythingv3 vae.

    I'm guessing that colour correction and some filtering adds a little noise

    Updated by avrix

    0 Reply