Comments

Blacklisted
    Show Search Options
    post #1522
    21 33 2 Q
    post #2312
    34 44 1 E
    1 5 5 S
    post #2279
    30 63 1 E
    post #2294
    31 51 1 E
    post #639
    75 130 4 E

    furrai said:
    It's actually two images. As far as I know, there's no way to specify multiple character trainings with AI. Each character was rendered separately, combined into one image, and run through image-to-image with a low strength to make the style match better. The text was added by hand.

    Ayo that's actually a genius idea :o

  • |
  • 0
  • post #2195
    40 93 1 E
    post #2175
    95 165 1 E
    2 1 1 E
    post #3
    130 126 49 S
    25 42 1 Q
    82 145 1 Q
    post #1944
    90 120 1 E
    post #1980
    19 38 1 E
    post #1928
    16 33 1 Q
    post #1948
    10 23 2 Q
    post #1948
    10 23 2 Q
    post #1752
    21 47 1 E
    post #1521
    13 11 1 Q
    post #1574
    9 19 1 Q
    post #1534
    15 35 1 Q
    post #1738
    13 31 1 E
    post #1715
    26 41 1 E
    post #186
    28 57 1 E
    post #1683
    38 95 2 E

    Wait. Is that... text that's not only discernable, not only pronounceable, not only cleanly-written, but MAKES SENSE IN CONTEXT? Wow. One in a million.

    Updated

  • |
  • 6
  • post #44
    15 7 1 S
    post #69
    62 91 3 E
    post #1375
    21 22 1 S
    post #861
    8 22 1 E
    post #917
    6 16 1 E
    post #1012
    2 8 1 E
    post #1182
    24 27 1 S
    post #1195
    13 26 1 E
    post #1465
    18 18 1 Q
    post #1444
    46 71 1 E
    post #1443
    23 29 2 E
    post #10
    56 91 3 E
    post #10
    56 91 3 E
    post #10
    56 91 3 E
    post #1196
    24 66 2 E

    tkyoprko said:
    omg how did you make such an amazing puffy anus. please give me your wisdom ;-;

    I'll give you one better!

    Pos: (by hioshiru and kenket and chunie), e621, explict, (solo), anthro dog, headset, (pink hair), (blue nipples), balls, (presenting hindquarters:1.2), (presenting anus:1.2), (((gaping)) (puffy) (huge) anus:1.3), ((donut anus)), glow, (moon night), dark, (city alley dumpster), (lights), street glow, mist, fog, pinup, detailed, realistic painting, impasto impressionism, (frank frazetta), looking back, long wavy hair worn up, latex socks, latex sleeves,

    Neg: deformed, blurry, bad anatomy, disfigured, poorly drawn, mutation, mutated, ugly, (((out of focus))), depth of field, focal blur, (text), (watermark), (signature), extra body parts, feral,

    Ye18, 40-60 samples, CFG 11 512x640, enjoy ❤

  • |
  • 2
  • post #1254
    8 2 1 E

    I don't know if there shouldn't be an unusual_anatomy tag, but I directly tried to get it kinda weird by making it a seamless tile-able image

  • |
  • 0
  • post #1196
    24 66 2 E
    post #1217
    19 38 1 E
    post #1198
    70 120 1 Q
    post #639
    75 130 4 E

    kemowolf said:
    How is this AI?!

    It's actually two images. As far as I know, there's no way to specify multiple character trainings with AI. Each character was rendered separately, combined into one image, and run through image-to-image with a low strength to make the style match better. The text was added by hand.

  • |
  • 4
  • post #1008
    147 228 2 E
    post #639
    75 130 4 E
    post #957
    1 3 1 Q

    If you don't have dedicated graphics card, I suggest you to use Google Colab environment. You can even choose to use NovelAI (easier to use, less customizable) or Stable Diffusion (harder, but you can customize everything)

  • |
  • 2
  • post #922
    41 64 2 E
    post #940
    10 6 1 S
    post #806
    8 9 2 S
    post #922
    41 64 2 E
    post #389
    9 4 1 E
    post #806
    8 9 2 S

    Those are some... very specific negative prompts. Good thing you added them too, because nobody needs to see that!

  • |
  • 1
  • post #787
    3 13 3 E

    gotadraw said:
    Yeah, they do haha. I don't edit any of these pictures once I generate them, I just keep them in raw form.

    if you're generating these with the Automatic1111 UI, the head is an easy fix - do inpainting on it with the "Inpaint at full resolution" box fixed, source original with maybe 8px mask blur. Drop the noise a bit, maybe to 0.5, run Euler a at maybe 30 or 40 iterations. That should clean it up; use the batch size option to select from the best alternative.

  • |
  • 0
  • post #796
    68 86 1 E
    post #787
    3 13 3 E

    kyiiel said:
    The eyes and hands need work.

    Yeah, they do haha. I don't edit any of these pictures once I generate them, I just keep them in raw form.

  • |
  • 0
  • post #787
    3 13 3 E
    post #731
    42 72 1 E
    post #701
    29 25 1 E
    post #639
    75 130 4 E
    post #644
    92 154 2 E
    10 18 1 S
    post #370
    1 5 1 E

    Is rope_bondage supposed to look like a noose? lol (I also regret looking up the e621 wiki page for a noose, the pictures were less playful than I expected. Dead dove meme... Almost literally.)

  • |
  • 0
  • post #243
    1 7 2 S
    post #61
    8 13 1 S
    post #74
    61 122 1 E
    post #239
    4 9 2 S

    lance_armstrong said:
    A lot of the AI images uploaded so far seem to have a very high contrast between dark and bright areas. Not necessarily from you, Gem.

    Also, shouldn't it be possible to get rid of all attempted signatures with a little inpainting?

    Very contrast heavy and yes, with inpainting or smudging in photoshop/similar

  • |
  • 1
  • post #239
    4 9 2 S

    A lot of the AI images uploaded so far seem to have a very high contrast between dark and bright areas. Not necessarily from you, Gem.

    Also, shouldn't it be possible to get rid of all attempted signatures with a little inpainting?

  • |
  • 1
  • post #243
    1 7 2 S
    post #184
    12 14 2 S
    post #184
    12 14 2 S
    post #3
    130 126 49 S
    post #12
    9 8 1 S
    post #3
    130 126 49 S