Comments

Blacklisted
    Show Search Options
    post #99957
    224 400 4 E

    Red's got a cum flood stored up haha.
    Moderation of upload standards is really hot or miss here. There are some with glaring issues that get approved and others that look perfectly fine that get deleted.

  • |
  • 2
  • post #100015
    10 19 7 E
    post #99962
    139 240 3 E
    post #99620
    122 194 1 E
    post #99987
    106 181 3 E
    post #99989
    171 218 2 E
    post #100005
    141 197 1 S
    post #100009
    273 443 3 E

    blockedperfection said:
    Where can I sign up to be held like that 😶‍🌫️

    Probably with a gymnast because that requires some impressive upper body strength and balance.
    Having a face full of pussy might serve as a power-boost though haha.

  • |
  • 6
  • post #98123
    128 240 4 E

    dixonuranus said:
    I'd love to hear her gargling and gagging

    Just thinking here with that big nose, the long snout..
    Having a little human penor in her mouth likely
    wouldn't interfere with her breathing.
    And she's not sloppy about it.

  • |
  • 0
  • post #99957
    224 400 4 E

    idk why these didn't meet the standarts before. almost ever submission got flagged and i couldn't figure out why

  • |
  • 1
  • post #83961
    94 114 6 S
    post #99493
    361 594 7 E
    post #99954
    34 25 7 S
    post #64226
    89 100 4 S

    Uncanny valley effect here for me. I feel as if these eyes try to stare into my soul and note everything as meticulously as an artificial drone can. ¯\_(ツ)_/¯ Lol.

  • |
  • 0
  • post #100000
    54 38 11 Q

    Congrats on the- wait a minute!...
    This isn't legimately man-made 100 000th post. :/

    Oh well, anyway, it was wholesome to see the journey of improvement in generating the AI stuff for you! :)

  • |
  • 2
  • post #100009
    273 443 3 E
    post #100000
    54 38 11 Q

    technical-grid said:
    Very cool composition!
    I'm eager to see such pieces be made for 250k, 500k, 750k and 1m as well :)
    Also lol at the hidden comments 😂, you can tell a warzone took place here hahaha

    Where? Are they already deleted by the staff?

  • |
  • 1
  • post #92104
    84 78 3 S
    post #99987
    106 181 3 E
    post #11647
    13 5 2 S
    post #100000
    54 38 11 Q

    Very cool composition!
    I'm eager to see such pieces be made for 250k, 500k, 750k and 1m as well :)
    Also lol at the hidden comments 😂, you can tell a warzone took place here hahaha

  • |
  • 4
  • post #88372
    154 220 3 E

    beepbep said:
    They definitely see us, and they definitely don't give a fuck.

    Well... technically they give a fuck, but between themselves.

  • |
  • 0
  • post #99990
    157 316 1 E
    24 26 1 E

    this director's feral stuff is some of my favorite. the chastity makes it even better too

  • |
  • 1
  • post #99834
    103 106 5 E

    weeml said:
    The prop 65 warning 😭

    Which is crazy seeing how the purpose of the CUBE is meant to replace reproductive actions.

    I'd still use it though...

  • |
  • 2
  • post #99857
    229 380 13 Q
    post #99966
    31 39 3 E
    post #95480
    223 348 3 E
    post #100006
    248 405 3 E
    post #100006
    248 405 3 E
    post #100004
    257 454 2 E
    post #100006
    248 405 3 E
    post #100004
    257 454 2 E
    post #98493
    174 324 9 E

    furryranch said:
    It's pretty easy actually once you get the hang of it. What to prompt for, etc. But like i said, to get EXACTLY what you want is near impossible without a specific LORA. LORAs require thousands of pictures to train off of. Not hard to get when you have a character like, say, Kat. If it's your own bespoke creation though? You have to either hand draw it thousand of times, or use AI, then edit the pictures to a "close enough" approximation, then use those to train your model.

    Nearly spot on!
    For most of the published pages 70% of the consistency came from prompting the right characteristics maybe 5-10% from some rough lora that I made for Tom and Jack and maybe 10% from manual drawing/sketching + inpaint (for exemple I have to "re-draw" Jack horns on almost every panel cause the model I used did not like this kind of curled/ram horns so I had to "guide it")
    Then there is always 10-15% of inconsistancies that I have to consider acceptable (otherwise the time I'd spend in editing would make my progress prohibitively slow)

    Right now I'm training some lora for illustrious (for the next chapter), the first draft for Tom and Jack is rather encouraging (I used ~50 cleaned up images for each).
    I hope to improve it a bit with the second batch (better images + better compatibility with other lora + smaller size) and then do the other characters 🤞
    If I succeed, this should increase the quality and consistency tremendously.

  • |
  • 3
  • post #99857
    229 380 13 Q
    post #99864
    70 120 1 E
    post #99746
    345 611 5 E
    post #99934
    89 162 3 E
    113 164 2 E
    post #99913
    199 352 5 E

    nagiman90 said:
    I'd rather grab those horns, perfect grips for some of the roughest fun around in either direction.

    throat tango

  • |
  • 1
  • post #99731
    195 302 1 E
    post #99962
    139 240 3 E
    post #91280
    178 255 1 E
    post #100000
    54 38 11 Q
    post #100000
    54 38 11 Q
    post #98533
    63 101 3 E
    post #99907
    151 252 2 E
    post #99954
    34 25 7 S
    post #99903
    99 120 4 S
    post #99950
    17 23 5 S
    post #99957
    224 400 4 E
    post #99644
    89 130 8 E

    Super realistic! What model did you use to create it? And is it possible to give us the prompt?

  • |
  • 0
  • post #92363
    260 461 2 E
    post #99923
    224 376 1 E
    post #99966
    31 39 3 E
    post #93772
    192 336 5 E
    post #99954
    34 25 7 S
    post #98771
    172 346 2 E
    99 161 1 E
    post #98533
    63 101 3 E
    post #99955
    316 601 2 E
    post #99954
    34 25 7 S
    post #98493
    174 324 9 E

    xxxmistercoolxxx said:
    I don't know anything about AI, but from what you wrote, it must be pretty difficult to use.

    It's pretty easy actually once you get the hang of it. What to prompt for, etc. But like i said, to get EXACTLY what you want is near impossible without a specific LORA. LORAs require thousands of pictures to train off of. Not hard to get when you have a character like, say, Kat. If it's your own bespoke creation though? You have to either hand draw it thousand of times, or use AI, then edit the pictures to a "close enough" approximation, then use those to train your model.

  • |
  • 2
  • post #99903
    99 120 4 S
    post #30422
    35 51 1 E
    post #99954
    34 25 7 S
    post #99954
    34 25 7 S
    post #99952
    50 68 1 S
    post #99521
    201 310 3 E
    post #99818
    90 134 2 E

    n_n said:
    Damn she cute

    Thank you. I wasn't sure whether I shall keep her "hair". In the end I thought she looks cuter that way xD

  • |
  • 1
  • post #99942
    65 103 4 E
    post #99862
    28 20 1 S
    post #99937
    91 149 2 Q
    post #99942
    65 103 4 E
    post #99521
    201 310 3 E