Comments

Blacklisted
    Show Search Options
    post #11703
    81 141 5 Q

    furthief said:
    Very delicious looking Kurama.

    Also, unrelated, is your name from what Ray from Achievement Hunter used in WWE?

    Thank you!

    And ding ding ding! You were the first one to call that out! I'm glad someone finally caught the reference lmao.

  • |
  • -1
  • post #13380
    57 100 4 E

    I love this style! If you don't mind me asking what is the prompt that you used for this post? Keep up the great work!

    Updated

  • |
  • 1
  • post #15754
    115 204 1 E
    post #15757
    72 118 1 E
    post #15768
    96 167 3 E

    I think I'm drooling at this sight...:) -sic!-
    A charming blush of embarrassment on the face is always welcome!

    More images generated by the img2img method?

  • |
  • 0
  • 201 331 3 E

    Holy Mother of Hoofs! It's wonderful, this look, these details.

    Will you share the prompt data and settings used, or is it a company secret?

  • |
  • 4
  • post #15390
    59 117 1 E
    post #15724
    53 95 1 E
    post #15725
    68 96 1 E
    post #15721
    49 85 1 E
    post #15783
    58 68 2 Q
    post #15783
    58 68 2 Q
    post #15774
    54 95 1 E
    post #15673
    84 152 2 E
    post #15753
    77 132 1 E
    post #15760
    26 51 3 E
    post #15760
    26 51 3 E
    post #15711
    147 231 2 E

    I have really liked the whole set of your latest images featuring the dane wearing a leather outfit, but I love the detail of her collar with a "bad bitch" pendant! It is so appropriate!
    I always appreciate when behind an image there is a peculiar idea, a unique fantasy which gives the possibility of a whole scenario telling some sort of story.
    I think you are doing great and I hope you'll like to explore more of the niche of clothed feral.
    For my own taste, I love whenever a female feral seems to be dominant and leading the intercourse despite being penetrated by the human male; it is just so hot.
    Thanks for sharing with us.

  • |
  • 5
  • post #15759
    63 115 2 E

    It is unusual for me but I am really enjoying your images of crossdressing feral.
    Very interesting and sexy.
    Please carry on and thanks for sharing with us.

  • |
  • 4
  • post #15717
    118 192 2 E
    post #15402
    158 313 1 E
    post #15405
    97 167 1 E
    169 330 1 E
    post #15381
    88 147 4 E
    post #15245
    192 393 1 E
    post #15717
    118 192 2 E
    post #15662
    22 39 1 E
    post #15388
    68 128 2 E
    post #11202
    164 304 3 E
    post #15535
    127 204 6 E

    parszuki said:
    I visit this server too:) I even post stuff sometimes. I think I found you, you use the same nickname as here.

    I'm a bit more active there since I've been posting there prior to making an e6ai account, but some of my improved generations have never been posted on the discord - like most of those that are already uploaded here. Discord only had the old crude versions of those gens.

    Updated

  • |
  • 0
  • post #14574
    125 241 5 E

    cronan55 said:
    This is great work, I'm also curious. I can see the prompt, but I'm a total noob at deciphering it. What model is this? is it local?

    Easyfluff is the model I used for this, Stable Diffusion. I trained a lora on mawshots for images like there. I can drop a link here if someone wants the LORA.

  • |
  • 0
  • post #15652
    125 227 2 E
    post #15362
    19 30 1 E
    post #15579
    53 103 3 E
    post #15604
    38 74 3 E
    post #15670
    150 287 1 E
    post #15650
    14 27 2 E
    post #15535
    127 204 6 E

    lungfish1223 said:
    I've only been posting my work on the Furry Diffusion discord before e6ai. In the future I'll likely try to stay on top of regular posting in both places, but the upload limit looks like it's going to be challenging to keep ahead of.

    I visit this server too:) I even post stuff sometimes. (cześć ziomek)

    Updated

  • |
  • 0
  • post #15651
    9 9 3 E
    post #15535
    127 204 6 E

    parszuki said:
    Since you can't share text prompts, the only solution is to keep track of your work. Do you publish elsewhere?

    I've only been posting my work on the Furry Diffusion discord before e6ai. In the future I'll likely try to stay on top of regular posting in both places, but the upload limit looks like it's going to be challenging to keep ahead of.

  • |
  • 0
  • post #15535
    127 204 6 E

    lungfish1223 said:
    All my generations are based off a very similar base prompt with slight modifications
    (blah, blah, full content of the message above:)
    but I have zero experience in LORA training, so it's unfortunately out of my capabilities.

    I'm a beginner and currently I only understand txt2img (additionally, it is not generated locally, on the computer:( - only via the website civitai.com)
    I've seen supporting loras like:
    https://civitai.com/models/107913/or-orprocapra-picticaudata-or-tibetan-gazelle
    https://civitai.com/models/106636?modelVersionId=114528
    https://civitai.com/models/106697/or-or-or-equus-kiang
    they are great when it comes to the realism of the animal, but they are average when it comes to "anatomical details that are particularly interesting to us":)
    Since you can't share text prompts, the only solution is to keep track of your work. Do you publish elsewhere?

  • |
  • 0
  • post #15617
    114 171 3 E
    post #15535
    127 204 6 E

    parszuki said:
    Do I see correctly that most of them were created on the same prompt with minor modifications? You went straight to my heart with this series - the biggest beauties with hooves - including the underrated blackbuck. You could try variations of other species, such as kudu, oryx, sambar, or reindeer.
    Will you share the prompt data and settings used, or is it a company secret? :-)

    All my generations are based off a very similar base prompt with slight modifications made on the spot to account for how well the model handles a particular species, yeah. The ones here are using a slightly outdated prompt - nowadays I also started including LORAs and negative embeddings. As for other species - I have several dozen still in the backlog to upload (including an Oryx and a Reindeer) but I gotta wait until the 10 I posted are approved before I can upload more.

    As for the settings - the model is EasyFluffV10.1, the sampler is DDIM, 30 sampling steps (nowadays, the ones here might have still used 45 - it doesn't seem to cause any difference in quality) - but the most important aspect is that they're all img2img from photo references at 0.4 denoise. Many of my generations, including the blackbuck and bison I already uploaded, would not have worked at all via pure txt2img - I tried, there were no results that even remotely looked like the animal in question. The more common species (from the ones I posted this applies to deer and the gazelle, but it also has been the case with most carnivores) do give decent results via txt2img, but the proportions or anatomy usually come out wrong, so I stick to img2img.

    I am assuming that it'd be possible to generate enough art from img2img to train a LORA that'd allow for these species to be properly generated via txt2img, but I have zero experience in LORA training, so it's unfortunately out of my capabilities.

  • |
  • 1
  • post #3
    127 122 47 S
    post #15617
    114 171 3 E
    post #15579
    53 103 3 E
    post #15535
    127 204 6 E

    Do I see correctly that most of them were created on the same prompt with minor modifications? You went straight to my heart with this series - the biggest beauties with hooves - including the underrated blackbuck. You could try variations of other species, such as kudu, oryx, sambar, or reindeer.
    Will you share the prompt data and settings used, or is it a company secret? :-)

  • |
  • 0
  • post #15513
    28 33 1 E

    wow realy cute.
    what model and lora did you used for this pic.
    i am a huge fan of ash i tryed to make my own lora of ash but sadly it did not work well.

  • |
  • 1
  • post #7067
    58 112 1 E
    post #15309
    44 82 2 E
    post #15309
    44 82 2 E
    post #12636
    118 250 2 E
    0 1 1 S
    post #15008
    13 18 7 E
    post #15420
    67 97 2 E
    post #15563
    163 320 1 E
    post #15435
    44 80 2 E
    post #12453
    68 122 3 E
    post #15530
    40 69 2 E
    post #12119
    448 795 3 E

    Overall terraraptor's creations are just chef's kiss, such degeneracy, but I'm loving it. Especially feral big cats, second kobolds/dragons.

  • |
  • 1
  • post #15479
    45 96 1 E
    post #15439
    57 91 1 E
    post #15384
    36 75 1 E
    post #15471
    34 106 1 E
    10 13 1 E
    post #15448
    81 111 1 E
    post #15478
    35 36 1 S

    Yeah, platypi dont have visible ears, I wonder what plati ears would look like if they did.

  • |
  • 1
  • post #15285
    96 109 8 E

    joker the pokemon salesmen. *slaps her belly* this baby can fit so much inside! *slaps her belly* she is so fast you cant even see her tackle! *slaps her belly* her charm skill is off the chart! *slaps her belly* Are you entertained?! if not her entertainment skill will surely be helpful !

  • |
  • 2
  • post #15438
    5 22 2 E

    heartlessdragon said:
    Literally... "Fuck the world" big dick energy here

    Haha in a way, yes ;)

    In any case it wasn't easy to do, the current models aren't made for it and it was done without using img2img or controlnet, I love challenges :p

  • |
  • 0
  • post #15438
    5 22 2 E
    65 88 4 E
    post #15331
    40 92 1 E
    post #15420
    67 97 2 E
    post #6403
    18 16 3 S

    aecii_3d said:
    Oh hey! Thanks for posting the prompts. I've always wondered how others go about it. Very interesting method you have along with good results to show. How does the renderer know which is which? Do you pre-define who Aiko is? Very curious about your workflow. Reading the lower section of your description im not sure what RP mask is, but i feel that is key information.

    Do some digging into "Regional Prompting" It allowed me to Basically divide my Prompt and Image into Three Sections: Common Prompt Affecting the whole image, Region 1 Prompt: Affecting the Left Side with Aiko, Region 2 Prompt: Affecting the Right Side with Barry.

    Very Powerful tool if your are working with multiple species or just radically different characters. I looked into Regional Prompting to defeat the curse of traits mixing into the whole image and all characters.

  • |
  • 1