CivArchive
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    Introduction:

    Erect Horse Penis LoRA for all humanoid characters. Trained for best compatibility with anime models only. Would work alongside with most character, concept or style LoRAs, except ones, that already have trained penis concept.

    Please, check the description, there is plenty of useful information.

    Flaccid Horse Penis LoRA - Flaccid version of horse penis LoRA

    Recommendations:

    • 1.0 emphasis

    • See relevant tag tips

    Relevant tag tips:

    There is a nice feature in prompting for Stable Diffusion - emphasis. Using this, Large Penis and (Large Penis:1.2) will do different sized penises. Second one can be just bigger than large, or even similar to huge penis. Don't use emphasis value higher than 1.4.

    You can combine tags below as you like to get the result you need.

    Smallest possible penis / testicles - Small, the stallionis maximus - Gigantic


    • Erection | Size Penis for penis state and size

      • Size value can be Small | Large | Huge or Gigantic

      • I do recommend to start from large size

      • You can use two tags at once to achieve bigger result

      • "small" tag is highly unstable due to very small dataset, ironic

    • Size Testicles for testicles size

      • Size value can be Small | Large | Huge or Gigantic

      • I do recommend to start from large size

      • You can use two tags at once to achieve bigger result

      • "small" tag is highly unstable due to very small dataset

    • Sagging Testicles | Resting Testicles for testicles state

      • Sagging for saggy testicles

      • Resting for on-surface state (like breast rest)

    • Cock Sheath for proper penis sheath

    • Flared Tip for flared penis tip shape

      • You can use it in negative like that (flared tip:1.2) to make penis more blunt

    • Thick Penis for penis girth

      • May be unstable, need further improvements

    • Precum, cum, wet, suggestive fluid in your negative prompt for less mess.

    • Navel for penis be less in "pointing up" position, while naked


    • Autopaizuri for penis between breasts (pre-v5)

      • Don't use this tag alongside with Erection

      • Not implemented in version 5 or higher

    • Autofellatio + Oral | Blowjob | Licking Penis for self fellatio (pre-v5)

      • You may use all three fellatio tags for higher change of autofellatio

      • Don't use this tag alongside with Erection

      • Not implemented in version 5 or higher


    • Skin-colored Penis | Testicles for regular skin-toned endowment

    • Dark Penis | Testicles for more dark penis or testicles

    • Color Penis | Testicles for your color

    • Skin-colored / Dark / Color testicles also changes sheath color

      • Sheath color can be changed independently, highly unstable


    Some colors may perform better than others. If you're getting the same color every time, just add it to negative prompt. Never forget about negatives. It would do the trick.

    Google Docs page - older prompt tips (v1 - v3)

    Example penis prompts:

    Use this if you have no idea how to use this LoRA and didn't read prompting tips above.


    For small erect penis:

    • erection, (small penis, small testicles:1.1), cock sheath, dark testicles, pink penis

      • "small" tag is highly unstable due to very small dataset

    For large erect penis:

    • erection, large penis, large testicles, cock sheath, dark testicles, pink penis

    For huge erect penis:

    • erection, huge penis, huge testicles, cock sheath, dark testicles, pink penis

    For gigantic erect penis:

    • erection, gigantic penis, gigantic testicles, cock sheath, dark testicles, pink penis


    If you're ran into any problems with this LoRA, you can always dm me on discord:

    troubledarkness - discord nickaname

    I'll be glad to help | Буду рад помочь.

    Credits:

    Trained on NAI Anime Full.

    Dataset of 150 pictures (v1), 8 epochs, Clip Skip - 1
    Dataset of 224 pictures (v2), 14 epochs, Clip Skip - 2
    Dataset of 160 pictures (v3), 10 epochs, Clip Skip - 2
    Dataset of 300 pictures (v4), 10 epochs, Clip Skip - 2
    Dataset of 600 pictures (v5), 10 epochs, Clip Skip - 2
    Dataset of 700 pictures (v6), 10 epochs, Clip Skip - 2

    Dataset of 1000 pictures (v7), 20 epochs, Clip Skip - 2

    Really big thanks to:

    • Some good folks from Discord server

    • You, for reading, downloading, liking and reviewing this LoRA

    Description

    Dataset now would be separated on two versions, flaccid penis and erect penis. Soon i'll try to do more with Horse Penis states. As i found out, it's almost impossible to do the same level controls over conflicting concepts like flaccid / erect / fully sheathed penises with lack of dataset, so i decided to separate it.

    Erect version is for: Erect Penis, Autopaizuri and Autofellatio concepts.

    Talking about advantages:

    • More accurate horse penises

    • More accurate and versatile dataset

    • More accurate urethra position, appears more often

    • Easier control over penis size, more options

    • Easier control over dataset and further imrpovements for me

    • Better Style LoRA compatibility

    • Less glitches on testicles

    • Less "Latex" effect of sheath and testicles

    • Less random and distorted hands on shafts

    Talking about disadvantages:

    • Affects style a little bit more than v1 or v2, would be improved in future

    • All-in-one LoRA no more

    • Less veins on penises

    FAQ

    Comments (13)

    1331711Jun 7, 2023· 47 reactions
    CivitAI

    that is unbelievably disgusting

    TroubleDarkness
    Author
    Jun 7, 2023· 6 reactions

    That is unbelievably biased.

    d3nt0n451559Jun 20, 2023· 3 reactions

    yet you found yourself on this page...

    connornelson16608Jun 27, 2023

    yet you love it

    AliasVaineJun 15, 2023
    CivitAI

    Im probably stupid or something but how do i use this? Is there a guide or video to use the loras thing? Sorry for bothering really wants to try this loras in particular

    TroubleDarkness
    Author
    Jun 18, 2023· 1 reaction

    Hi, i'm not into CivitAI right now. Was not answering any comments. If you want to use LoRA, place any downaloded LoRA file to SD folder -> models -> LoRA.

    Then, start your Stable Diffusion, go to red book icon under your "Generate" button -> LoRA tab and select your desired downloaded LoRA. It would be placed in your positive prompt box.

    fossJun 16, 2023
    CivitAI

    the amount of dedication to bring this to life is admirable. patrician taste

    daMattJun 21, 2023
    CivitAI

    I assume, this only works with girls? Which is a pitty.

    Wanted to do guys with huge equine schlongs too.

    TroubleDarkness
    Author
    Jun 21, 2023· 1 reaction

    Nope. It works with all humanoid characters. Also, i would update this LoRA soon, so it would work better with male characters. Working on another LoRA right now.

    daMattJun 21, 2023

    @TroubleDarkness Really, because I cant get it to work with non females.

    Do you maybe have a short prompt samplefor me with a male character? That be great.

    TroubleDarkness
    Author
    Jun 21, 2023· 1 reaction

    @daMatt if you'll put something like: "1boy, male, muscular, eqcok, large penis, large testicles, erection", it should work. If it's still doing female characters for some reason, put "female, 1girl, breasts" to negatives. Or you can just wait for newer version. There won't be autofellatio concept, not sure what to do with it right now, but better quality and versatility - of course. And i'm trying to improve color control.

    TroubleDarkness
    Author
    Jun 25, 2023· 1 reaction

    @daMatt Hi, updated to v4, now works great with male characters. Also, implemented few new features and changed prompting. You can read about new prompt tips in LoRA despcription.

    daMattJun 25, 2023

    @TroubleDarkness will test it out, thanks