CivArchive
    Preview 148983007
    Preview 148985208
    Preview 148989777
    Preview 149058762
    Preview 148983098
    Preview 149056615
    Preview 149059822
    Preview 148988848
    Preview 148983008

    πŸ’‘ YOUR Penis (Retracted) V5 has 3 versions: Flaccid / Erect / Micro.

    This LoRA (V5.2) lets you control foreskin length; erection state; shaft curvature; pubic hair type; scrotal appearance; and skin hair, all in one. It’s designed for retracted penises across Asian, Caucasian, and Latino ethnicities.

    Selected from 50,000 AI curated photos with several custom build programmes and three years of hard work. It’s designed for strong generalisation and natural variety, drawing on editorial poses, lighting, and styles, with front and back views. Each version uses its own consistent trigger words (like scrotum, micropenis for v5.2). Version numbers use R for training steps ratio instead of E for epochs.
    
    Use Moss for beginners, Krea requires delicate language skills like anatomy terms including: frenulum, urethral opening, glans and coronal ridge. Let a censorship free AI to convey your ideas or ref photos plus triggering words into a full sentence style prompt which works like a charm. V5.2 allows you to craft the shape of penis shaft and bend it to any direction.

    Krea2 guardrail actively removes prompt like "penis" "cum" "erect" before generation which means you will likely get a genital free figure, use TextFusion Refusal-Reduction lora will make things easy.

    🍌 Get Free Copies and Get Involved in the Next Lora

    πŸ’β€β™‚οΈ My models have been downloaded nearly 20,000 times. Last year, I found people trading them on other platforms, so I naturally decided to stop sharing them for free. To make this sustainable, I need support from contributors in many ways.

    πŸ’β€β™‚οΈ Share a full video set and get free access to all my loras. African bros are especially welcome! These data will be used with MiniMax H3 video model.

    πŸ™… Random selfies from the internet don’t really work as training data β€” they’re more about vanity than natural anatomy. Proper training data should be shot in natural daylight, framed from below the navel to above the knees. Please DM @huggy on Civitai.

    With 1 particular pubes type, a full set of images from a single person should include total of 160 images (16 states x 2 poses x 5 angles).

    🍌 16 States (4 x 4)

    • Shriveled (Saggy & Tight scrotum) (Pulled Back & Semi Covered foreskin)

    • Natural Flaccid (Saggy & Tight scrotum) (Pulled Back & Semi Covered foreskin)

    • Semi-erect (Saggy & Tight scrotum) (Pulled Back & Semi Covered foreskin)

    • Erect (Saggy & Tight scrotum) (Pulled Back & Semi Covered foreskin)

    🍌 2 Poses & 5 Angles

    • Standing: POV (from above and avoiding feet), floor view (from bottom), front, profile

    • Squatting: POV (from above and avoiding feet), front, profile, floor view (from bottom), back view (from behind)

    🍌 4 Types of Pubic Hair

    • Shaved

    • Trimmed

    • Natural

    • Wet

    🍌 Video (100)

    5 Angles (Top / Bottom / Side / Front / POV Static Camera)

    2-Axis 90-Degree Pan

    10s each

    • 16 States + 2 Poses + 4 Types of Pubic Hair * 2-Axis 90-Degree Pan (22x2)

    • Erection / pull back foreskin (2 Actions x7)

    • 2-Axis swing (2 Actions x7)

    • Handsfree precum streaming, handsfree cumshot (2 Actions x7)

    • Pressed against glass, dry hump (1 Action x7)

    🍌 Regions

    • South African

    • South Asian

    • North Asian

    • North European

    • Pacific Islanders

    🍌 Characters

    • Under 40 years old

    • Slim - Medium build

    • Uncircumcised

    🍌 photograph

    • 1.5m-2m shooting distance

    • No portrait mode, No flash

    • Sharp and raw only

    • Min 1k Res after cropping

    🍌 Submission

    Chuck your files into a zip file, upload it to one of these storage sites, and DM @huggy the link on Civitai:

    • drive.google.com

    • https://mega.io

    • www.dropbox.com


    🍌 Prompt Bleed:

    Prompt bleed is something to be cautious of when writing captions for training data. A classic example is training a lora of a kiwi bird. Using the trigger "kiwi bird" seems natural, but the model's association with "kiwi fruit" is so strong it can totally stuff up the results, creating a bird-fruit hybrid. Switching to a unique trigger like "kiwi_bird" with an underscore solves the problem.

    Another case is using "curtain wall" for a lofi lora, which will often just generate a wall with a curtain. A plain phrase like "a giant window from ceiling to floor" is a much safer bet.

    It shows how hard it is to teach a base model a new concept with a lora without causing confusion, and some models get confused more easily than others. A good process is to test captions as prompts across different models first. If there's already prompt bleed without a lora, it's best to use a synonym. For instance, with the prompt "red lighting," many illustrative models will generate a character with red skin instead of a lighting conditionβ€”an issue that seems unique to the colour red.

    This makes a project like training for a penis a massive challenge. You're dealing with 16 states (4x2x2), so it would be much easier to train each state as an independent lora with its own unique trigger word to avoid bleed. For the penis shaft alone, you've got 'Shriveled' (like after a cold shower), 'natural flaccid,' 'semi-erect,' and 'erect.' Then for the scrotum, it could be 'very saggy' or 'tight,' and the foreskin might be 'pulled back' or 'semi covered.' That’s where the 4x2x2 calculation comes from, giving at least 16 initial states to classify.

    Then, there are also 4 types of pubes (shaved, trimmed, natural, wet) and the 4 major races, which require sub-classes. It would be a total disaster to repeatedly use the word "penis" in the captions. Multiple unique trigger words is likely the only workable solution.


    🍌 Version 4.4 - Multi Orgasms

    🍌 Basic trigger words:

    flacid penis, erected penis, small penis, big penis, huge penis,

    🍌 Style boost prompt:

    bokeh, motion blur, moody atmosphere, dark environment, source_photo, realistic, best quality, masterpiece, highres, professional photography,

    🍌 Negative prompt:

    (extra digits), source_anime, source_pony, logo, watermark, text, worst quality, low quality, poorly drawn, bad anatomy, extra navel, hairy, disproportional, unnatural, mutation, deformed, nail polish, ugly, old, border

    πŸ“’ Issues with V4.3 and V4.2:

    When training an SDXL LoRA for a pony style, the goal was to replicate a specific style/character from the training dataset. However, using Repeats 5, Epochs 40, Network Dim 64, Network Alpha 64 led to overfitting (V4.3), causing glitches when used with high-quality merged base models or other LoRAs. On the other hand, using Repeats 2, Epochs 10, Network Dim 64, Network Alpha 64 resulted in underfitting (V4.2), producing a "half-baked" style that lacked proper detail.

    Unet block weights graph (V4.3E21) with uneven distribution indicates that some layers have much stronger activations than others, which means certain features are being exaggerated. The training process might be amplifying certain layers too much, leading to inconsistent outputs across different settings.

    🍌 Version 4.3 - high fidelity.

    V4.3E21 can generate realistic images with 5 times fidelity than V4.2 theoretically. New tagging method allows better control on penis size, pubes and balls. All LoRAs were trained with PONY based model and should only work with selected PONY based models, ignore the SDXL / illustrious label as I'm testing the compatibility. See below for 54-checkpoint reviews.

    πŸ“’ Checkpoint recommendations:

    🍌 Limitations of SDXL

    • Checkpoint like Duchaiten Pony Real produces images with stunning details which is overwhelming when using additional lora, SDXL unable to effectively allocate sampling steps across different elements.Β 

    • Unlike Flux, in SDXL, full-body generations struggle because the latent U-Net doesn’t allocate enough feature space early in the denoising process.

    • Both Duchaiten Pony Real and Your Penis V4.3 are sharing limited denoising U-Net sampling steps during generation, resulting missing limbs, deformed face and mutated dick.

    • This explains Your Penis V4.3 works flawlessly with PVC Style base model, as PVC material is easy to render.

    • Duchaiten and Penis V4.3 are good on its own, for SDXL the denoising steps aren't being distributed evenly across complex images. This leads to artifacts that are amplified by highres fix. Offline inpainting could work though. Feels like I've hit pony's limit. Time for illustrious and flux.

    πŸ“’ Important instructions:

    • V4.3E21 (5 times fidelity): When working with other Loras (not more than 2), start with a lora weight of 0.5 and a low CFG scale 3.5 (a higher CFG scale results in sharper outputs).Best for inpainting.

    • V4.3E41 (10 times fidelity): This ultra-fidelity version only works as a standalone. The output quality surpassed that of images from flux. Best for inpainting.

    • V4.3E17 and V4.3E11: These are fine-tuned version, which should works with most Pony checkpoints with subtle effect.

    πŸ“’ Two uses of this lora, create real life penis with triggering word "penis", anime style dominated checkpoint requires additional triggering word "realistic" .

    πŸ“’ Enhance realness of a photo, especially on hairs without using triggering word.

    • Use the Lora with epoch below 7 for a stable result, like V03E06, though lora with higher epoch like V03E10 has better resemblances to the training source; (this does not apply to V4 or laterοΌ‰

    • USE fewer triggering word each time for best result;

    • Use CFG between 4.5 (complex scene) to 7.5 (simple);

    • For anime start training steps from a lower value like 19 with Euler a sampler, if you are satisfied with the result, use hi-res fix / face fix (and set Euler to 29) to increase over all quality;

    • For realistic photos, use DPM++2M Karra, 30+ steps for close up portrait, 35+ steps for full body shot.

    • There's no universal prompt / lora weight for every generation. If you're using anime style / character lora with realistic checkpoint, starting with a lower lora weight like 0.7. Ignore the lora weight in sample images, due to a recent bug, image generated online will display lora weight of 1 regardless the actual value.

    • Step number setting (which is the weight for all tags) is closely associated with the complexity of the prompt, if your outcome has extra objects like fingers or limbs, try lower the step value (and the lora weight too); if your outcome has objects disappeared, lack of quality, texture and reality, try raising the step value.

    🍌 Changes in Version 4.3 - high fidelity:

    1) Use tag with underscore.

    2) Trained with "slow baking" technique with proper num repeat and epoch ratio.

    🍌 Changes in Version 4.2 - low fidelity:

    1) New racial ratio: 7Afr | 3Lat | 87Cau | 71Asi

    2) New state ratio: 60Flaccid | 38Erect | 66Semi-erect

    🍌 Changes in Version 4.1:

    1) Some of the source photos from V3 include limbs that needed to be cropped out or removed. They make V3 loose focus on penis, creating distortion and diphallia which never happened on V2.

    2) Remove resources with weird foreskin

    3) Reduce training resource quantity down to ???, as this is a common problem across most of my loras, too many training images reduce the outcome quality, the quality of the resource images is more important.

    4) Increase training resource resolution.

    5) Reduce training steps down to 1000, as I found lower training epochs lora got stable results.

    πŸ“’ Mirroring

    I’ve noticed a few sites, like Modelslab and yodayo, using bots to mirror my models. SeaArt in particular shows big numbers for downloads and generations.

    Description

    imageCount: 387

    steps:20,000

    stepRatio: 52 (under training perhaps?)

    FAQ

    LORA
    Krea 2

    Details

    Downloads
    0
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/14/2026
    Updated
    11/19/2026
    Deleted
    -
    Trigger Words:
    flaccid penis
    erect penis
    semi-erect penis
    big penis
    huge penis
    hung penis
    curved penis
    contracted scrotum
    hanging scrotum
    low-hanging scrotum
    shaved pubes
    sparse pubes
    trimmed pubes

    Files

    YOUR Penis (Erect & Retracted) V5.2R52 Krea2 base.safetensors