Please check out my <a target="_blank" rel="ugc" href="https://ko-fi.com/part_loras">Ko-Fi</a> page if you are interested in supporting me.LoRA commissions open! -&gt; <a target="_blank" rel="ugc" href="https://www.fiverr.com/partai/develop-your-custom-lora-or-loha-model-for-stable-diffusion">Fiverr</a><h3>This is a LoHa LoRA! You need the <a target="_blank" rel="ugc" href="https://github.com/KohakuBlueleaf/a1111-sd-webui-locon">extension</a>! Why? They do a lot better with multi-concepts.</h3><h3>Trigger words for V5.9 - From 325 images to 904: v4.14 needs "futanari" in prompt but v5.9 doesn't!</h3>Try Clip Skip 1 and Clip Skip 2!&lt;lora:GirlyPenisv59:0.7&gt;(penis, testicles) You can now specify between "flaccid" OR "erection", "precum", "chastity, testicles" (don't prompt for "penis", "erection", "flaccid"), "bulge" (don't prompt for "penis", "testicles", "erection", "flaccid"), "penis out", "erection under clothes" (don't prompt for "erection","penis"), "foreskin", "tucked penis", "cock ring", "veins, veiny penis", "clothing aside" (can be reinforced with "leotard aside" or "panties aside" for example), "ejaculation, cum, projectile cum", "futanari masturbation", "femboy" (for more masculine face, probably doesn't work tho).Its probably a good idea to complement the LoRA with more specific ones for things that its struggling with like "chastisty"... 70 out of 910 images had chastity in it but its still hard for it to draw that. I will make these specific ones if theres enough interest in it. Most tags for camera angles and a few different sex positions should also work.<h3>Follow the steps in the Model Version notes to reproduce my images.</h3>Sample images generated from CAN or Nothing, check metadata!All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.It was trained on 904 512x512 images scraped from the internet and 9 epochs using animefull_final.Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific tags.

Futanari - LoHa

Generate using a weight of 0.4-0.72 like this: &lt;lora:SmallPenis10:0.4&gt; .If you use more, the model will most likely generate white borders around the image (thats a problem in my Dataset, already working on it. Hopefully next version won't have this problem)Not tested this version, yet. How I archived my generations:<ol><li>txt2img: DPM++ SDE Karras with 20 steps, 512x512(can go up to 768 for wide or tall), Restore faces on (using CodeFormer weight 1.0 in Settings), Hires-fix on, to 1024x1024 (double original size) with your preferred upscaler and Denoise 0.5, CFG 7. Then send to img2img!</li><li>img2img: DPM++ SED Karras with 20 steps, Restore faces on (CodeFormer weight 1), rescale to 1536x1536, CFG 7, Denoise between 0.3-0.7 (based on how much you want to improve the image), SAME PROMPT! Send to extras when happy with img2img/inpaint results.</li><li>extras: Scale to x3 (final will be 4608x4608, I suggest going lower, I did x3 just for the samples here) Upscaler 1 - FatalAnime 4x, Upscaler 2 - SwinIR 4x with 0.10 visibility, GFPGAN 0.10 visibility, CodeFormer 0.10 visibility.</li></ol>If anyone is curious about my version names: v{version}.{trainingEpochs}

SmallPenis10.safetensors

v1.10 - Normal LoRA

v5.9

v4.14

v3.8 - Normal LoRA

v2.20 - Normal LoRA

v2.15 - Normal LoRA

v1.15 - Normal LoRA

v1.20 - Normal LoRA

Generate using a weight of 0.4-0.72 like this: &lt;lora:SmallPenis20:0.4&gt; .If you use more, the model will most likely generate white borders around the image (thats a problem in my Dataset, already working on it. Hopefully next version won't have this problem)I believe this version is overfitting. You might wanna try the 15 epochs one or the 10 epochs one. How I archived my generations:<ol><li>txt2img: DPM++ SDE Karras with 20 steps, 512x512(can go up to 768 for wide or tall), Restore faces on (using CodeFormer weight 1.0 in Settings), Hires-fix on, to 1024x1024 (double original size) with your preferred upscaler and Denoise 0.5, CFG 7. Then send to img2img!</li><li>img2img: DPM++ SED Karras with 20 steps, Restore faces on (CodeFormer weight 1), rescale to 1536x1536, CFG 7, Denoise between 0.3-0.7 (based on how much you want to improve the image), SAME PROMPT! Send to extras when happy with img2img/inpaint results.</li><li>extras: Scale to x3 (final will be 4608x4608, I suggest going lower, I did x3 just for the samples here) Upscaler 1 - FatalAnime 4x, Upscaler 2 - SwinIR 4x with 0.10 visibility, GFPGAN 0.10 visibility, CodeFormer 0.10 visibility.</li></ol>If anyone is curious about my version names: v{version}.{trainingEpochs}

Files with SHA256: 0e1615d5a7f3ea53b89cab1e819b60a6cbfce330b9b7a2ae8ae678d0eb0e6a6c