Trained on <a target="_blank" rel="ugc" href="https://civarchive.com/models/133005?modelVersionId=288982">Juggernaut XL v8</a>. All training images were with (mostly Caucasian) women 20-30 years old, without logos or text; any logos/text that you get are from the base model, not this LoRA. Does not render Asian or African pubic hair accurately (looks too Caucasian). Steps: 29280, Epochs: 60, Repeats: 4, Network dimension: 128. Took 13 hr on RTX4080. I tested earlier epochs, and (maybe) because of high network dimension, there still isn't much overfitting. There are plenty of guides on dimension/epochs/steps/repeats, but its still mostly a black box to me.Recommended strength: 0.3-0.8. &lt;lora:SDXL_hairy:0.5&gt; CFG scales 3-8.Can work without prompts, but the phrase "hairy pussy, female pubic hair, vagina, clitoris, ..." in your prompts works best.<hr />Works very well with <a target="_blank" rel="ugc" href="https://civarchive.com/models/194245/omnium">Omnium</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/189109/photopedia-xl">Photopedia XL</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/152525/realism-engine-sdxl">RealismEngine SDXL</a>, and pretty well with <a target="_blank" rel="ugc" href="https://civarchive.com/models/167764/sdxxxl">SDXXXL</a>, NightVision, NewReality, RealisticStockPhoto, RealisticDigital, SocaRealism, ThinkDiffusionXL, <a target="_blank" rel="ugc" href="https://civarchive.com/models/101055">SD XL (base)</a>, Juggernaut, RealVisXL3, WyvernMix, Copax.I had poor results using this LoRA with EnjoyXL, ImperfectXL, TD-UltraReal.<hr />Best to add into your prompt a few other LoRAs for more realism, like <a target="_blank" rel="ugc" href="https://civarchive.com/models/232746">Real Humans</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/135160/polyhedronall-sdxl-10-skin-hands-eyes-mf">Polyhedron_all SDXL</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/285909/freckles-and-skin-xl">Freckles &amp; Skin XL</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/118427">Perfect Eyes XL</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/128371">Teeth XL</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/models/137409">NaturalBodyXL</a>, and even additional hairy pussy LoRAs like <a target="_blank" rel="ugc" href="https://civarchive.com/models/224786/really-hairy-women">Really Hairy Women</a> or <a target="_blank" rel="ugc" href="https://civarchive.com/models/122069/hairy-girls-sdxl-10">Hairy Girls SDXL</a>.I've had excellent upscale results with <a target="_blank" rel="ugc" href="https://civarchive.com/models/116225">4x-UltraSharp</a>, and terrible with the default "latent".

SDXL_hairy

same as v1.5, but with 32 dimensions instead of 128. Trained on the same 123 images, 4 repeats, 20 epochs, 4920 steps, 2.5 hr on RTX 4080. "Only" 223Mb (instead of 891Mb for non-lite version). So far, my tests show nearly identical images between lite and full. Note that the file name is v1.5_LITE, but v1.4_LITE shows up when you call it in the prompt; just a typo on my part that I don't know how to fix easily.

Files with SHA256: f854e52ba506c1c879e7ca780851edf2aa20896d5fe8587a2ccb401319e52074