Trained on Juggernaut XL v8. 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. <lora:SDXL_hairy:0.5> CFG scales 3-8.
Can work without prompts, but the phrase "hairy pussy, female pubic hair, vagina, clitoris, ..." in your prompts works best.
Works very well with Omnium, Photopedia XL, RealismEngine SDXL, and pretty well with SDXXXL, NightVision, NewReality, RealisticStockPhoto, RealisticDigital, SocaRealism, ThinkDiffusionXL, SD XL (base), Juggernaut, RealVisXL3, WyvernMix, Copax.
I had poor results using this LoRA with EnjoyXL, ImperfectXL, TD-UltraReal.
Best to add into your prompt a few other LoRAs for more realism, like Real Humans, Polyhedron_all SDXL, Freckles & Skin XL, Perfect Eyes XL, Teeth XL, NaturalBodyXL, and even additional hairy pussy LoRAs like Really Hairy Women or Hairy Girls SDXL.
I've had excellent upscale results with 4x-UltraSharp, and terrible with the default "latent".
Description
Some fine tuning for this new version. Trained on Juggernaut-XL v8. Recommended weight: 0.3-0.8. All training images were with women 20-30 years old, without logos or text; any logos/text that you get are from the base model, not this LoRA.
Works very well with Omnium, Photopedia XL, RealismEngine SDXL.
Works pretty well with SDXXXL, NightVision, NewReality, RealisticStockPhoto, RealisticDigital, SocaRealism, ThinkDiffusionXL, SD XL (base), Juggernaut, RealVisXL3, WyvernMix, Copax.
I had poor results using this LoRA with EnjoyXL, ImperfectXL, TD-UltraReal.
Best to add into your prompt a few other LoRAs for more realism, like Real Humans, Polyhedron_all SDXL, Freckles & Skin XL, Perfect Eyes XL, Teeth XL, NaturalBodyXL, and even additional hairy pussy LoRAs like Really Hairy Women or Hairy Girls SDXL.
I've had excellent upscale results with 4x-UltraSharp, and terrible with the default "latent".
FAQ
Comments (11)
Why'd you remove the old version? I think it wiped all the gens from others.
Appreciate the question; answer=I'm a bonehead. I accidentally removed the old version when updating the new one; it's my first time uploading, so it was a simple mistake.
Network dimension: 128 makes the Lora size absolutely huge, almost 1gig for a lora, thats too much. I cant download it because im on a data capped internet plan. I normally trained 32-64 network dimensions to keep the size down because im not even sure a high network dimension matters much. Even at a dimension of 64, the lora was big, like 400mb. I lowered it down to 32 and never notice any difference in quality.
not work with fat,chubby woman
yep, it was trained on normal weight and thin women only, 20-30 years old. Other people have posted LoRAs that should work better for you, like "Really Hairy Women".
@Refurrify thank you, i"ll try it :)
Who likes fat girls ?? :-)
@DesignerSingapore Everyone that has a brain
@DD2BBW Nope. Muslims only ;-)