Slider pony & ILustrious
详情
下载文件 (1)
模型描述
LoRA Slider Anatomy — PONY/IL
Rank 100/100 | 1024×1024 | 1000 high-fidelity images | Prodigy Constant
What this LoRA does
Trained for full anatomical control of the female figure with high-fidelity photorealism. Built with Machine Learning engineering and precise dataset curation.
Anatomical Control
Full control over body proportions and regions:
Face — bone structure, cheekbones, chin, natural proportions
Neck and throat — natural length and definition
Shoulders and collarbone — proportional width, prominent collarbone
Chest and bust — natural shape, positioning and fabric physics
Abdomen and waist — waist-to-hip ratio, anatomically correct navel
Hips and glutes — natural lumbar curve, hip proportions
Hourglass figure — harmonic and realistic proportions
Breast Size Control
Natural and proportional scaling without anatomical distortion:
small breasts | medium breasts | big breasts | huge breasts
Supported Poses
The model maintains anatomical consistency across all poses:
Front facing
3/4 front
Side profile
Back view
Back view with face turned
Expressions
Serious / neutral
Soft smile
Open smile with teeth
Hair Variations
Straight loose
Wavy loose
High and low ponytail
Messy updo with loose strands
Bun
Ethnic Diversity
Works with ethnic diversity without additional LoRA:
European / Nordic
Latin / Mediterranean
Asian
Black / African descent
Brunette / olive skin
Clothing and Materials
Correctly renders fabric physics in contact with the body:
Casual
Tank top, crop top, ribbed top, t-shirt
Lingerie and Swimwear
Bikini — triangle, holographic, printed, metallic
Lingerie — lace, bodysuit, corset, bra, panties
Formal and Editorial
Tight dress, wrap dress, dress shirt, blazer, pencil skirt
Environments
Indoor — living room, bedroom, hallway, office
Outdoor — beach, pool, garden, veranda
Urban — street, rooftop with city view
Lighting
Golden hour — warm afternoon light
Window light — soft and diffused
Direct sunlight — outdoor with projected shadows
Studio — controlled neutral background
Neon — urban bicolor night lighting
Warm ambient light
Skin Quality
Subsurface scattering — light passing through skin naturally
Subsurface dispersion — micro-level light dispersion
Natural pore texture
Fine vellus hair
Wet skin with sun reflection
Catchlight in eyes
Recommended Keywords
anatomically accurate, hourglass figure, slender waist, wide voluptuous hips,
natural breast shape, soft breast tissue, flawless body proportions,
smooth skin, micro skin details, natural pore texture, fine vellus hair,
subsurface scattering, subsurface dispersion, prominent collarbone,
visible neck, elongated neck, delicate face, sharp facial features
Notes
Trained on Flux Dev — use with Flux Dev or compatible hybrids
No merge — pure training result
Dataset: 1000 manually curated high-fidelity images
Optimizer: Prodigy Constant
Built with applied Machine Learning engineering and Data Science.
⚠️ CONTENT WARNING (NSFW):
This merge is uncensored and capable of generating high-quality explicit NSFW content and nudity. It has a tendency towards revealing clothing in casual settings.
For SFW results: Strong negative prompts are highly recommended (e.g.,
nude, nipples, explicit, nsfw).
⚠️ LICENSE & PERMISSIONS (READ BEFORE DOWNLOADING)
1. PERSONAL USE ONLY This model is provided free of charge for Personal, Non-Profit, and Research use only. You may use it to create images for your personal portfolio.
2. STRICTLY NO REDISTRIBUTION
❌ DO NOT re-upload this file to Civitai, Hugging Face, or any other platform.
❌ DO NOT host this model on third-party generation services (e.g., Tensor.art, Mage.space, Telegram Bots).
3. COMMERCIAL RESTRICTIONS Using this model or its outputs for commercial revenue (Influencers, Ads, Stock Photos) without a license is PROHIBITED.
💼 COMMERCIAL SERVICES & COMMISSIONS
I do not sell the model file for commercial use. Instead, I offer premium AI solutions for brands and agencies:
✨ Exclusive AI Influencers: I create and manage consistent digital personas for Instagram/Social Media.
🏢 Corporate B2B LoRAs: Custom training for brand identity and mascots.
📸 High-End Image Packs: Monthly content packages for your brand.
To hire me for professional AI Modeling services: 📩 Contact: [[email protected]]
o activate the model you need to insert the token "Atysldry" and the class "woman"
Recommended strength: 0.9-3
Recommended settings:
Standard resolutions 512 x 640, 600x800, 640x960, 1024x1024
Resolution: 540x540 mark the Hires.fix, result 1080 x 1080 pixel
Resolution settings:
Standard resolutions 512x640, 600x800, 640x690
Resolution: 540x540 select the Hires.fix checkbox, result 1080 x 1080 pixels
Note: I am testing the sampling methods and I will add the others to the settings.
Use these recommended settings for generation:
Sampling method: Euler a
Sampling steps: 30-50
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: Restart
Sampling steps: 30-50
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: Kohaku_LoNyu_Yog
Sampling steps: 30-50
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: Euler_Max
Sampling steps: 30-50
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: Euler_Smea_Dy
Sampling steps: 18-50
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: Euler a
Sampling steps: 18-50
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: LCM
Sampling steps: 18-30
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: DDPM Karras
Sampling steps: 18-30
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: DPM++ 2M
Sampling steps: 18-30
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: DPM++ SDE Karras
Sampling steps: 18-30
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Sampling method: DPM++ 2M SDE Karras
Sampling steps: 18-30
CFG Scale: 2.0 - 7.0
Skip clip: 1-2
Use the recommended negative prompt:
Stable_Yogis_PDXL_Negatives-neg,monochrome, bad fingers, malformed hands, malformed arm, multiplied arm