Sweety Girl Origin

The first fully trained version of the Sweety Girl series. A photorealistic model focused on female portraits with editorial quality.

About the model

Sweety Girl Origin is the trained foundation behind the series aesthetic. Previous versions (V1-V4) were merges; Origin is the first complete fine-tune, trained on 7,175 curated images at native 640x960 resolution.

Unlike merges, Origin has its own technical identity — capabilities learned directly from the dataset, not interpolated from other models.

Key features

• Photographic model focused on portraits and editorial photography

• Wide ethnic variation (East Asian, European, Latina, Nordic, Mediterranean, mixed-heritage)

• Responsive breast size slider (small breasts, medium breasts, large breasts respond in a controlled manner)

• Realistic skin textures with visible pores and subsurface scattering

• Hair rendered with individual strands and natural shine

• Strong performance across varied lighting conditions (golden hour, studio, urban night, dappled sunlight, backlight)

• Distinct material properties in fabrics (satin, lace, denim, knit, silk)

• Compatible with standard SD1.5 LoRAs and embeddings

• No VAE required — model generates clean, detailed results natively

Technical specifications

• Base: Stable Diffusion 1.5

• Training resolution: 640x960

• Dataset: 7,175 images

• Full fine-tune (UNet + embedded VAE)

• No external VAE needed

Recommended settings

• Samplers: DPM++ 2M Karras, Euler a, DPM++ SDE Karras, Restart

• Steps: 25-40

• CFG Scale: 3.0 - 7.0

• Clip Skip: 1 or 2

• Generation resolution: 640x960 (native) or 2:3 variations

• Optional Hires fix for larger resolutions

Suggested negative prompt

deformed, bad anatomy, bad hands, missing fingers, extra fingers, mutated hands, blurry face, out of focus face, cartoon, anime, illustration, painting, 3d render, watermark, text, signature, oversaturated, plastic skin, doll, low quality, flat lighting, overexposed

Content

This model is capable of generating NSFW content. For SFW results, use appropriate negative prompts (nude, nipples, explicit, nsfw).

Recommendations

• Adetailer extension recommended for facial refinement in close-ups

• Danbooru-style prompts work best

• Ethnic variation responds well to descriptive tags for facial structure

⚠️ 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]]

I recommend using the Adetailer extension.

Use this extension to fix hand errors:

https://github.com/licyk/advanced_euler_sampler_extension

Use these recommended settings for generation:

Sampling method: Euler_Max

Sampling steps: 30-50

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: 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_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++ 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

(CyberRealistic_Negative-neg), deformed, bad anatomy, bad hands, missing fingers,

extra fingers, mutated hands, poorly drawn hands,

blurry face, out of focus face, cartoon, anime,

illustration, painting, drawing, 3d render,

watermark, text, signature, oversaturated, bad neck,

plastic skin, doll, unrealistic, low quality,

flat lighting, overexposed, nude, asian, chinese, japansese