[𝕃𝕠𝕧𝕖𝕝𝕪🥰| 𝔽𝕠𝕣𝕥𝕟𝕚𝕥𝕖] - 🎨𝕀𝕝𝕝𝕦𝕤𝕥𝕣𝕚𝕠𝕦𝕤 𝕏𝕃/🦄ℙ𝕠𝕟𝕪 𝕏𝕃 𝕃𝕠ℝ𝔸

This is a high-fidelity LoRA designed for Illustrious-XL/Pony XL It was trained on a curated synthetic dataset to ensure maximum flexibility and character consistency while maintaining the high-aesthetic standards of the base model.

🥰𝑀𝑜𝒹𝑒𝓁 𝒪𝓋𝑒𝓇𝓋𝒾𝑒𝓌: 𝐹𝑜𝓇𝓉𝓃𝒾𝓉𝑒 𝐿𝑜𝓋𝑒𝓁𝓎

This LoRA brings the popular Rare Outfit "Lovely" to your generations. Designed for versatility, it excels at replicating her specific character design while allowing for stylistic flexibility-whether you’re aiming for the original Fortnite game-art style or a more realistic/anime-inspired interpretation.

🎨𝒦𝑒𝓎 𝒱𝒾𝓈𝓊𝒶𝓁 𝐹𝑒𝒶𝓉𝓊𝓇𝑒𝓈

• Hair: Mid-length, vibrant bubblegum pink hair with a black bow accessory.

• Top: A white sleeveless shirt featuring a large, crowned heart emblem with wings and a "shattered" effect.

• Outfit Details: Black pleated skirt with rose patterns, dark pink leggings/thigh-highs, and fingerless gloves.

• Accessories: Red heart-shaped grenades (explosives) strapped to the arms and legs, often seen with lit fuses.

🚀 𝕌𝕤𝕒𝕘𝕖 ℝ𝕖𝕔𝕠𝕞𝕞𝕖𝕟𝕕𝕒𝕥𝕚𝕠𝕟𝕤

⚙️𝐵𝒶𝓈𝑒 𝑀𝑜𝒹𝑒𝓁: 🎨𝐼𝓁𝓁𝓊𝓈𝓉𝓇𝒾𝑜𝓊𝓈

• Trigger Word: LovelyFN

• LoRA Weight: 0.7 - 0.8 (Start at 0.7 for maximum accuracy)

• CFG Scale: 5.0 - 7.0

• Clip Skip: 2

• Sampling Method: Euler a or DPM++ 2M Karras

• Recommend to use: Nova 3DCG XL, WAI-illustrious-SDXL

⚙️ 𝐵𝒶𝓈𝑒 𝑀𝑜𝒹𝑒𝓁: 🦄𝒫𝑜𝓃𝓎 𝒳𝐿

• Trigger Word: LovelyFN

• Recommended Weight: 0.8 - 0.9

• CFG Scale: 5.0 - 7.0

• Sampler: DPM++ 2M Karras (25–30 steps)

• Recommend to use: WAI-ANI-PONYXL, WAI-SemiReal, BlenderMix

🛠️ ℙ𝕣𝕠𝕞𝕡𝕥𝕚𝕟𝕘 𝔾𝕦𝕚𝕕𝕖

This model is highly responsive to descriptive tags. For the best results, use a mix of the trigger word and specific outfit/pose descriptions.

• Main Trigger: LovelyFN

• Core Look: pink hair, long hair, pink eyes, 1girl, solo

• Signature Outfit: miniskirt, skirt, thighhighs, boots, belt, heart

• Tactical Gear: gloves, black gloves, fingerless gloves

Negative Tags: low quality, blurry, deformed, text, watermark

📈 𝕋𝕖𝕔𝕙𝕟𝕚𝕔𝕒𝕝 𝔻𝕖𝕥𝕒𝕚𝕝𝕤

• Dataset: Created using a high-quality synthetic workflow to generate diverse angles and lighting from a single reference source.

• Training: Optimized using bfloat16 for precision.

• Train Model: WAI-illustrious-SDXL v.17/ WAI-ANI-PONYXL v.14

• Version: 2.0/1.0 (Last Release)

🕒 𝒱𝑒𝓇𝓈𝒾𝑜𝓃 𝐻𝒾𝓈𝓉𝑜𝓇𝓎

Version 1.0 (Initial Release)

• Focus: Establishing character consistency.

• Note: Was 1st version of that lora (beta).

Version 2.0 (Dataset Expansion)

• Focus: Flexibility and Pose Variety.

• Improvements: Cleaner Visuals, Dynamic Poses, Better Accuracy, Faster Loading, less size

Version 1.0 (Pony)

• Focus: Pony release

• Note: Establishing character consistency.

💬 ℕ𝕠𝕥𝕖𝕤 & 𝔽𝕖𝕖𝕕𝕓𝕒𝕔𝕜

I am constantly refining the dataset generation process. If you enjoy the model, please post your generations and leave a review-it helps me understand how to improve future versions!

If you run into issues with character bleeding or specific clothing items, let me know in the discussion.