Countdown to Goodbye! (please read): https://civarchive.com/articles/12655

Fashion model series: Anok Yai. Trained on a large dataset (420 images). Sample images generated WITHOUT any other LoRAs (except my own) as a demonstration of this LoRA's capabilities. Made this as there isn't a SD1.5 LoRA of her on here.

Check out my checkpoint merges here: Aneurysm (realism-newly updated with v2), Acoustica (semi-real) and Anabolic (modern anime). Download my other LoRAs here

Thank you for 1.3K followers! Your comments/reviews/likes/follows are most welcome. I'd love to see the images you create, so please share on here or reach me on Discord (zombiehead91). Feel free to message me on CivitAI's messaging feature too.

About the subject:

American-South Sudanese fashion model who's reached supermodel status, having won multiple industry awards including "Model of the Year" in 2023. Born in Egypt after her family had fled genocide in Sudan, she later moved to the US, growing up in New Hampshire.

She was got her start in 2017 when she was discovered by a professional photographer during her university's homecoming week, who posted a photo of her to Instagram that earned over 20,000 likes. Various modeling agencies reached out to sign her, with her eventually choosing Next Model Management.

Since then, she's walked the runways for brands including Prada, Alexander Wang, Versace, Max Mara, Fendi, Burberry, and Louis Vuitton, as well appearing in ads for Tiffany & Co., Nike, Hood by Air, and Ambush.

She's also made appearances in music videos, notably in Travis Scott's "I KNOW?" and Offset's "Swing My Way". She has over 2.5 million followers on Instagram.

Trigger word: ZH_An0kYa1,

Other useful triggers: 1girl, solo, realistic, looking at viewer, black hair, very dark skin, short hair/afro/dreadlocks (see tags in LoRA for full list).

Suggested settings

ADetailer, hi-res.fix use is recommended.
Suggested settings : 0.8 to 1, Clip Skip: 1-2, ADetailer recommended
Method: DPM++(3M or 2M) SDE Karras, Steps:30-50, CFG : 6-7, 512x768 + high res fix with 2x upscale

Notice : Usage of this resource is ONLY permitted for educational, personal and non-commercial use. Please observe the permissions listed on this page - do NOT share this resource anywhere else without my knowledge, especially on other sites for commercial use. Please be respectful of the subject and CivitAI terms of use, and avoid all NSFW content. No warranty is provided, and the user bears responsibility for any/all use of this resource. Happy to discuss this further on Discord if unclear

About the training data:

This LoRA was trained on 420 images of the subject