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

Fashion model series: Melodie Vaxelaire. Trained on a large dataset (400 images). Sample images generated WITHOUT any other LoRAs (except my own) as a demonstration of this LoRA's capabilities. Made this as she has very unique features and a distinctive look.

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:

Guadeloupean-born French fashion model who has over 103,000 followers on Instagram.

Initially aiming to be a dancer (having trained for 11 years), she was instead discovered by an agent at the age of 18 in a supermarket while on a gap year from university. That lead to a full-time career as a fashion model, working between Paris, NY, and all around the world. Initially finding some industry resistance to her naturally curly hair, she's stated that it is now her defining asset as a model.

Since signing with the world-famous Elite Paris agency, she's worked for notable brands like Chanel, Gap, Etam, Abercrombie & Fitch and the United Colors of Benetton.

Trigger word: ZH_MVax3La1r3,

Other useful triggers: 1girl, solo, realistic, looking at viewer, brown eyes, black hair, curly hair, dark skin (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 400 images of the subject