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

Instagram model series: Brynhildur Brá Gunnlaugsdóttir. Trained on a large dataset (350 images). Sample images generated WITHOUT any other LoRAs (except my own) as a demonstration of this LoRA's capabilities. Likeness based on her more recent years, due to the changes to her appearance from cosmetic enhancements, etc.

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:

23 year old Icelandic TikTok & Instagram star known for posting lip sync, comedy, beauty and vlog content. She is one of the most popular Icelanders on TikTok, with brynhildurgunnlaugss TikTok account boasting over 1.6 million followers, and a further 119k followers on Instagram.

Originally from Egilsstaðir, she was soccer (football) player in her youth, most notably playing for UMF Selfoss. She is currently without a club since 2020.

Trigger word: ZH_Brynh1ldurBG

Other useful triggers: 1girl, solo, realistic, looking at viewer, blue eyes, blonde hair, long hair, dark skin, large breasts, tattoo (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 350 images of the subject