Instagram series: Carmella Rose. Trained on a large dataset (650 images). Sample images generated WITHOUT any other LoRAs except my own as a demonstration of this LoRA's capabilities.

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 1.2K followers! Your comments/reviews/likes/follows are most welcome, as are tips/buzz so I can keep making these! 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 model (Carmella Rose McBreen) popular for her appearances as a commercial model in magazines, photo shoots, and Instagram rather than high fashion. She got her start with the famous Wilhelmina Model agency, and has since worked with top agencies such as M1M entertainment, Elite Model, and No Tie Management. Her features include appearances and interviews in magazines like Playboy, Maxim, Elle and Grazia. Currently, she has over 2.4 million followers on Instagram and 156,200 followers on TikTok. She is also media influencer for the nonprofit organization Models of Compassion.

Trigger word: ZH_Carm3llaR0s3M,

Other useful triggers: 1girl, solo, realistic, looking at viewer, long hair, lips, brown eyes, brown hair, (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 650 images of the subject