Actress Series #5: Bae Doona. Trained on a large dataset (390+ images). Sample images generated WITHOUT any other LoRAs as a demonstration of this LoRA's capabilities.

Check out my checkpoint merges here: Aneurysm (photoreal), Acoustica (semi-real) and Anabolic (modern anime). Download my other LoRAs here

Special thanks to Samael1976 for sharing a sneak preview of his AniMerge v4.0 model for some of the sample images! Please check out his amazing work.

I'd like to get to 1K followers so 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 new messaging feature too.

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 subject:

South Korean actress & photographer known internationally for her roles in films like Cloud Atlas (2012), Jupiter Ascending (2015), the Rebel Moon series (2023-2024) as well the Netflix television series Sense8 (2015–2018. She is also well known through her roles in Korean cinema in films like such as Sympathy for Mr. Vengeance (2002), The Host (2006), and Air Doll (2009), and in the Netflix period zombie thriller, Kingdom (2019–2020).

Trigger word: ZH_BaeDoona,

Other useful triggers: 1girl, solo, realistic, looking at viewer, black hair, brown hair, short hair, black eyes (see tags in LoRA for full list).

Suggested settings

ADetailer, hi-res.fix use is recommended.
Suggested settings : 0.9 to 1, Clip Skip: 1, ADetailer: eyes only
Method: DPM++(3M or 2M) SDE Karras, Steps:30-50, CFG : 6-7, 512x768 + high res fix with 2x upscale

About the training data:

This LoRA was trained on 390+ images of the subject