Anna Sorokin (AKA Anna Delvey)

Anna Sorokin took on the identity of "Anna Delvey" to pose as a German Heiress from 2013 - 2017 within the New York social scene. She used this identity to gain access to NY elites as was later convicted of defrauding financial institutions and individuals. She served (2) years in NY State Correctional Facilities before being remanded to the US Immigration Service for deportation back to Germany. In March 2021 she contested deportation and was released under house arrest pending resolution of her immigration case. Her story was featured in a 2022 Netflix series "Inventing Anna". Anna was born in the former Soviet Union in 1991 before her family emigrated to Germany in 2007. She worked previously in London and Paris before moving to New York in 2013.

This is a SD V1-5 version LoRA, with a trigger word of 4nn4D31v3y.

This model was trained for SFW use, but may trend toward risqué without careful prompting. You should always include NSFW as a negative prompt if you have any concerns and to be respectful. Use of this model should always abide by Civitai's Content Rules. Use for generating illegal, sexual, violent, or other non-consensual content and themes is expressly discouraged.

This model is a SD V1.5 LoRA trained on 40 publicly available images using Kohya_ss (https://github.com/kohya-ss/sd-scripts) webui (https://github.com/bmaltais/kohya_ss). Sample images were rendered using A1111 (https://github.com/AUTOMATIC1111/stable-diffusion-webui).

Sample Prompt:

a RAW photograph of 25 year old (4nn4D31v3y woman) sitting on a couch,wearing a (gray dress),facing the viewer,(medium shot),portrait,(perfect chestnut hair),(red lipstick),simple background,rich details,hyper realistic,intense,highly detailed,face_focus,looking_at_viewer,<lora:4nn4D31v3y_SD1-5:0.9>

If you are pleased with the models provided, I would be grateful for your support with a 👍 Like, 🚶 Follow, or ❤ Review. I greatly appreciate your comments, feedback, and images which helps me continue to improve my model workflow, testing, and image generation.

I am also extremely grateful for tips ☕ if you appreciate my work, (https://buymeacoffee.com/Signalytix), as it helps significantly to offset my costs and effort, allowing me to devote more time to research, create, contribute, and share my work with the community. Suggestions posted to my tips page (https://buymeacoffee.com/Signalytix) garner my utmost attention for new models. I currently focus on development of LoRAs and embeddings for SDXL and V1.5.

------------------------------------------------------

Model Card:

Name: 4nn4D31v3y_SD1-5:0.9

Version: 1-SDXL

Description: Anna Sorokin (AKA Anna Delvey), Social Influencer LoRA

Trigger Words: 4nn4D13v3y

Data Set: 40 images (768x768)

Epochs: 3

Steps: 765

Batches: 4

Repeats: 25

Optimizer: DAdaptAdam

Base Model: runwayml/stable-diffusion-v1-5

------------------------------------------------------

ARTIFICIAL HUMANS ASSOCIATION (AHA) CERTIFICATION:

No WAIFUS were harmed, exploited, or compromised in the training of this model or creation of images.