Original size 384x512

8 Figures of Ashley

PROTECT STATUS: not protected
Longread translated automatically

In this project, I explored how a character—specifically, my cat, Ashley—would look as a representative of different subcultures.

Ashley in her natural habitat

The original dataset consists of 38 photographs gathered from a personal archive. It includes images of a cat from various angles, under different lighting conditions, and against various backgrounds.

Result

METAL / GRUNGE

PUNK / CYBERPUNK

SKATER / Y2K

RAVE / GOTH

I had to edit the prompts for a long time to make the neural network convey Ashley’s facial features, and even in the final generations, not all details look realistic; nevertheless, the generations often capture the cat’s favorite poses found in the photos.

Process

big
Original size 512x512

Example where the placeholder for the subculture image turned out to be a portrait

Initially, Stable Diffusion XL 1.0 (SDXL) was chosen as the base model during the process, and LoRA (Low-Rank Adaptation) was used to fine-tune the character. However, SDXL proved to be too resource-intensive and was replaced with Stable Diffusion 1.5.Another set of issues arose during the creation phase: the neural network was transforming the cat into a human and generating portraits without backgrounds or details. This was resolved by transferring the key features of Ashley’s subculture onto the background.Overall, I am satisfied with the result and hope Ashley’s cyber-doubles had a good time.

Original size 1978x658

Top Attempts

8 Figures of Ashley
Project created at 26.09.2026
We use cookies to improve the operation of the website and to enhance its usability. More detailed information on the use of cookies can be fo...
Show more