art.jt

Lesley Tannahill

about this artist ↗ · custom FLUX.1-dev LoRA

01 Model & Methodology Filed 2026-05-05

Custom FLUX.1-dev LoRA, fine-tuned on Lesley Tannahill's own canvas work.

A LoRA (low-rank adaptation) is a compact set of trainable weights that sits on top of a much larger frozen base model. Instead of retraining FLUX.1-dev, the open-source 12-billion-parameter text-to-image transformer from Black Forest Labs, the LoRA only adjusts ~50 million new parameters using a small artist-specific dataset. The result keeps FLUX's general image-generation ability intact while teaching it one artist's visual language.

Pieces in this gallery are produced by a private FLUX.1-dev LoRA trained on 28 hand-curated reproductions from lesleytannahill.com, spanning the Selected Self-Portraits series: Fictions, Making Up My Minds, and Process of Discovery. Every image was captioned with its title, medium, dimensions, and year, binding the trigger to specific painterly cues rather than a generic style label.

Base Model
FLUX.1-dev
Training Set
28 canvases
LoRA Rank
32
Steps
1,500
Train Time
12 min · H100

Trigger word lesley_tannahill_style is prepended to every weather-derived prompt before inference. Trained via ostris/flux-dev-lora-trainer on Replicate.