Gerhard Richter

Custom FLUX.1-dev LoRA, fine-tuned on Gerhard Richter'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 60 hand-curated reproductions from WikiArt catalog, covering his photorealist canvases and the squeegee Abstrakte Bilder (1962-2017) - dragged-paint surfaces, color-strip compositions, blurred photo paintings. Every image was captioned with its title, medium, dimensions, and year, binding the trigger to specific painterly cues rather than a generic style label.

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