vestigiaproject/fayumportraits

An image model trained on ancient Fayum wood paintings. Use "fayumprtrt" in the prompt.

Public
448 runs

Run time and cost

This model costs approximately $0.067 to run on Replicate, or 14 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia H100 GPU hardware. Predictions typically complete within 45 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Fayum Portraits is a LoRA (Low-Rank Adaptation) model trained on Flux Dev with reference to ancient Fayum wood panel paintings.

How to Use

Provide a prompt describing the desired portrait, including the keyword fayumprtrt. For example:

A young man with curly hair, in the style of fayumprtrt, painted on a wood panel with encaustic techniques, Roman-Egyptian funerary art, 2nd century CE.

A woman with a golden diadem, in the style of fayumprtrt, painted on a wood panel with rich, warm tones, Roman-Egyptian style.

Generate and download your image.