FIGURA: A Modular Prompt Engineering Method for Artistic Figure Photography in Safety-Filtered Text-to-Image Models

TL;DR

The paper introduces FIGURA, a modular prompt engineering system that enables artists to generate artistic figure photography within safety-filtered text-to-image models, revealing new insights into filter behavior and achieving high success rates.

Contribution

It presents a novel, empirically validated prompt engineering framework that systematically overcomes safety filters in commercial T2I models for artistic figure creation.

Findings

Safety filters detect absence descriptions more than presence descriptions.

Artistic references influence safety filter behavior.

Spatial context acts as an independent filter variable.

Abstract

Safety filters in commercial text-to-image (T2I) models systematically block legitimate artistic content involving the human figure, treating classical nude photography with the same restrictiveness as explicit material. While prior research has documented this problem extensively, no operational system exists that enables professional artists to generate artistic figure photography within the constraints of active safety filters. We present the FIGURA Method (Framework for Intelligent Generation of Unrestricted Artistic Results), a modular prompt engineering system comprising eight interconnected knowledge files, empirically validated through 200+ documented generation tests on FLUX 2 Pro (Cloud) with active safety filters at the default tolerance level. Our systematic testing reveals several previously undocumented findings: (1) safety filters primarily detect absence descriptions (references to missing clothing) rather than presence descriptions (references to body form), which we formalize as the Golden Rule; (2) artistic references to painters function simultaneously as aesthetic guides and as safety anchors that alter filter behavior; (3) spatial context operates as an independent filter variable, with documented success rate hierarchies; and (4) geometric vocabulary for body description bypasses pattern recognition in silhouette contexts. The system achieves documented success rates between 80% and 90% across five structured prompt templates, demonstrating that the artistic censorship problem identified in recent literature admits practical, systematic solutions that work with active safety mechanisms rather than circumventing them.