Published October 11, 2026 | Version 1.0

Preference ≠ Tattooability: Auditing Reward Models for AI Tattoo Generation

Authors/Creators

  • 1. ZheLogic, LLC

Description

AI tattoo generation is usually ranked with the same reward models that rank general text-to-image outputs. Those models predict which image a crowd annotator prefers. A tattoo that will be worn also has to survive a needle, a gap that heals shut, and ink that spreads. We audited that gap with deterministic, physically scaled probes and with CLIPScore, PickScore, HPSv2.1 and ImageReward, on tattoo-subject pairs from HPDv2 and ImageRewardDB, on controlled defects, and on a print-scale ink-spread stress test. On HPDv2 tattoo-subject pairs, a-priori probes agree with human preference below chance, and that contrast remains after a Holm correction across scorers. Nothing here ranks a commercial AI tattoo generator.

Competing interest: the author operates tatany.app; that product was not evaluated or ranked.

Files

Preference_Tattooability_v1.0.pdf

Files (8.9 MB)

Name Size
md5:1c00de3a78cc65cae1c192e6ff319d65
1.8 MB Download
md5:561229b0269b27974407faae4cab1241
1.7 MB Preview Download
md5:2c6439372ec46142523fe7c4b11b6783
5.4 MB Preview Download

Additional details

Related works

Is documented by
Other: https://tatany.app (URL)
Is supplement to
Software: https://github.com/Stark-Will/tattoo-probes (URL)