AI RESEARCH
Toward Trustworthy Portrait Editing: Evaluation of Demographic Misrepresentation in I2I Models
arXiv CS.CV
•
ArXi:2602.16149v2 Announce Type: replace Instruction-guided image-to-image (I2I) editors are increasingly used in consumer and professional visual workflows, where trustworthiness depends not only on prompt compliance but also on equitable preservation of identity-relevant attributes. We formalize two failure modes: Soft Erasure, where requested edits are weakly realized or silently suppressed, and Stereotype Replacement, where edits