Across six text-to-image models, stereotyped outputs rise from 25.9% of single photos to about 36% of storyboards and 44% of four-panel comics, with bias expressed through plot, character placement, and dialogue.
Social biases through the text-to-image generation lens
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Investigating Social Bias in Narrative Image Generation
Across six text-to-image models, stereotyped outputs rise from 25.9% of single photos to about 36% of storyboards and 44% of four-panel comics, with bias expressed through plot, character placement, and dialogue.