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.
In each experiment, we include an explicit note within the prompt to mitigate the potential positional bias
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 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.