AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Navigating Text-to-Image Generative Bias across Indic Languages

Surbhi Mittal, Arnav Sudan, Mayank Vatsa, Richa Singh, Tamar Glaser, Tal Hassner

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
prompt in Indic languages instead of EnglishStable Diffusion · IndicTTI AssameseCLGC (%): 64.53 -> 7.29Hurt
prompt in Indic languages instead of EnglishAlt Diffusion · IndicTTI AssameseCLGC (%): 58.16 -> 14.65Hurt
use Dalle3 instead of open-source models for Indic promptstext-to-image generation · IndicTTI HindiCLGC (%): 7.35 -> 64.16Improved
use multilingual-trained AltDiffusion instead of Stable Diffusion for Indic promptsStable Diffusion · IndicTTI HindiCLGC (%): 7.35 -> 16.79Improved
use multilingual-trained AltDiffusion instead of Stable Diffusion for English promptsStable Diffusion · IndicTTI EnglishCLGC (%): 64.53 -> 58.16Hurt
Dalle3 on low-resource scripts (Meitei, Ol Chiki, Bodo)Dalle3 · IndicTTI LGCLGC (%): 33.06 (English) -> 1.52 Manipuri Meitei, 2.09 SantaliHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy