AI Paper Atlas

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

ITI-GEN: Inclusive Text-to-Image Generation

Cheng Zhang, Xuanbai Chen, Siqi Chai, Chen Henry Wu, Dmitry Lagun, Thabo Beeler, Fernando De la Torre

ICCV 2023 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 59 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
learn inclusive tokens from reference images instead of hard prompt specificationStable Diffusion · CelebA eyeglassKL divergence: 0.371 -> 2 × 10^-4Improved
aggregate separate inclusive tokens by element-wise sum for multiple attributesITI-GEN · CelebA male x young x eyeglass x smileKL divergence: 0.476 -> 0.094Improved
add semantic consistency loss L_sem (ablation)ITI-GEN (CelebA reference) · FID on FFHQFID: 77.78 -> 60.38Improved
add semantic consistency loss L_sem (ablation)ITI-GEN (FAIR reference) · FID on FFHQFID: 62.69 -> 51.83Improved
use synthetic FAIR reference images instead of real CelebA images (ablation)ITI-GEN · FID on FFHQFID: 60.38 -> 51.83Improved
increase reference images per category beyond 10 (ablation)ITI-GEN · quantity ablationqualityImproved
use Custom Diffusion (personalization) with reference images instead of ITI-GENStable Diffusion · CelebA smileKL divergence: 0.134 -> 0.469Hurt
apply ethical intervention promptsStable Diffusion · CelebA pale skinKL divergence: 0.308 -> 0.644Hurt

Later papers that compared with this method

5 later accepted papers report ITI-GEN as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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