AI Paper Atlas

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

OmniText: A Training-Free Generalist for Controllable Text-Image Manipulation

Agus Gunawan, Samuel Teodoro, Yun Chen, Soo Ye Kim, Jihyong Oh, Munchurl Kim

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control

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
add Self-Attention Inversion to TextDiff-2 for text removal (ablation)TextDiff-2 · SCUT-EnsText all text removalPSNR: 25.42 -> 30.02Improved
add Cross-Attention Reassignment on top of SAI (ablation)OmniText text removal · SCUT-EnsText all text removalPSNR: 30.02 -> 29.52Hurt
add Cross-Attention Reassignment on top of SAI (ablation)OmniText text removal · SCUT-EnsText largest text removalFID: 16.70 -> 15.33Improved
add cross-attention content loss L_C via latent optimization (ablation)TextDiff-2 · ScenePair text editingword accuracy (ACC, %): ACC 76.41 -> 88.52; MS-SSIM 35.56 -> 29.90Mixed
add grid trick and self-attention style loss (ablation)TextDiff-2 · ScenePair text editingMS-SSIM (x10^-2): 35.56 -> 40.19; ACC 76.41 -> 78.28Mixed
combine content loss with grid and style loss (ablation)OmniText · ScenePair text editingword accuracy (ACC, %): 78.28 -> 78.44Improved
apply OmniText to replace backbone TextDiff-2 on text editingTextDiff-2 · ScenePair text editingMSE (x10^-2): 6.49 -> 4.79Improved
add grid trick with self-attention modulation to UDiffTextUDiffText · OmniText-Bench style transfer (qualitative)style transfer qualityMixed
use prompt-tuning for general editing baselinesopen-source editing models · ScenePair text editingword accuracyNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

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