AI Paper Atlas

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

UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing

Tsu-Jui Fu, Yusu Qian, Chen Chen, Wenze Hu, Zhe Gan, Yinfei Yang

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 16 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
add instruction-based editing to T2I training (ablation)UniVG · GenEvalGenEval score: 0.71 -> 0.70No clear effect
add instruction-based editing to T2I training (ablation)UniVG · HPSv2HPSv2: 28.4 -> 28.3No clear effect
add ID-preserving generation without auxiliary tasks (ablation)UniVG · MagicBrushCLIP-T: 28.3 -> 26.9Hurt
add ID-preserving generation without auxiliary tasks (ablation)UniVG · EmuEditCLIP-T: 25.2 -> 24.9Hurt
add auxiliary tasks and layout generation to T2I+editing (ablation)UniVG · MagicBrushCLIP-T: 28.3 -> 29.8Improved
add auxiliary tasks and layout generation to T2I+editing (ablation)UniVG · EmuEditCLIP-T: 25.2 -> 26.2Improved
add auxiliary tasks when ID generation is included (ablation)UniVG · MagicBrushCLIP-T: 26.9 -> 29.5Improved
add auxiliary tasks when ID generation is included (ablation)UniVG · Unsplash-50CLIP-T: 28.9 -> 28.1Hurt
add auxiliary tasks when ID generation is included (ablation)UniVG · Unsplash-50ID similarity: 0.327 -> 0.329No clear effect
use channel-wise concatenation of image latents instead of sequence concatenationUniVG vs OmniGen · Editing inference timetime (sec): 36.8 -> 10.4Improved
scale model from B to XL (ablation)UniVG · T2I and editingbenchmarksImproved
add unified multi-task training vs task-specific SD3UniVG vs SD3 · GenEvalGenEval score: 0.71 -> 0.70No 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