AI Paper Atlas

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

TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning In Text-to-Image Models

Teng-Fang Hsiao, Bo-Kai Ruan, Yi-Lun Wu, Tzu-Ling Lin, Hong-Han Shuai

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 6 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
share contextual (text) tokens instead of concatenating reference vision tokensTF-TI2I · attention computecompute and memory: (2R-1) times vs ((R-1)+(n_P/n_I)R) timesImproved
add Reference Contextual Masking (RCM) to contextual token sharing (ablation)TF-TI2I · qualitative multi-reference examplereference fidelityImproved
add Winner-Takes-All (WTA) module (ablation)TF-TI2I · qualitative multi-reference exampledetail and color richnessImproved
use TF-TI2I instead of OmniGen on single-reference FG-TI2ITF-TI2I · FG-TI2I OBJ(text) x ACT(img)Image Reward: 0.85 -> 1.30Improved
TF-TI2I vs MasaCtrl on reference alignmentTF-TI2I · FG-TI2I OBJ(img) x TEX(text)DINO similarity: 96.4 -> 87.5Hurt
TF-TI2I vs Kosmos-G on DreamBench reference alignmentTF-TI2I · DreamBenchCLIP-Image: 84.7 -> 79.1Hurt
TF-TI2I vs best editing baseline on Wild-TI2ITF-TI2I · Wild-TI2ICLIP-Directional Score: 0.210 -> 0.115Hurt
TF-TI2I vs best editing baseline on Wild-TI2ITF-TI2I · Wild-TI2ICLIP-Text: 29.3 -> 30.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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