AI Paper Atlas

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

Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation

Tianyi Wei, Dongdong Chen, Yifan Zhou, Xingang Pan

TPAMI 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 13 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 block alignment loss (ablation)MMDiT latent optimization (SD3) · three similar subjectsSR (Grounding DINO): +8.3%Improved
add overlap loss (ablation)MMDiT latent optimization (SD3) · three similar subjectsSR (Grounding DINO): +8.6%Improved
add text encoder alignment loss to form L_amb (ablation)MMDiT latent optimization (SD3) · three similar subjectsSR (Grounding DINO): 57.3%Improved
add overlap online detection and back-to-start sampling (ablation)L_amb (SD3) · three similar subjectsSR (Grounding DINO): 57.3% -> 66.7%Improved
add reject sampling (ablation)SD3 with L_amb + L_res · three similar subjectsSR (Grounding DINO): 66.7% -> 67.8%Improved
add reject sampling (ablation)SD3 with L_amb + L_res · four similar subjectsSR (Grounding DINO): 52.7% -> 60.8%Improved
add reject sampling (ablation)SD3 with L_amb + L_res · two similar subjectsSR (Grounding DINO): 68.8% -> 68.8%No clear effect
reverse block alignment constraint (later blocks constrained to earlier) (ablation)block alignment loss · similar subjectsgeneration qualityHurt
use our method instead of CONFORMSD3 Medium · four similar subjectsSR (Grounding DINO): 43.7% -> 68.7% (GPT-4o)Improved
apply method on SD3.5 instead of SD3SD3.5 Medium · four similar subjectsSR (Grounding DINO): 26.2% -> 65.9%Improved
add back-to-start samplingL_amb · two similar subjectssampling time: about 68.7 seconds; triggered 0.4%, 29.3%, 42.1%Mixed

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