AI Paper Atlas

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

Paragraph-to-Image Generation with Information-Enriched Diffusion Model

Weijia Wu, Zhuang Li, Yefei He, Mike Zheng Shou, Chunhua Shen, Lele Cheng, Yan Li, Tingting Gao, Di Zhang

IJCV 2025 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 38 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 LoRA adaptation of the Llama V2 text encoder (ablation)ParaDiffusion · ParaPrompts-400text faithfulness win rate: 53.4% win vs 44.5% loseImproved
increase LoRA rank from 8 to 64 (ablation)ParaDiffusion LoRA · ParaPrompts-400win rate: 50.6% -> 53.4%Improved
increase LoRA rank from 64 to 128 (ablation)ParaDiffusion LoRA · ParaPrompts-400win rate: 53.4% -> 51.9%Hurt
LoRA alpha 32 instead of 16 (r=64) (ablation)ParaDiffusion LoRA · ParaPrompts-400win rate: 52.3% -> 53.4%Improved
LoRA alpha 64 instead of 32 (r=64) (ablation)ParaDiffusion LoRA · ParaPrompts-400win rate: 53.4% -> 53.1%No clear effect
lengthen captions from 10 to 150 words (ParaImage-Big 500k) (ablation)ParaDiffusion · ParaPrompts-400text faithfulness voting: 8.5% -> 40.6%Improved
lengthen captions from 10 to 150 words (ParaImage-Small 3k) (ablation)ParaDiffusion · ParaPrompts-400text faithfulness voting: 16.4% -> 31.2%Improved
train on manually curated ParaImage-Small instead of LAION (ablation)ParaDiffusion · ParaPrompts-400visual appeal voting: 3.1% -> 54.7%Improved
train on LAION-Aesthetics instead of LAION (ablation)ParaDiffusion · ParaPrompts-400visual appeal voting: 3.1% -> 18.5%Improved
increase ParaImage-Big size from 0.3m to 3.3m (ablation)ParaDiffusion · MS-COCO 256x256FID-30K: 13.45 -> 9.64Improved
increase ParaImage-Big size from 0.3m to 3.3m (ablation)ParaDiffusion · ParaPrompts-400visual appeal voting: 17.1% -> 50.2%Improved
add Stage-2 training on ParaImage-Big (ablation)ParaDiffusion · ParaPrompts-400visual appeal win: 82.1 win vs 17.9 loseImproved

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