AI Paper Atlas

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

Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation

Dian Xie, Shitong Shao, Lichen Bai, zikai zhou, Bojun Cheng, Shuo Yang, WU JUN, Zeke Xie

ICLR 2026 · Image generation › Text-to-image diffusion · approach: Inference-time T2I improvement · 1 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
raise the CFG scale to the effective scale matched to the method (e-CFG)CFG · GenEvaloverall score (%): 55.84% -> 59.57%Improved
apply Transcendent Diffusion Guidance on top of CFGCFG · GenEvaloverall score (%): 55.84% -> 58.29%Improved
replace TDG with CFG at TDG's effective scaleTDG · GenEvaloverall score (%): 58.29% -> 57.23%No clear effect
replace FreeU with CFG at FreeU's effective scaleFreeU · GenEvaloverall score (%): 54.22% -> 58.47%Improved
replace APG with CFG at APG's effective scaleAPG · GenEvaloverall score (%): 55.95% -> 59.57%Improved
replace Z-Sampling with CFG at its effective scaleZ-Sampling · HPDaverage winning rate vs CFG (%): 70% -> 62%Hurt
replace CFG++ with CFG at its effective scaleCFG++ · HPDaverage winning rate vs CFG (%): 61% -> 53%Hurt
replace TDG with CFG at its effective scaleTDG · HPDaverage winning rate vs CFG (%): 56% -> 48%Hurt
replace Z-Sampling with CFG at its effective scale on HPS v2Z-Sampling · Pick-a-PicHPS v2 winning rate: 90% -> 74%Hurt
replace Z-Sampling with CFG at its effective scale on SD-2.1Z-Sampling · Pick-a-Pic (SD-2.1)HPS v2 winning rate: 90% -> 60%Hurt
increase CFG scale from 5.5 to 20 (ablation)CFG · Pick-a-Pic (SD-XL)HPS v2Improved
increase CFG scale (ablation)CFG · Pick-a-Pic (SD-XL)AESNo clear effect

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