AI Paper Atlas

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

Analyzing and Improving Training-Free Fast Sampling of Text-to-Image Diffusion Models

Zhenyu Zhou, Defang Chen, Siwei Lyu, Chun Chen, Can Wang

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Inference-time T2I improvement · 3 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
use TORS schedule instead of uniform outer schedule at 10 stepsFlux.1-Dev · DrawBench (Flux.1-Dev)ImageReward: 0.71 -> 0.97Improved
use TORS schedule instead of uniform outer schedule at 10 stepsFlux.1-Dev · DrawBench (Flux.1-Dev)HPSv2: 27.70 -> 29.30Improved
use TORS schedule instead of uniform outer schedule at 10 stepsSD 3.5 medium · DrawBench (SD3.5 medium)ImageReward: 0.55 -> 0.86Improved
use TORS instead of GITS scheduleFlux.1-Dev · DrawBench (Flux.1-Dev)ImageReward: 0.90 -> 0.97Improved
add fast solvers DPM-Solver or UniPC (ablation)Flux.1-Dev 10 steps · DrawBench (Flux.1-Dev)ImageReward: 0.71 -> 0.78Improved
add feature caching with FORA (ablation)Flux.1-Dev 10 steps · DrawBench (Flux.1-Dev)ImageReward: 0.71 -> 0.71No clear effect
add TaylorSeers feature caching (ablation)SD 3.5 medium · DrawBench (SD3.5 medium)ImageReward: 0.55 -> 0.54No clear effect
use TORS 10 steps instead of uniform 10 stepsFlux.1-Dev · GenEval (Flux.1-Dev)overall: 0.57 -> 0.67Improved
apply Flux-derived TORS schedule to unseen Qwen-ImageQwen-Image · DrawBench (unseen model, N=10)HPSv2: 27.10 -> 29.28Improved
apply Flux-derived TORS schedule to Flux + Skin LoRAFlux + Skin LoRA · DrawBench (unseen model, N=10)HPSv2: 26.59 -> 28.24Improved
profile TORS statistics with 100 steps instead of 25 steps (ablation)TORS · DrawBench (Flux.1-Dev, schedule profiled with 25 steps)HPSv2: 28.23 -> 29.30Improved
vary the number of prompts used for profiling TORS from 25 to 100 (ablation)TORS · DrawBench (Flux.1-Dev)ImageReward: 0.96 -> 0.97No clear effect

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