AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

InstaEdit: Instant Image Editing via Optimized Noise Prediction

Ning Ma, Yangrui Shao

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Accelerating autoregressive image generation · 0 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 reparameterization module (ablation)InstaEdit · GEdit-Bench (English)overall: 5.35 -> 5.67Improved
add singular value prediction module (ablation)InstaEdit · GEdit-Bench (English)overall: 5.27 -> 5.67Improved
add noise regularization loss L_reg (ablation)InstaEdit · GEdit-Bench (English)overall: 5.48 -> 5.67Improved
add Stage II LoRA fine-tuning of foundation model (ablation)InstaEdit · GEdit-Bench (English)overall: 5.51 -> 5.67Improved
add InstaEdit with 4 steps vs 8-step baselineFLUX.1-Kontext · GEdit-Bench (English)overall: 5.21 -> 5.67Improved
add InstaEdit with 4 steps vs 8-step baselineFLUX.2-klein-base-9B · ImgEdit-Benchoverall: 6.81 -> 7.47Improved
InstaEdit 4 steps vs FlowFast 10 stepsFLUX.1-Kontext · GEdit-Bench (English)overall: 5.45 -> 5.67Improved
InstaEdit vs LCM at 4 stepsFLUX.1-Kontext · GEdit-Bench (English) (4-step)overall: 5.23 -> 5.67Improved
InstaEdit 4 steps vs 30-step Step1X-EditStep1X-Edit · GEdit-Bench (English)overall: 6.79 -> 6.84No clear effect
InstaEdit 4 steps vs 30-step FLUX.2-klein-base-4BFLUX.2-klein-base-4B · GEdit-Bench (English)speedup: 2.57×Mixed
add InstaEdit with 3 steps on distilled modelFLUX.2-klein-9B · GEdit-Bench (distilled)overall: 7.36 -> 7.35No clear effect
InstaEdit 8 steps vs LCM 8 stepsFLUX.1-Kontext · GEdit-Bench (English) (8-step)overall: 5.60 -> 5.75Improved

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