AI Paper Atlas

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

InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting

Duc Vu, Kien Nguyen, Trong-Tung Nguyen, Ngan Nguyen, Phong Nguyen, Khoi Nguyen, Cuong Pham, Anh Tran

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 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 InverFill inversion noiseSANA-Sprint 0.6B (2 NFEs) blended sampling · BrushBenchImageReward x10: 10.73 -> 11.76Improved
add InverFill inversion noiseSANA-Sprint 0.6B (2 NFEs) blended sampling · MagicBrushImageReward x10: 2.65 -> 3.07Improved
add InverFill inversion noiseSDXL Turbo (4 NFEs) blended sampling · BrushBenchCLIP similarity: 27.21 -> 27.74Improved
add InverFill to the specialized BrushNet pipelineSDXL Turbo + BrushNet · BrushBenchImageReward x10: 12.30 -> 12.34Improved
add InverFill to the specialized BrushNet pipelineSDXL Turbo + BrushNet · MagicBrushImageReward x10: 4.31 -> 4.31No clear effect
add Re-Blending (ablation)InverFill on SANA-Sprint 0.6B · BrushBench (SANA-Sprint 0.6B, 2 NFEs)ImageReward x10: 7.93 -> 11.22Improved
add Gaussian regularization (ablation)InverFill on SANA-Sprint 0.6B · BrushBench (SANA-Sprint 0.6B, 2 NFEs)ImageReward x10: 11.22 -> 11.51Improved
add LADD adversarial loss (ablation)InverFill on SANA-Sprint 0.6B · BrushBench (SANA-Sprint 0.6B, 2 NFEs)ImageReward x10: 11.51 -> 11.76Improved
add Re-Blending (ablation)InverFill on SDXL-Turbo · BrushBench (SDXL-Turbo, 4 NFEs)ImageReward x10: 10.60 -> 11.29Improved
add Gaussian regularization (ablation)InverFill on SDXL-Turbo · BrushBench (SDXL-Turbo, 4 NFEs)ImageReward x10: 11.29 -> 12.10Improved
replace SDS regularization with Gaussian moment-matching loss (ablation)InverFill on SANA-Sprint 0.6B · BrushBench (SANA-Sprint 0.6B, 2 NFEs)ImageReward x10: 11.29 -> 11.51Improved
replace 50-step DDIM inversion (with blending) by one-step InverFill (ablation)SDXL-Turbo blended sampling · BrushBench (SDXL-Turbo, 4 NFEs)ImageReward x10: 12.07 -> 12.34Improved

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