Research map / Image generation / Editing and style transfer
Training-Free Text-Guided Image Editing with Visual Autoregressive Model
Yufei Wang, Lanqing Guo, Zhihao Li, Jiaxing Huang, Pichao Wang, Bihan Wen, Jian Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use VAR-based AREdit instead of RF-Inversion | AREdit · 1K image editing efficiency | editing time: 27s (13.5s) -> 2.5s (1.2s) | Improved |
| use VAR-based AREdit instead of LEdits++ | AREdit · 1K image editing efficiency | editing time: 19s (12s) -> 2.5s (1.2s) | Improved |
| AREdit versus PnP-DirInv. on background preservation | AREdit · PIE-Bench | PSNR: 22.46 -> 24.19 | Improved |
| AREdit versus MasaCtrl on LPIPS | AREdit · PIE-Bench | LPIPS: 0.1066 -> 0.0870 | Improved |
| AREdit versus PnP-DirInv. on structure distance | AREdit · PIE-Bench | Structure Distance: 0.0243 -> 0.0305 | Hurt |
| AREdit versus LEdits++ on CLIP edited similarity | AREdit · PIE-Bench | CLIP Similarity (edited): 23.37 -> 22.77 | Hurt |
| add channel-dimension fine-grained mask instead of spatial-only mask (ablation) | AREdit · PIE-Bench (qualitative) | fidelity | Improved |
| add attention control (ablation) | AREdit · PIE-Bench (qualitative) | editing quality on large-area changes | Improved |
| increase gamma (reuse more cached low-frequency steps) (ablation) | AREdit · PIE-Bench (qualitative) | fidelity vs generative diversity | Mixed |
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.
- LEDits++ — LEDITS++: Limitless Image Editing using Text-to-Image Models (CVPR 2024) · better on 5 of 7 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
- EditInfinity: Image Editing with Binary-Quantized Generative Models (NeurIPS 2025 · similarity 0.90)
- NEP: Autoregressive Image Editing via Next Editing Token Prediction (NeurIPS 2025 · similarity 0.90)
- The Promise of RL for Autoregressive Image Editing (NeurIPS 2025 · similarity 0.90)
- Inversion-Free Image Editing with Language-Guided Diffusion Models (CVPR 2024 · similarity 0.89)
- Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models (NeurIPS 2026 · similarity 0.89)
- SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusion (CVPR 2025 · similarity 0.89)
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.
