Research map / Image generation / Text-to-image diffusion
Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing
Vadim Titov, Madina Khalmatova, Alexandra Ivanova, Dmitry P Vetrov, Aibek Alanov
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 Guide-and-Rescale instead of PnP | real image editing · Editing benchmark | LPIPS: 0.366 -> 0.228 | Improved |
| use Guide-and-Rescale instead of PnP | real image editing · Editing benchmark | Time (s): 197.0 -> 24.26 | Improved |
| use Guide-and-Rescale instead of EDICT | real image editing · Editing benchmark | CLIP: 0.229 -> 0.243 | Improved |
| use Guide-and-Rescale instead of P2P + NPI Prox | real image editing · Editing benchmark | LPIPS: 0.170 -> 0.228 | Hurt |
| use Guide-and-Rescale instead of baselines on dog-to-cat | real image editing · Dog-to-cat (AFHQ) | FID: 39.55 -> 39.07 | Improved |
| add self-attention and feature guiders to naive CFG editing (ablation) | Guide-and-Rescale · qualitative editing examples | preservation of structure | Improved |
| add noise rescaling in range instead of none or fixed (ablation) | Guide-and-Rescale · qualitative editing examples | editing quality | Improved |
| use guide-and-rescale instead of P2P + NPI Prox in user study | real image editing · User study Q1 editing | % preferring ours: 50 % | No 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.
- EDICT — EDICT: Exact Diffusion Inversion via Coupled Transformations (CVPR 2023) · better on 3 of 4 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
- Inversion-Free Image Editing with Language-Guided Diffusion Models (CVPR 2024 · similarity 0.90)
- High-Fidelity Diffusion-Based Image Editing (AAAI 2024 · similarity 0.90)
- AutoEdit: Automatic Hyperparameter Tuning for Image Editing (NeurIPS 2025 · similarity 0.89)
- Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators (ICLR 2024 · similarity 0.89)
- PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code (ICLR 2024 · similarity 0.89)
- EditInfinity: Image Editing with Binary-Quantized Generative Models (NeurIPS 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.
