Research map / Image generation / Text-to-image diffusion
LUSD: Localized Update Score Distillation for Text-Guided Image Editing
Worameth Chinchuthakun, Tossaporn Saengja, Nontawat Tritrong, Pitchaporn Rewatbowornwong, Pramook Khungurn, Supasorn Suwajanakorn
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 |
|---|---|---|---|
| add attention-based spatial regularization (ablation) | LUSD · MagicBrush test | CLIP-T: 0.277 -> 0.287 | Improved |
| add attention-based spatial regularization (ablation) | LUSD · MagicBrush test | L1*: 0.057 -> 0.015 | Improved |
| add gradient normalization (ablation) | LUSD · MagicBrush test | CLIP-T: 0.268 -> 0.287 | Improved |
| add gradient normalization (ablation) | LUSD · MagicBrush test | CLIP-AUC: 0.017 -> 0.074 | Improved |
| add gradient normalization (ablation) | LUSD · MagicBrush test | L1*: 0.013 -> 0.015 | Hurt |
| add annealing of gamma (ablation) | LUSD · MagicBrush test | CLIP-T: 0.265 -> 0.287 | Improved |
| add annealing of gamma (ablation) | LUSD · MagicBrush test | CLIP-AUC: 0.025 -> 0.074 | Improved |
| add gradient filtering (ablation) | LUSD · MagicBrush test | CLIP-T: 0.279 -> 0.287 | Improved |
| add gradient filtering (ablation) | LUSD · MagicBrush test | CLIP-AUC: 0.053 -> 0.074 | Improved |
| add moving average to attention masks (ablation) | LUSD · MagicBrush test | CLIP-AUC: 0.071 -> 0.074 | Improved |
| use LUSD instead of SBP | SBP · MagicBrush test | CLIP-AUC: 0.068 -> 0.074 | Improved |
| use LUSD instead of DDS on object insertion only | DDS · MagicBrush test (object insertion subset) | CLIP-AUC: 0.043 -> 0.080 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- HIVE — HIVE: Harnessing Human Feedback for Instructional Visual Editing (CVPR 2024) · better on 4 of 4 shared results
- LEDITS++ — LEDITS++: Limitless Image Editing using Text-to-Image Models (CVPR 2024) · better on 4 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
- Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps (NeurIPS 2024 · similarity 0.89)
- Textualize Visual Prompt for Image Editing via Diffusion Bridge (AAAI 2025 · similarity 0.88)
- Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation (ICLR 2025 · similarity 0.88)
- Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation (ICLR 2024 · similarity 0.88)
- An Item Is Worth a Prompt: Versatile Image Editing with Disentangled Control (AAAI 2025 · similarity 0.88)
- Prompt Augmentation for Self-supervised Text-guided Image Manipulation (CVPR 2024 · similarity 0.87)
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.
