Research map / Image generation / Editing and style transfer
ArtEditor: Learning Customized Instructional Image Editor from Few-Shot Examples
Shijie Huang, Yiren Song, Yuxuan Zhang, Hailong Guo, Xueyin Wang, Jiaming Liu
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 position encoding cloning (ablation) | ArtEditor · Customized image editing (Pexels 50 images) | GPT Score: 59.748 -> 63.207 | Improved |
| add position encoding cloning (ablation) | ArtEditor · Customized image editing (Pexels 50 images) | CLIPimg: 0.746 -> 0.854 | Improved |
| add position encoding cloning (ablation) | ArtEditor · Customized image editing (Pexels 50 images) | CLIP Score: 0.259 -> 0.279 | Improved |
| add noise-free conditioning (ablation) | ArtEditor · Customized image editing (Pexels 50 images) | GPT Score: 38.438 -> 63.207 | Improved |
| add noise-free conditioning (ablation) | ArtEditor · Customized image editing (Pexels 50 images) | CLIPimg: 0.727 -> 0.854 | Improved |
| add noise-free conditioning (ablation) | ArtEditor · Customized image editing (Pexels 50 images) | CLIP Score: 0.251 -> 0.279 | Improved |
| add ArtEditor-Base large-scale pre-training before LoRA (ablation) | ArtEditor-LoRA · Customized editing (qualitative, Fig. 6) | visual harmony and text following | Improved |
| add ArtEditor-LoRA style adaptation on top of Base (ablation) | ArtEditor-Base · Customized editing (qualitative, Fig. 6) | degree of stylization | Improved |
| ArtEditor-Base vs Instruct-Pix2Pix on general editing | ArtEditor-Base · General image editing (HQ-Edit) | GPT Score: 38.201 -> 51.159 | Improved |
| ArtEditor vs OmniGen on customized editing | ArtEditor · Customized image editing (Pexels 50 images) | GPT Score: 50.684 -> 63.207 | 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.
- Instruct-Pix2Pix — InstructPix2Pix: Learning To Follow Image Editing Instructions (CVPR 2023) · better on 6 of 6 shared results
- OmniGen — OmniGen: Unified Image Generation (CVPR 2025) · better on 3 of 3 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
- UltraEdit: Instruction-based Fine-Grained Image Editing at Scale (NeurIPS 2024 · similarity 0.88)
- Learning to Manipulate Artistic Images (AAAI 2024 · similarity 0.88)
- InsightEdit: Towards Better Instruction Following for Image Editing (CVPR 2025 · similarity 0.88)
- Zero-shot Image Editing with Reference Imitation (NeurIPS 2024 · similarity 0.88)
- AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea (CVPR 2025 · similarity 0.87)
- Paint by Inpaint: Learning to Add Image Objects by Removing Them First (CVPR 2025 · 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.
