Research map / Image generation / Editing and style transfer
InstructGIE: Towards Generalizable Image Editing
Zichong Meng, Changdi Yang, Jun Liu, Hao Tang, Pu Zhao, Yanzhi 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 |
|---|---|---|---|
| add VMamba-based reformed conditioned latent diffusion model (ablation) | InstructGIE · InstructGIE synthetic test set | FID: 10.15 -> 7.57 | Improved |
| add VMamba-based reformed conditioned latent diffusion model (ablation) | InstructGIE · InstructGIE synthetic test set | CLIP DirSim: 0.13 -> 0.27 | Improved |
| add editing-shift matching loss (ablation) | InstructGIE · InstructGIE synthetic test set | FID: 9.23 -> 7.57 | Improved |
| add editing-shift matching loss (ablation) | InstructGIE · InstructGIE synthetic test set | CLIP DirSim: 0.15 -> 0.27 | Improved |
| add language instruction unification via frozen LLM (ablation) | InstructGIE · InstructGIE synthetic test set | FID: 10.37 -> 7.57 | Improved |
| add language instruction unification via frozen LLM (ablation) | InstructGIE · InstructGIE synthetic test set | CLIP DirSim: 0.23 -> 0.27 | Improved |
| add selective area matching loss (ablation) | InstructGIE · InstructGIE synthetic test set | FID: 11.31 -> 7.57 | Improved |
| add selective area matching loss (ablation) | InstructGIE · InstructGIE synthetic test set | CLIP DirSim: 0.19 -> 0.27 | Improved |
| use InstructGIE instead of PromptDiffusion | visual-prompt image editing · InstructGIE synthetic test set | FID: 13.75 -> 7.57 | Improved |
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.
- InstructPix2Pix — InstructPix2Pix: Learning To Follow Image Editing Instructions (CVPR 2023) · better on 2 of 2 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
- FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model (CVPR 2025 · similarity 0.89)
- Instruct-CLIP: Improving Instruction-Guided Image Editing with Automated Data Refinement Using Contrastive Learning (CVPR 2025 · similarity 0.88)
- OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision (ICLR 2025 · similarity 0.88)
- RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers (NeurIPS 2025 · similarity 0.88)
- Learning Where to Edit Vision Transformers (NeurIPS 2024 · similarity 0.88)
- ImgEdit: A Unified Image Editing Dataset and Benchmark (NeurIPS 2025 · similarity 0.88)
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.
