Research map / Image generation / Text-to-image diffusion
One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations
Yiming Zhu, Hongyu Liu, Yibing Song, Ziyang Yuan, Xintong Han, Chun Yuan, Qifeng Chen, Jue 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 scale parameter in semantic alignment (ablation) | FFCLIP · CelebA-HQ Aged 10 | age distance: 13.9412 -> 9.8874 | Improved |
| add translation parameter in semantic alignment (ablation) | FFCLIP · CelebA-HQ Aged 10 | age distance: 20.0762 -> 9.8874 | Improved |
| add scale parameter (ablation) | FFCLIP · CelebA-HQ Bald | hair pixel count: 0.0630 -> 0.0279 | Improved |
| add scale parameter (ablation) | FFCLIP · CelebA-HQ Red hair | hair color difference: 0.7082 -> 0.7171 | Hurt |
| use 4 modulation blocks instead of 0 (ablation) | FFCLIP · CelebA-HQ Bald | hair pixel count: 0.2689 -> 0.0279 | Improved |
| increase modulation blocks from 4 to 6 (ablation) | FFCLIP · CelebA-HQ | editing metrics: Bald 0.0279 -> 0.0236; Angry 0.5810 -> 0.7380 | Mixed |
| increase modulation blocks from 4 to 10 (ablation) | FFCLIP · CelebA-HQ Bald | hair pixel count: 0.0279 -> 0.1720 | Hurt |
| use 4 blocks instead of 2 (ablation) | FFCLIP · CelebA-HQ Aged 10 | age distance: 18.5182 -> 9.8874 | Improved |
| use FFCLIP instead of StyleCLIP | FFCLIP vs StyleCLIP · CelebA-HQ Aged 10 | age distance: 17.0053 -> 9.8874 | Improved |
| use FFCLIP instead of StyleCLIP in human voting | FFCLIP vs StyleCLIP · CelebA-HQ Bald | human vote share (%): 8.6 -> 85.7 | 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.
- TediGAN — TediGAN: Text-Guided Diverse Face Image Generation and Manipulation (CVPR 2021) · better on 7 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
- Prompt Augmentation for Self-supervised Text-guided Image Manipulation (CVPR 2024 · similarity 0.87)
- Textualize Visual Prompt for Image Editing via Diffusion Bridge (AAAI 2025 · similarity 0.86)
- Text-Vision Co-Instructed Image Editing (NeurIPS 2026 · similarity 0.86)
- Text-Driven Image Editing via Learnable Regions (CVPR 2024 · similarity 0.85)
- SmartCLIP: Modular Vision-language Alignment with Identification Guarantees (CVPR 2025 · similarity 0.85)
- An Item Is Worth a Prompt: Versatile Image Editing with Disentangled Control (AAAI 2025 · similarity 0.85)
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.
