Research map / Image generation / Editing and style transfer
EDICT: Exact Diffusion Inversion via Coupled Transformations
Bram Wallace, Akash Gokul, Nikhil Naik
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 coupled transformations with two alternating noise vectors instead of DDIM inversion | Stable Diffusion 1.4 · MS-COCO-2017 validation, 50 steps, unconditional reconstruction | MSE: 0.030083 -> 0.015260 | Improved |
| Use coupled transformations with two alternating noise vectors instead of DDIM inversion | Stable Diffusion 1.4 · MS-COCO-2017 validation, 50 steps, conditional reconstruction | MSE: 0.418175 -> 0.015260 | Improved |
| Use coupled transformations with two alternating noise vectors instead of DDIM inversion | Stable Diffusion 1.4 · MS-COCO-2017 validation, 200 steps, unconditional reconstruction | MSE: 0.023406 -> 0.015260 | Improved |
| Use coupled transformations with two alternating noise vectors instead of DDIM inversion | Stable Diffusion 1.4 · MS-COCO-2017 validation, 200 steps, conditional reconstruction | MSE: 0.496944 -> 0.015260 | Improved |
| Use coupled transformations with two alternating noise vectors instead of DDIM inversion | Stable Diffusion 1.4 · MS-COCO-2017 validation, 1000 steps, unconditional reconstruction | MSE: 0.018960 -> 0.015260 | Improved |
| Use coupled transformations with two alternating noise vectors instead of DDIM inversion | Stable Diffusion 1.4 · MS-COCO-2017 validation, 1000 steps, conditional reconstruction | MSE: 0.509345 -> 0.015260 | Improved |
| Add intermediate mixing layers rather than use coupling without mixing (ablation) | EDICT · Text-conditioned image generation | image quality and composition | Improved |
| Use no intermediate mixing layers (ablation) | EDICT · Text-conditioned image generation | image quality and composition | Hurt |
| Set the mixing coefficient too high, such as p=0.97 (ablation) | EDICT · 50-step generation and inversion | latent alignment | Mixed |
| Set the mixing coefficient too low (ablation) | EDICT · 50-step inversion | latent alignment | Hurt |
| Increase the number of baseline editing steps from 50 to 100 or 250 (ablation) | DDIM and other baseline editing methods · Image editing | visual edit quality | No clear effect |
Later papers that compared with this method
5 later accepted papers report EDICT as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- Jumping the Landing Phase: Noise Variance Matching Enables Accurate Few-Step Inversion (ECCV 2026 · better on 5 of 5 shared results)
- Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing (ECCV 2024 · better on 3 of 4 shared results)
- DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation (CVPR 2024 · better on 3 of 3 shared results)
- An Edit Friendly DDPM Noise Space: Inversion and Manipulations (CVPR 2024 · better on 1 of 1 shared result)
- TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing (CVPR 2024 · better on 1 of 1 shared result)
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 0.92)
- Exploring Fixed Point in Image Editing: Theoretical Support and Convergence Optimization (NeurIPS 2024 · similarity 0.91)
- Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models (ICLR 2025 · similarity 0.91)
- High-Fidelity Diffusion-Based Image Editing (AAAI 2024 · similarity 0.91)
- DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editing (NeurIPS 2025 · similarity 0.90)
- A Variational Perspective on Solving Inverse Problems with Diffusion Models (ICLR 2024 · similarity 0.90)
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.
