SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914527551946752 |
|---|---|
| author | Yan, Zhengan Zheng, Shikang Qin, Haoran Tu, Xiaobing Wang, Yinggui Liu, Jiacheng Ren, Jiaxuan Lin, Yuqi Cai, Peiliang Ren, Jinkui Zhang, Xiantao Zhang, Linfeng |
| author_facet | Yan, Zhengan Zheng, Shikang Qin, Haoran Tu, Xiaobing Wang, Yinggui Liu, Jiacheng Ren, Jiaxuan Lin, Yuqi Cai, Peiliang Ren, Jinkui Zhang, Xiantao Zhang, Linfeng |
| contents | Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising over all spatial tokens. Dynamic-resolution sampling reduces this cost by performing early steps at reduced resolution. However, existing approaches prioritize upsampling using low-level heuristics such as edge detection or channel variance, which are weakly aligned with editing semantics and may lead to structural inconsistency. Moreover, spatial regions are often upsampled without verifying whether semantic modification is actually required, resulting in redundant high-resolution computation and accumulated errors. Therefore, we propose SpecEdit, a training-free dynamic-resolution framework tailored for diffusion-based image editing. SpecEdit follows a draft-and-verify scheme: a low-resolution draft first estimates the semantic outcome, after which token-level discrepancies are used to identify edit-relevant tokens for high-resolution denoising, while the remaining tokens stay at a coarse resolution. Experiments on Qwen-Image-Edit and FLUX.1-Kontext-dev demonstrate up to 10x and 7x acceleration, while maintaining strong quality. SpecEdit is complementary to step distillation and other acceleration techniques, achieving up to 13x speedup when combined with existing methods. Our code is in supplementary material and will be released on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02152 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking Yan, Zhengan Zheng, Shikang Qin, Haoran Tu, Xiaobing Wang, Yinggui Liu, Jiacheng Ren, Jiaxuan Lin, Yuqi Cai, Peiliang Ren, Jinkui Zhang, Xiantao Zhang, Linfeng Computer Vision and Pattern Recognition Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising over all spatial tokens. Dynamic-resolution sampling reduces this cost by performing early steps at reduced resolution. However, existing approaches prioritize upsampling using low-level heuristics such as edge detection or channel variance, which are weakly aligned with editing semantics and may lead to structural inconsistency. Moreover, spatial regions are often upsampled without verifying whether semantic modification is actually required, resulting in redundant high-resolution computation and accumulated errors. Therefore, we propose SpecEdit, a training-free dynamic-resolution framework tailored for diffusion-based image editing. SpecEdit follows a draft-and-verify scheme: a low-resolution draft first estimates the semantic outcome, after which token-level discrepancies are used to identify edit-relevant tokens for high-resolution denoising, while the remaining tokens stay at a coarse resolution. Experiments on Qwen-Image-Edit and FLUX.1-Kontext-dev demonstrate up to 10x and 7x acceleration, while maintaining strong quality. SpecEdit is complementary to step distillation and other acceleration techniques, achieving up to 13x speedup when combined with existing methods. Our code is in supplementary material and will be released on GitHub. |
| title | SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.02152 |