SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing Workflow
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912653286309888 |
|---|---|
| author | Tang, Kenan Li, Yanhong Qin, Yao |
| author_facet | Tang, Kenan Li, Yanhong Qin, Yao |
| contents | Prompt-based models have demonstrated impressive prompt-following capability at image editing tasks. However, the models still struggle with following detailed editing prompts or performing local edits. Specifically, global image quality often deteriorates immediately after a single editing step. To address these challenges, we introduce SPICE, a training-free workflow that accepts arbitrary resolutions and aspect ratios, accurately follows user requirements, and consistently improves image quality during more than 100 editing steps, while keeping the unedited regions intact. By synergizing the strengths of a base diffusion model and a Canny edge ControlNet model, SPICE robustly handles free-form editing instructions from the user. On a challenging realistic image-editing dataset, SPICE quantitatively outperforms state-of-the-art baselines and is consistently preferred by human annotators. We release the workflow implementation for popular diffusion model Web UIs to support further research and artistic exploration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_09697 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing Workflow Tang, Kenan Li, Yanhong Qin, Yao Graphics Computer Vision and Pattern Recognition Machine Learning Prompt-based models have demonstrated impressive prompt-following capability at image editing tasks. However, the models still struggle with following detailed editing prompts or performing local edits. Specifically, global image quality often deteriorates immediately after a single editing step. To address these challenges, we introduce SPICE, a training-free workflow that accepts arbitrary resolutions and aspect ratios, accurately follows user requirements, and consistently improves image quality during more than 100 editing steps, while keeping the unedited regions intact. By synergizing the strengths of a base diffusion model and a Canny edge ControlNet model, SPICE robustly handles free-form editing instructions from the user. On a challenging realistic image-editing dataset, SPICE quantitatively outperforms state-of-the-art baselines and is consistently preferred by human annotators. We release the workflow implementation for popular diffusion model Web UIs to support further research and artistic exploration. |
| title | SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing Workflow |
| topic | Graphics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2504.09697 |