arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2504.09697cs.GRcs.CVcs.LG
收藏

SPICE:一种协同、精确、迭代且可定制的图像编辑工作流

SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing Workflow

University of California, Santa Barbara(加州大学圣芭芭拉分校)

Kenan Tang, Yanhong Li, Yao Qin

AI总结:

SPICE是一种无需训练的协同工作流,结合扩散模型与Canny边缘ControlNet,支持任意分辨率、准确遵循指令,并在百步编辑中持续提升质量,优于现有基线。

摘要:

基于提示的模型在图像编辑任务中展现了令人印象深刻的提示遵循能力。然而,这些模型在遵循详细编辑提示或执行局部编辑时仍存在困难。具体而言,全局图像质量通常在单次编辑步骤后立即恶化。为应对这些挑战,我们引入了SPICE,一种无需训练的工作流,它接受任意分辨率和宽高比,准确遵循用户要求,并在超过100个编辑步骤中持续提升图像质量,同时保持未编辑区域不变。通过协同基础扩散模型和Canny边缘ControlNet模型的优势,SPICE稳健地处理用户的自由形式编辑指令。在一个具有挑战性的真实图像编辑数据集上,SPICE在定量上优于最先进的基线,并始终受到人类标注者的青睐。我们发布了该工作流在流行扩散模型Web UI上的实现,以支持进一步的研究和艺术探索。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑