EditCrafter：基于预训练扩散模型的无调优高分辨率图像编辑
EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model
AI总结：
本文提出EditCrafter，利用预训练文本到图像扩散模型实现无需调优的高分辨率图像编辑，解决了传统方法在处理任意宽高比和高分辨率图像时的局限性。
摘要：
我们提出EditCrafter，一种无需调优的高分辨率图像编辑方法，利用预训练的文本到图像（T2I）扩散模型处理远超训练时使用的分辨率的图像。利用大规模T2I扩散模型的生成先验，可以开发出广泛的新生成和编辑应用。尽管已有许多基于扩散模型的图像编辑方法，但它们难以应用于任意宽高比或更高分辨率的图像，因为它们仅在训练分辨率（512x512或1024x1024）下工作。简单地应用基于补丁的编辑会导致不真实的物体结构和重复。为了解决这些挑战，我们引入了EditCrafter，一个简单而有效的编辑流程。EditCrafter首先执行拼图反转，以保留输入高分辨率图像的原始身份。我们进一步提出了一种针对从反转潜在空间中进行高分辨率图像编辑的噪声阻尼流形约束分类器自由引导（NDCFG++）。我们的实验表明，EditCrafter可以在各种分辨率下实现令人印象深刻的结果，而无需微调和优化。
英文摘要：
We propose EditCrafter, a high-resolution image editing method that operates without tuning, leveraging pretrained text-to-image (T2I) diffusion models to process images at resolutions significantly exceeding those used during training. Leveraging the generative priors of large-scale T2I diffusion models enables the development of a wide array of novel generation and editing applications. Although numerous image editing methods have been proposed based on diffusion models and exhibit high-quality editing results, they are difficult to apply to images with arbitrary aspect ratios or higher resolutions since they only work at the training resolutions (512x512 or 1024x1024). Naively applying patch-wise editing fails with unrealistic object structures and repetition. To address these challenges, we introduce EditCrafter, a simple yet effective editing pipeline. EditCrafter operates by first performing tiled inversion, which preserves the original identity of the input high-resolution image. We further propose a noise-damped manifold-constrained classifier-free guidance (NDCFG++) that is tailored for high resolution image editing from the inverted latent. Our experiments show that the our EditCrafter can achieve impressive editing results across various resolutions without fine-tuning and optimization.
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。
