无需微调，可直接编辑任意分辨率图像的扩散模型方法
EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model
- 通过分块反演保留高分辨图像原貌
- 在1024×1024以上分辨率实现自然编辑结果
- 适合希望快速部署高分图像编辑的开发者
我们提出EditCrafter，一种无需微调的高分辨率图像编辑方法，利用预训练文本到图像（T2I）扩散模型处理远超训练分辨率（512×512或1024×1024）的图像。现有基于扩散模型的编辑方法难以适配任意长宽比或更高分辨率图像，因仅支持训练时的固定分辨率。简单分块编辑会引发结构失真与重复。为此，我们设计了EditCrafter：首先进行分块反演以保留输入高分辨率图像的原始身份；进一步提出噪声抑制的流形约束无分类器引导（NDCFG++），用于从反演潜在空间中进行编辑。实验表明，该方法可在不进行微调或优化的情况下，在多种分辨率上实现出色的编辑效果。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。