论文标题
高分辨率图像通过多阶段混合扩散编辑
High-Resolution Image Editing via Multi-Stage Blended Diffusion
论文作者
论文摘要
扩散模型在图像生成和图像编辑中显示出很好的结果。但是，由于高分辨率生成的训练扩散模型的计算成本，目前的方法仅限于低分辨率。我们提出了一种使用预先训练的低分辨率扩散模型来编辑百万像素范围内图像的方法。我们首先使用混合扩散以低分辨率编辑图像，然后使用超分辨率模型和混合扩散在多个阶段将其详细介绍。使用我们的方法，我们实现了比仅将架子超分辨率方法应用于扩散模型的输出的更高的视觉保真度。与直接使用更高分辨率的扩散模型相比，我们还获得了更好的全局一致性。
Diffusion models have shown great results in image generation and in image editing. However, current approaches are limited to low resolutions due to the computational cost of training diffusion models for high-resolution generation. We propose an approach that uses a pre-trained low-resolution diffusion model to edit images in the megapixel range. We first use Blended Diffusion to edit the image at a low resolution, and then upscale it in multiple stages, using a super-resolution model and Blended Diffusion. Using our approach, we achieve higher visual fidelity than by only applying off the shelf super-resolution methods to the output of the diffusion model. We also obtain better global consistency than directly using the diffusion model at a higher resolution.
