Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks
This work addresses the problem of slow mask generation in diffusion-based image editing for users of text-to-image models, offering a significant speed improvement but is incremental as it builds on existing attention mechanisms.
The paper tackles the inefficiency of obtaining semantic masks for diffusion-based image editing by proposing InstDiffEdit, which uses cross-modal attention to generate instant masks automatically, achieving up to 6 times faster inference speed while outperforming state-of-the-art methods in image quality and editing results.
Diffusion-based Image Editing (DIE) is an emerging research hot-spot, which often applies a semantic mask to control the target area for diffusion-based editing. However, most existing solutions obtain these masks via manual operations or off-line processing, greatly reducing their efficiency. In this paper, we propose a novel and efficient image editing method for Text-to-Image (T2I) diffusion models, termed Instant Diffusion Editing(InstDiffEdit). In particular, InstDiffEdit aims to employ the cross-modal attention ability of existing diffusion models to achieve instant mask guidance during the diffusion steps. To reduce the noise of attention maps and realize the full automatics, we equip InstDiffEdit with a training-free refinement scheme to adaptively aggregate the attention distributions for the automatic yet accurate mask generation. Meanwhile, to supplement the existing evaluations of DIE, we propose a new benchmark called Editing-Mask to examine the mask accuracy and local editing ability of existing methods. To validate InstDiffEdit, we also conduct extensive experiments on ImageNet and Imagen, and compare it with a bunch of the SOTA methods. The experimental results show that InstDiffEdit not only outperforms the SOTA methods in both image quality and editing results, but also has a much faster inference speed, i.e., +5 to +6 times.