Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models
This addresses the computational bottleneck for users of text-guided diffusion models in image editing, offering a significant speedup while maintaining quality.
The paper tackles the slow optimization time in diffusion-based image editing by proposing negative-prompt inversion, which achieves comparable reconstruction fidelity solely through forward propagation, enabling inversion at 512 pixels in about 5 seconds—over 30 times faster than null-text inversion.
In image editing employing diffusion models, it is crucial to preserve the reconstruction fidelity to the original image while changing its style. Although existing methods ensure reconstruction fidelity through optimization, a drawback of these is the significant amount of time required for optimization. In this paper, we propose negative-prompt inversion, a method capable of achieving equivalent reconstruction solely through forward propagation without optimization, thereby enabling ultrafast editing processes. We experimentally demonstrate that the reconstruction fidelity of our method is comparable to that of existing methods, allowing for inversion at a resolution of 512 pixels and with 50 sampling steps within approximately 5 seconds, which is more than 30 times faster than null-text inversion. Reduction of the computation time by the proposed method further allows us to use a larger number of sampling steps in diffusion models to improve the reconstruction fidelity with a moderate increase in computation time.