TweezeEdit: Consistent and Efficient Image Editing with Path Regularization
By: Jianda Mao , Kaibo Wang , Yang Xiang and more
Potential Business Impact:
Changes pictures perfectly with simple words.
Large-scale pre-trained diffusion models empower users to edit images through text guidance. However, existing methods often over-align with target prompts while inadequately preserving source image semantics. Such approaches generate target images explicitly or implicitly from the inversion noise of the source images, termed the inversion anchors. We identify this strategy as suboptimal for semantic preservation and inefficient due to elongated editing paths. We propose TweezeEdit, a tuning- and inversion-free framework for consistent and efficient image editing. Our method addresses these limitations by regularizing the entire denoising path rather than relying solely on the inversion anchors, ensuring source semantic retention and shortening editing paths. Guided by gradient-driven regularization, we efficiently inject target prompt semantics along a direct path using a consistency model. Extensive experiments demonstrate TweezeEdit's superior performance in semantic preservation and target alignment, outperforming existing methods. Remarkably, it requires only 12 steps (1.6 seconds per edit), underscoring its potential for real-time applications.
Similar Papers
3D-Consistent Multi-View Editing by Diffusion Guidance
CV and Pattern Recognition
Makes 3D pictures look right after editing.
AutoEdit: Automatic Hyperparameter Tuning for Image Editing
CV and Pattern Recognition
Makes editing pictures with words much faster.
Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers
CV and Pattern Recognition
Makes computers understand pictures better for tasks.