Related papers: EEdit: Rethinking the Spatial and Temporal Redunda…
Text-guided image editing aims to modify specific regions according to the target prompt while preserving the identity of the source image. Recent methods exploit explicit binary masks to constrain editing, but hard mask boundaries…
Current methods commonly utilize three-branch structures of inversion, reconstruction, and editing, to tackle consistent image editing task. However, these methods lack control over the generation position of the edited object and have…
This paper investigates the role of CLIP image embeddings within the Stable Video Diffusion (SVD) framework, focusing on their impact on video generation quality and computational efficiency. Our findings indicate that CLIP embeddings,…
This paper studies the problem of StyleGAN inversion, which plays an essential role in enabling the pretrained StyleGAN to be used for real image editing tasks. The goal of StyleGAN inversion is to find the exact latent code of the given…
Despite many attempts to leverage pre-trained text-to-image models (T2I) like Stable Diffusion (SD) for controllable image editing, producing good predictable results remains a challenge. Previous approaches have focused on either…
The tremendous progress in neural image generation, coupled with the emergence of seemingly omnipotent vision-language models has finally enabled text-based interfaces for creating and editing images. Handling generic images requires a…
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…
This paper presents a video inversion approach for zero-shot video editing, which models the input video with low-rank representation during the inversion process. The existing video editing methods usually apply the typical 2D DDIM…
We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input…
Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image editing. By shifting the editing paradigm from noise…
Generative Adversarial Network (GAN) based localized image editing can suffer from ambiguity between semantic attributes. We thus present a novel objective function to evaluate the locality of an image edit. By introducing the supervision…
Diffusion models have made significant advances in generating high-quality images, but their application to video generation has remained challenging due to the complexity of temporal motion. Zero-shot video editing offers a solution by…
Large-scale Text-to-Image (T2I) diffusion models have revolutionized image generation over the last few years. Although owning diverse and high-quality generation capabilities, translating these abilities to fine-grained image editing…
Text-guided image editing is an essential task that enables users to modify images through natural language descriptions. Recent advances in diffusion models and rectified flows have significantly improved editing quality, primarily relying…
Inversion-based visual editing provides an effective and training-free way to edit an image or a video based on user instructions. Existing methods typically inject source image information during the sampling process to maintain editing…
Recent advances in diffusion models have significantly improved image editing. However, challenges persist in handling geometric transformations, such as translation, rotation, and scaling, particularly in complex scenes. Existing…
Text-driven image synthesis has made significant advancements with the development of diffusion models, transforming how visual content is generated from text prompts. Despite these advances, text-driven image editing, a key area in…
Recent large-scale text-guided diffusion models provide powerful image-generation capabilities. Currently, a significant effort is given to enable the modification of these images using text only as means to offer intuitive and versatile…
Diffusion models have opened the path to a wide range of text-based image editing frameworks. However, these typically build on the multi-step nature of the diffusion backwards process, and adapting them to distilled, fast-sampling methods…
Diffusion-based image editing is a composite process of preserving the source image content and generating new content or applying modifications. While current editing approaches have made improvements under text guidance, most of them have…