Related papers: Exploring Iterative Manifold Constraint for Zero-s…
By comparing the original and target prompts, we can obtain numerous editing pairs, each comprising an object and its corresponding editing target. To allow editability while maintaining fidelity to the input image, existing editing methods…
With the rise of large, publicly-available text-to-image diffusion models, text-guided real image editing has garnered much research attention recently. Existing methods tend to either rely on some form of per-instance or per-task…
Diffusion-based point editing methods have gained significant traction in image editing tasks due to their ability to manipulate image semantics and fine details by applying localized perturbations on the manifold of noise latent. However,…
Recent advances in training-free attention control methods have enabled flexible and efficient text-guided editing capabilities for existing generation models. However, current approaches struggle to simultaneously deliver strong editing…
Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the…
Text-guided image editing involves modifying a source image based on a language instruction and, typically, requires changes to only small local regions. However, existing approaches generate the entire target image rather than selectively…
Recovering natural language prompts for image generation models, solely based on the generated images is a difficult discrete optimization problem. In this work, we present the first head-to-head comparison of recent discrete optimization…
The diffusion model has demonstrated superior performance in synthesizing diverse and high-quality images for text-guided image translation. However, there remains room for improvement in both the formulation of text prompts and the…
Controllable image generation is fundamental to the success of modern generative AI, yet it faces a critical trade-off between semantic fidelity and inference speed. The RemEdit diffusion-based framework addresses this trade-off with two…
Zero-shot generative model adaptation (ZSGM) aims to adapt a pre-trained generator to a target domain using only text guidance and without any samples from the target domain. Central to recent ZSGM approaches are directional loss which use…
Recent advances in vision-language models like Stable Diffusion have shown remarkable power in creative image synthesis and editing.However, most existing text-to-image editing methods encounter two obstacles: First, the text prompt needs…
In this paper, we focus on the task of instruction-based image editing. Previous works like InstructPix2Pix, InstructDiffusion, and SmartEdit have explored end-to-end editing. However, two limitations still remain: First, existing datasets…
Diffusion-based editing has rapidly evolved from curated inpainting tools into general-purpose editors spanning text-guided instruction following, mask-localized edits, drag-based geometric manipulation, exemplar transfer, and training-free…
Continuous image editing aims to provide slider-style control of edit strength while preserving source-image fidelity and maintaining a consistent edit direction. Existing learning-based slider methods typically rely on auxiliary modules…
Image editing has advanced significantly with the development of diffusion models using both inversion-based and instruction-based methods. However, current inversion-based approaches struggle with big modifications (e.g., adding or…
Image editing in rectified flow models remains challenging due to the fundamental trade-off between reconstruction fidelity and editing flexibility. While inversion-based methods suffer from trajectory deviation, recent inversion-free…
Recent pre-trained text-to-image flow models have enabled remarkable progress in text-based image editing. Mainstream approaches adopt a corruption-then-restoration paradigm, where the source image is first corrupted into an editable…
Inversion-free image editing using flow-based generative models challenges the prevailing inversion-based pipelines. However, existing approaches rely on fixed Gaussian noise to construct the source trajectory, leading to biased trajectory…
Text-guided image editing with diffusion models has achieved remarkable quality but often suffers from prohibitive latency. We introduce \textbf{FlashEdit}, a real-time localized image editing framework for the standard inversion-based…
The diffusion-based generative models have achieved remarkable success in text-based image generation. However, since it contains enormous randomness in generation progress, it is still challenging to apply such models for real-world visual…