Related papers: Training-Free Multi-Concept Image Editing
The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and FLUX.2-klein). However, these models present significant…
We introduce Delta Denoising Score (DDS), a novel scoring function for text-based image editing that guides minimal modifications of an input image towards the content described in a target prompt. DDS leverages the rich generative prior of…
Cross-modality distillation arises as an important topic for data modalities containing limited knowledge such as depth maps and high-quality sketches. Such techniques are of great importance, especially for memory and privacy-restricted…
The problem of unsupervised learning and segmentation of hyperspectral images is a significant challenge in remote sensing. The high dimensionality of hyperspectral data, presence of substantial noise, and overlap of classes all contribute…
Diffusion models are capable of generating impressive images conditioned on text descriptions, and extensions of these models allow users to edit images at a relatively coarse scale. However, the ability to precisely edit the layout,…
Diffusion-based image editing offers strong semantic controllability, but remains computationally expensive due to iterative high-resolution denoising over all spatial tokens. Dynamic-resolution sampling reduces this cost by performing…
We present a method to create interpretable concept sliders that enable precise control over attributes in image generations from diffusion models. Our approach identifies a low-rank parameter direction corresponding to one concept while…
Text-to-image models suffer from various safety issues that may limit their suitability for deployment. Previous methods have separately addressed individual issues of bias, copyright, and offensive content in text-to-image models. However,…
Diffusion models have achieved remarkable success in generating high-resolution, realistic images across diverse natural distributions. However, their performance heavily relies on high-quality training data, making it challenging to learn…
Motivated by recent advancements in text-to-image diffusion, we study erasure of specific concepts from the model's weights. While Stable Diffusion has shown promise in producing explicit or realistic artwork, it has raised concerns…
Consistency distillation methods have demonstrated significant success in accelerating generative tasks of diffusion models. However, since previous consistency distillation methods use simple and straightforward strategies in selecting…
While continuous diffusion models have achieved remarkable success, discrete diffusion offers a unified framework for jointly modeling text and images. Beyond unification, discrete diffusion provides faster inference, finer control, and…
Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. In scalable applications,…
Sampling from unnormalized multimodal distributions with limited density evaluations remains a fundamental challenge in machine learning and natural sciences. Successful approaches construct a bridge between a tractable reference and the…
Text-to-image diffusion models have demonstrated the underlying risk of generating various unwanted content, such as sexual elements. To address this issue, the task of concept erasure has been introduced, aiming to erase any undesired…
Advanced change detection techniques primarily target image pairs of equal and high quality. However, variations in imaging conditions and platforms frequently lead to image pairs with distinct qualities: one image being high-quality, while…
Although the diffusion model has achieved remarkable performance in the field of image generation, its high inference delay hinders its wide application in edge devices with scarce computing resources. Therefore, many training-free sampling…
Discrete diffusion models are a class of generative models that construct sequences by progressively denoising samples from a categorical noise distribution. Beyond their rapidly growing ability to generate coherent natural language, these…
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…
We propose Delta Rectified Flow Sampling (DRFS), a novel inversion-free, path-aware editing framework within rectified flow models for text-to-image editing. DRFS is a distillation-based method that explicitly models the discrepancy between…