Related papers: Bi-Erasing: A Bidirectional Framework for Concept …

Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as…

Text-guided diffusion models have revolutionized generative tasks by producing high-fidelity content from text descriptions. They have also enabled an editing paradigm where concepts can be replaced through text conditioning (e.g., a dog to…

Recently, diffusion-based image generation methods are credited for their remarkable text-to-image generation capabilities, while still facing challenges in accurately generating multilingual scene text images. To tackle this problem, we…

Concept erasure has emerged as a key research direction for ensuring safe and ethical image synthesis in Text-to-Image (T2I) models. While existing studies have explored concept erasure across multiple concepts, they typically assume only a…

We propose DeCoDi, a debiasing procedure for text-to-image diffusion-based models that changes the inference procedure, does not significantly change image quality, has negligible compute overhead, and can be applied in any diffusion-based…

Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure methods. Existing reawakening methods mainly rely on…

Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or undesirable content. Existing concept erasure methods are…

The widespread adoption of text-to-image (T2I) generation has raised concerns about privacy, bias, and copyright violations. Concept erasure techniques offer a promising solution by selectively removing undesired concepts from pre-trained…

Diffusion models have dramatically advanced text-to-image generation in recent years, translating abstract concepts into high-fidelity images with remarkable ease. In this work, we examine whether they can also blend distinct concepts,…

Although text-to-image diffusion models exhibit remarkable generative power, concept erasure techniques are essential for their safe deployment to prevent the creation of harmful content. This has fostered a dynamic interplay between the…

Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…

Scene text editing is a challenging task that involves modifying or inserting specified texts in an image while maintaining its natural and realistic appearance. Most previous approaches to this task rely on style-transfer models that crop…

Object removal has so far been dominated by the mask-and-inpaint paradigm, where the masked region is excluded from the input, leaving models relying on unmasked areas to inpaint the missing region. However, this approach lacks contextual…

Concept erasure aims to remove specified features from an embedding. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. removing a concept to observe changes in model behavior). We…

As generative models expand the possibilities of visual content creation, layered image synthesis has emerged as a promising direction for controllable and creative editing. However, existing methods struggle to fully realize this…

Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision. As these representations are increasingly being used in real-world applications, the inability to \emph{control} their…

Text-to-image diffusion models suffer from the risk of generating outdated, copyrighted, incorrect, and biased content. While previous methods have mitigated the issues on a small scale, it is essential to handle them simultaneously in…

Editing images with diffusion models under strict training-free constraints remains a significant challenge. While recent optimisation-based methods achieve strong zero-shot edits from text, they struggle to preserve identity and capture…

Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyright violations. The techniques of machine unlearning, also…

Denoising diffusion models have emerged as a dominant approach for image generation, however they still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be…