相关论文: Erasing Concepts from Diffusion Models

Robust concept removal for text-to-image (T2I) and text-to-video (T2V) models is essential for their safe deployment. Existing methods, however, suffer from costly retraining, inference overhead, or vulnerability to adversarial attacks.…

This paper addresses the societal concerns arising from large-scale text-to-image diffusion models for generating potentially harmful or copyrighted content. Existing models rely heavily on internet-crawled data, wherein problematic…

The rapid progress of visual autoregressive (VAR) models has brought new opportunities for text-to-image generation, but also heightened safety concerns. Existing concept erasure techniques, primarily designed for diffusion models, fail to…

Text-to-image diffusion models have demonstrated remarkable effectiveness in rapid and high-fidelity personalization, even when provided with only a few user images. However, the effectiveness of personalization techniques has lead to…

Existing concept erasure methods for text-to-image diffusion models commonly rely on fixed anchor strategies, which often lead to critical issues such as concept re-emergence and erosion. To address this, we conduct causal tracing to reveal…

Recent advances in text-to-image (T2I) diffusion models have seen rapid and widespread adoption. However, their powerful generative capabilities raise concerns about potential misuse for synthesizing harmful, private, or copyrighted…

Text-to-image models are increasingly popular and impactful, yet concerns regarding their safety and fairness remain. This study investigates the ability of ten popular Stable Diffusion models to generate harmful images, including NSFW,…

In the evolving domain of text-to-image generation, diffusion models have emerged as powerful tools in content creation. Despite their remarkable capability, existing models still face challenges in achieving controlled generation with a…

A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images.They either finetune the model, or invert the image in the latent space of the pretrained model. However,…

Concept erasure aims to remove harmful, inappropriate, or copyrighted content from text-to-image diffusion models while preserving non-target semantics. However, existing methods either rely on costly fine-tuning or apply coarse semantic…

Tuning-free diffusion-based models have demonstrated significant potential in the realm of image personalization and customization. However, despite this notable progress, current models continue to grapple with several complex challenges…

With the advance of diffusion models, various personalized image generation methods have been proposed. However, almost all existing work only focuses on either subject-driven or style-driven personalization. Meanwhile, state-of-the-art…

Large multimodal models such as Stable Diffusion can generate, detect, and classify new visual concepts after fine-tuning just a single word embedding. Do models learn similar words for the same concepts (i.e. <orange-cat> = orange + cat)?…

Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT), and employed flow-matching for improved training and…

Recent advancements in large-scale text-to-image diffusion models have enabled many applications in image editing. However, none of these methods have been able to edit the layout of single existing images. To address this gap, we propose…

Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has…

With the rapid progress of diffusion-based content generation, significant efforts are being made to unlearn harmful or copyrighted concepts from pretrained diffusion models (DMs) to prevent potential model misuse. However, it is observed…

Text-driven image and video diffusion models have recently achieved unprecedented generation realism. While diffusion models have been successfully applied for image editing, very few works have done so for video editing. We present the…

Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining…

While generative models produce high-quality images of concepts learned from a large-scale database, a user often wishes to synthesize instantiations of their own concepts (for example, their family, pets, or items). Can we teach a model to…