Related papers: Zero-Residual Concept Erasure via Progressive Alig…

Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts-such as entity missing, attribute binding errors, and incorrect relationships remains a…

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…

Erase inpainting, or object removal, aims to precisely remove target objects within masked regions while preserving the overall consistency of the surrounding content. Despite diffusion-based methods have made significant strides in the…

Large language models (LLMs) often acquire knowledge during pretraining that is undesirable in downstream deployments, e.g., sensitive information or copyrighted content. Existing approaches for removing such knowledge rely on fine-tuning,…

Large-scale text-to-image generative models have shown their remarkable ability to synthesize diverse and high-quality images. However, it is still challenging to directly apply these models for editing real images for two reasons. First,…

Diffusion models have recently surpassed GANs in image synthesis and editing, offering superior image quality and diversity. However, achieving precise control over attributes in generated images remains a challenge. Concept Sliders…

We introduce a novel approach for concept blending in pretrained text-to-image diffusion models, aiming to generate images at the intersection of multiple text prompts. At each time step during diffusion denoising, our algorithm forecasts…

This paper addresses the performance bottlenecks of existing text-driven image generation methods in terms of semantic alignment accuracy and structural consistency. A high-fidelity image generation method is proposed by integrating…

Recent advancements in text-to-image diffusion models have brought them to the public spotlight, becoming widely accessible and embraced by everyday users. However, these models have been shown to generate harmful content such as…

The powerful generative capabilities of diffusion models have raised growing privacy and safety concerns regarding generating sensitive or undesired content. In response, machine unlearning (MU) -- commonly referred to as concept erasure…

Text-to-image diffusion models have made significant advancements in generating high-quality, diverse images from text prompts. However, the inherent limitations of textual signals often prevent these models from fully capturing specific…

Diffusion customization methods have achieved impressive results with only a minimal number of user-provided images. However, existing approaches customize concepts collectively, whereas real-world applications often require sequential…

In this work, we present DeepEraser, an effective deep network for generic text removal. DeepEraser utilizes a recurrent architecture that erases the text in an image via iterative operations. Our idea comes from the process of erasing…

Generative models, particularly diffusion-based text-to-image (T2I) models, have demonstrated astounding success. However, aligning them to avoid generating content with unacceptable concepts (e.g., offensive or copyrighted content, or…

The rapid growth of text-to-video (T2V) diffusion models has raised concerns about privacy, copyright, and safety due to their potential misuse in generating harmful or misleading content. These models are often trained on numerous…

Text-to-image (T2I) diffusion models have achieved remarkable success in generating high-quality images from textual prompts. However, their ability to store vast amounts of knowledge raises concerns in scenarios where selective forgetting…

As large-scale diffusion models continue to advance, they excel at producing high-quality images but often generate unwanted content, such as sexually explicit or violent content. Existing methods for concept removal generally guide the…

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…

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse…

We propose a novel, zero-shot image generation technique called "Visual Concept Blending" that provides fine-grained control over which features from multiple reference images are transferred to a source image. If only a single reference…