Related papers: Responsible Diffusion Models via Constraining Text…
With the advance of generative AI, the text-to-image (T2I) model has the ability to generate various contents. However, the generated contents cannot be fully controlled. There is a potential risk that T2I model can generate unsafe images…
The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases. Without interventions, these biases could propagate a skewed worldview and restrict opportunities for minority groups. In…
Text-to-image generation models~(e.g., Stable Diffusion) have achieved significant advancements, enabling the creation of high-quality and realistic images based on textual descriptions. Prompt inversion, the task of identifying the textual…
Recent advancements in text-to-image diffusion models have demonstrated remarkable success, yet they often struggle to fully capture the user's intent. Existing approaches using textual inputs combined with bounding boxes or region masks…
While diffusion models have revolutionized text-to-image generation with their ability to synthesize realistic and diverse scenes, they continue to struggle to generate consistent and legible text within images. This shortcoming is commonly…
Generative models have been very popular in the recent years for their image generation capabilities. GAN-based models are highly regarded for their disentangled latent space, which is a key feature contributing to their success in…
Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing safety concerns about the vulnerability of the model that…
Diffusion models have achieved unprecedented success in image generation but pose increasing risks in terms of privacy, fairness, and security. A growing demand exists to \emph{erase} sensitive or harmful concepts (e.g., NSFW content,…
Text-to-image diffusion models have achieved remarkable progress in generating diverse and realistic images from textual descriptions. However, they still struggle with personalization, which requires adapting a pretrained model to depict…
Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…
Recent work has shown that a model's input word embeddings can serve as effective control variables for steering its behavior toward outputs that satisfy desired properties. However, this has only been demonstrated for pretrained…
Visual-textual correlations in the attention maps derived from text-to-image diffusion models are proven beneficial to dense visual prediction tasks, e.g., semantic segmentation. However, a significant challenge arises due to the input…
Text-to-image models encounter safety issues, including concerns related to copyright and Not-Safe-For-Work (NSFW) content. Despite several methods have been proposed for erasing inappropriate concepts from diffusion models, they often…
Text-to-image (T2I) models can be maliciously used to generate harmful content such as sexually explicit, unfaithful, and misleading or Not-Safe-for-Work (NSFW) images. Previous attacks largely depend on the availability of the diffusion…
Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-driven, relying on…
Image restoration aims to enhance low quality images, producing high quality images that exhibit natural visual characteristics and fine semantic attributes. Recently, the diffusion model has emerged as a powerful technique for image…
With the current shift in the mass media landscape from journalistic rigor to social media, personalized social media is becoming the new norm. Although the digitalization progress of the media brings many advantages, it also increases the…
Text-to-image models can generate harmful images when presented with unsafe prompts, posing significant safety and societal risks. Alignment methods aim to modify these models to ensure they generate only non-harmful images, even when…
Diffusion models have demonstrated exceptional capability in generating high-quality images, videos, and audio. Due to their adaptiveness in iterative refinement, they provide a strong potential for achieving better non-autoregressive…
The correspondence between input text and the generated image exhibits opacity, wherein minor textual modifications can induce substantial deviations in the generated image. While, text embedding, as the pivotal intermediary between text…