中文
相关论文

相关论文: SustainDiffusion: Optimising the Social and Enviro…

200 篇论文

Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…

计算机视觉与模式识别 · 计算机科学 2024-04-26 Xuehai He , Weixi Feng , Tsu-Jui Fu , Varun Jampani , Arjun Akula , Pradyumna Narayana , Sugato Basu , William Yang Wang , Xin Eric Wang

Text-to-image models, such as Stable Diffusion (SD), undergo iterative updates to improve image quality and address concerns such as safety. Improvements in image quality are straightforward to assess. However, how model updates resolve…

密码学与安全 · 计算机科学 2024-09-02 Yixin Wu , Yun Shen , Michael Backes , Yang Zhang

The rapid development of text-to-image generation has brought rising ethical considerations, especially regarding gender bias. Given a text prompt as input, text-to-image models generate images according to the prompt. Pioneering models…

计算机与社会 · 计算机科学 2024-08-22 Yankun Wu , Yuta Nakashima , Noa Garcia

Generative models are nowadays widely used to generate graphical content used for multiple purposes, e.g. web, art, advertisement. However, it has been shown that the images generated by these models could reinforce societal biases already…

软件工程 · 计算机科学 2025-08-07 Tosin Fadahunsi , Giordano d'Aloisio , Antinisca Di Marco , Federica Sarro

In layout-to-image (L2I) synthesis, controlled complex scenes are generated from coarse information like bounding boxes. Such a task is exciting to many downstream applications because the input layouts offer strong guidance to the…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Ruyu Wang , Xuefeng Hou , Sabrina Schmedding , Marco F. Huber

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…

机器学习 · 计算机科学 2024-03-18 Xudong Shen , Chao Du , Tianyu Pang , Min Lin , Yongkang Wong , Mohan Kankanhalli

In this paper, we present DesignDiffusion, a simple yet effective framework for the novel task of synthesizing design images from textual descriptions. A primary challenge lies in generating accurate and style-consistent textual and visual…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Zhendong Wang , Jianmin Bao , Shuyang Gu , Dong Chen , Wengang Zhou , Houqiang Li

The Stable Diffusion Model (SDM) is a prevalent and effective model for text-to-image (T2I) and image-to-image (I2I) generation. Despite various attempts at sampler optimization, model distillation, and network quantification, these…

计算机视觉与模式识别 · 计算机科学 2024-06-18 Jinchao Zhu , Yuxuan Wang , Siyuan Pan , Pengfei Wan , Di Zhang , Gao Huang

Text-to-image diffusion models have been adopted into key commercial workflows, such as art generation and image editing. Characterising the implicit social biases they exhibit, such as gender and racial stereotypes, is a necessary first…

计算机与社会 · 计算机科学 2023-12-19 Adhithya Prakash Saravanan , Rafal Kocielnik , Roy Jiang , Pengrui Han , Anima Anandkumar

The emergence of diffusion models has significantly advanced generative AI, improving the quality, realism, and creativity of image and video generation. Among them, Stable Diffusion (StableDiff) stands out as a key model for text-to-image…

硬件体系结构 · 计算机科学 2025-07-03 Zhican Wang , Guanghui He , Hongxiang Fan

As text-to-image models grow increasingly powerful and complex, their burgeoning size presents a significant obstacle to widespread adoption, especially on resource-constrained devices. This paper presents a pioneering study on…

计算机视觉与模式识别 · 计算机科学 2024-11-25 Samarth N Ramesh , Zhixue Zhao

Recent advancements in text-to-image models, such as Stable Diffusion, show significant demographic biases. Existing de-biasing techniques rely heavily on additional training, which imposes high computational costs and risks of compromising…

人工智能 · 计算机科学 2025-03-28 Eunji Kim , Siwon Kim , Minjun Park , Rahim Entezari , Sungroh Yoon

State-of-the-art Text-to-Image models like Stable Diffusion and DALLE$\cdot$2 are revolutionizing how people generate visual content. At the same time, society has serious concerns about how adversaries can exploit such models to generate…

计算机视觉与模式识别 · 计算机科学 2023-08-17 Yiting Qu , Xinyue Shen , Xinlei He , Michael Backes , Savvas Zannettou , Yang Zhang

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…

计算机视觉与模式识别 · 计算机科学 2023-04-27 Patrick Schramowski , Manuel Brack , Björn Deiseroth , Kristian Kersting

Several studies have raised awareness about social biases in image generative models, demonstrating their predisposition towards stereotypes and imbalances. This paper contributes to this growing body of research by introducing an…

计算机视觉与模式识别 · 计算机科学 2024-08-13 Yankun Wu , Yuta Nakashima , Noa Garcia

Latent diffusion models excel at producing high-quality images from text. Yet, concerns appear about the lack of diversity in the generated imagery. To tackle this, we introduce Diverse Diffusion, a method for boosting image diversity…

计算机视觉与模式识别 · 计算机科学 2023-10-20 Mariia Zameshina , Olivier Teytaud , Laurent Najman

Diffusion-based models, widely used in text-to-image generation, have proven effective in 2D representation learning. Recently, this framework has been extended to 3D self-supervised learning by constructing a conditional point generator…

计算机视觉与模式识别 · 计算机科学 2025-07-15 Yiyang Chen , Shanshan Zhao , Lunhao Duan , Changxing Ding , Dacheng Tao

Generative diffusion models have achieved remarkable success in producing high-quality images. However, these models typically operate in continuous intensity spaces, diffusing independently across pixels and color channels. As a result,…

图形学 · 计算机科学 2025-05-20 Javier E. Santos , Agnese Marcato , Roman Colman , Nicholas Lubbers , Yen Ting Lin

We present SDXL, a latent diffusion model for text-to-image synthesis. Compared to previous versions of Stable Diffusion, SDXL leverages a three times larger UNet backbone: The increase of model parameters is mainly due to more attention…

计算机视觉与模式识别 · 计算机科学 2023-07-06 Dustin Podell , Zion English , Kyle Lacey , Andreas Blattmann , Tim Dockhorn , Jonas Müller , Joe Penna , Robin Rombach

Text-to-image diffusion models have recently attracted the interest of many researchers, and inverting the diffusion process can play an important role in better understanding the generative process and how to engineer prompts in order to…

计算机视觉与模式识别 · 计算机科学 2024-10-22 Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu , Mubarak Shah
‹ 上一页 1 2 3 10 下一页 ›