English
Related papers

Related papers: Scaling Text-to-Image Diffusion Transformers with …

200 papers

Text encoders in diffusion models have rapidly evolved, transitioning from CLIP to T5-XXL. Although this evolution has significantly enhanced the models' ability to understand complex prompts and generate text, it also leads to a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Lifu Wang , Daqing Liu , Xinchen Liu , Xiaodong He

With the rapid development of diffusion models, text-to-image(T2I) models have made significant progress, showcasing impressive abilities in prompt following and image generation. Recently launched models such as FLUX.1 and Ideogram2.0,…

Computer Vision and Pattern Recognition · Computer Science 2025-01-24 Jiayi Lei , Renrui Zhang , Xiangfei Hu , Weifeng Lin , Zhen Li , Wenjian Sun , Ruoyi Du , Le Zhuo , Zhongyu Li , Xinyue Li , Shitian Zhao , Ziyu Guo , Yiting Lu , Peng Gao , Hongsheng Li

Variational autoencoders (VAEs) typically encode images into a compact latent space, reducing computational cost but introducing an optimization dilemma: a higher-dimensional latent space improves reconstruction fidelity but often hampers…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Xunzhi Xiang , Xingye Tian , Guiyu Zhang , Yabo Chen , Shaofeng Zhang , Xuebo Wang , Xin Tao , Qi Fan

Latent diffusion models for medical image super-resolution universally inherit variational autoencoders designed for natural photographs. We show that this default choice, not the diffusion architecture, is the dominant constraint on…

Diffusion models have attained impressive visual quality for image synthesis. However, how to interpret and manipulate the latent space of diffusion models has not been extensively explored. Prior work diffusion autoencoders encode the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-26 Zeyu Lu , Chengyue Wu , Xinyuan Chen , Yaohui Wang , Lei Bai , Yu Qiao , Xihui Liu

Most visual generative models compress images into a latent space before applying diffusion or autoregressive modelling. Yet, existing approaches such as VAEs and foundation model aligned encoders implicitly constrain the latent space…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Sen Ye , Jianning Pei , Mengde Xu , Shuyang Gu , Chunyu Wang , Liwei Wang , Han Hu

Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training. This paper shows that…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Weilai Xiang , Hongyu Yang , Di Huang , Yunhong Wang

Diffusion-based representation learning has achieved substantial attention due to its promising capabilities in latent representation and sample generation. Recent studies have employed an auxiliary encoder to identify a corresponding…

Machine Learning · Computer Science 2025-03-11 Yeongmin Kim , Kwanghyeon Lee , Minsang Park , Byeonghu Na , Il-Chul Moon

Latent Diffusion Models (LDMs) rely heavily on the compressed latent space provided by Variational Autoencoders (VAEs) for high-quality image generation. Recent studies have attempted to obtain generation-friendly VAEs by directly adopting…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 John Page , Xuesong Niu , Kai Wu , Kun Gai

Recent text-to-image (T2I) diffusion models achieve remarkable realism, yet faithful prompt-image alignment remains challenging, particularly for complex prompts with multiple objects, relations, and fine-grained attributes. Existing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Liyao Jiang , Ruichen Chen , Chao Gao , Di Niu

Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear-$\beta$ noise schedule that spends much of its sampling steps at high noise levels. Because high noise levels are associated with…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 Pramook Khungurn , Sukit Seripanitkarn , Phonphrm Thawatdamrongkit , Supasorn Suwajanakorn

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Shilong Zhang , He Zhang , Zhifei Zhang , Chongjian Ge , Shuchen Xue , Shaoteng Liu , Mengwei Ren , Soo Ye Kim , Yuqian Zhou , Qing Liu , Daniil Pakhomov , Kai Zhang , Zhe Lin , Ping Luo

Artificial Intelligence-Generated Content (AIGC) has made significant strides, with high-resolution text-to-image (T2I) generation becoming increasingly critical for improving users' Quality of Experience (QoE). Although…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 Chongbin Yi , Yuxin Liang , Ziqi Zhou , Peng Yang

As recent advances in large-scale Text-to-Image (T2I) diffusion models have yielded remarkable high-quality image generation, diverse downstream Image-to-Image (I2I) applications have emerged. Despite the impressive results achieved by…

Computer Vision and Pattern Recognition · Computer Science 2024-10-11 Geonung Kim , Beomsu Kim , Eunhyeok Park , Sunghyun Cho

In this work, we empirically study Diffusion Transformers (DiTs) for text-to-image generation, focusing on architectural choices, text-conditioning strategies, and training protocols. We evaluate a range of DiT-based…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Chen Chen , Rui Qian , Wenze Hu , Tsu-Jui Fu , Jialing Tong , Xinze Wang , Lezhi Li , Bowen Zhang , Alex Schwing , Wei Liu , Yinfei Yang

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

Machine Learning · Computer Science 2025-06-09 Yin Lu , Xuening Zhu , Tong He , David Wipf

Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent distribution. We…

Machine Learning · Computer Science 2025-08-05 Theodoros Kouzelis , Ioannis Kakogeorgiou , Spyros Gidaris , Nikos Komodakis

Pixel-space generative models are often more difficult to train and generally underperform compared to their latent-space counterparts, leaving a persistent performance and efficiency gap. In this paper, we introduce a novel two-stage…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Jiachen Lei , Keli Liu , Julius Berner , Haiming Yu , Hongkai Zheng , Jiahong Wu , Xiangxiang Chu

The recent success of text-to-image synthesis has taken the world by storm and captured the general public's imagination. From a technical standpoint, it also marked a drastic change in the favored architecture to design generative image…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Minguk Kang , Jun-Yan Zhu , Richard Zhang , Jaesik Park , Eli Shechtman , Sylvain Paris , Taesung Park

Reducing token count is crucial for efficient training and inference of latent diffusion models, especially at high resolution. A common strategy is to build high-compression image tokenizers with more channels per token. However, when…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Xin Cai , Zhiyuan You , Zhoutong Zhang , Tianfan Xue