English
Related papers

Related papers: Supercharged One-step Text-to-Image Diffusion Mode…

200 papers

Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models. Although distillation of pre-trained diffusion models has been successful in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Jeeyung Kim , Ze Wang , Qiang Qiu

Classifier-free guidance (CFG) is a fundamental tool in modern diffusion models for text-guided generation. Although effective, CFG has notable drawbacks. For instance, DDIM with CFG lacks invertibility, complicating image editing;…

Computer Vision and Pattern Recognition · Computer Science 2024-09-13 Hyungjin Chung , Jeongsol Kim , Geon Yeong Park , Hyelin Nam , Jong Chul Ye

One-step generators distilled from Masked Diffusion Models (MDMs) compress multiple sampling steps into a single forward pass, enabling efficient text and image synthesis. However, they suffer two key limitations: they inherit modeling bias…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Yuanzhi Zhu , Xi Wang , Stéphane Lathuilière , Vicky Kalogeiton

Diffusion Models (DMs) have achieved great success in image generation and other fields. By fine sampling through the trajectory defined by the SDE/ODE solver based on a well-trained score model, DMs can generate remarkable high-quality…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Bowen Zheng , Tianming Yang

Diffusion models often exhibit inconsistent sample quality due to stochastic variations inherent in their sampling trajectories. Although training-based fine-tuning (e.g. DDPO [1]) and inference-time alignment techniques[2] aim to improve…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Sixian Wang , Zhiwei Tang , Tsung-Hui Chang

State-of-the-arts text-to-image generation models such as Imagen and Stable Diffusion Model have succeed remarkable progresses in synthesizing high-quality, feature-rich images with high resolution guided by human text prompts. Since…

Computer Vision and Pattern Recognition · Computer Science 2025-01-31 Ziyi Dong , Pengxu Wei , Liang Lin

We introduce NitroFusion, a fundamentally different approach to single-step diffusion that achieves high-quality generation through a dynamic adversarial framework. While one-step methods offer dramatic speed advantages, they typically…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Dar-Yen Chen , Hmrishav Bandyopadhyay , Kai Zou , Yi-Zhe Song

While diffusion distillation has enabled one-step generation through methods like Variational Score Distillation, adapting distilled models to emerging new controls -- such as novel structural constraints or latest user preferences --…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Yihong Luo , Tianyang Hu , Yifan Song , Jiacheng Sun , Zhenguo Li , Jing Tang

Recent advances in few-step diffusion models have demonstrated their efficiency and effectiveness by shortcutting the probabilistic paths of diffusion models, especially in training one-step diffusion models from scratch (\emph{a.k.a.}…

Machine Learning · Computer Science 2026-02-03 Haitao Lin , Peiyan Hu , Minsi Ren , Zhifeng Gao , Zhi-Ming Ma , Guolin ke , Tailin Wu , Stan Z. Li

Diffusion models have revolutionized text-to-image generation with its exceptional quality and creativity. However, its multi-step sampling process is known to be slow, often requiring tens of inference steps to obtain satisfactory results.…

Machine Learning · Computer Science 2024-03-26 Xingchao Liu , Xiwen Zhang , Jianzhu Ma , Jian Peng , Qiang Liu

Diffusion models excel in high-quality generation but suffer from slow inference due to iterative sampling. While recent methods have successfully transformed diffusion models into one-step generators, they neglect model size reduction,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Yuanzhi Zhu , Xingchao Liu , Qiang Liu

Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. Yet, the limited capacity of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Xiangyu Fan , Zesong Qiu , Zhuguanyu Wu , Fanzhou Wang , Zhiqian Lin , Tianxiang Ren , Dahua Lin , Ruihao Gong , Lei Yang

Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation. To overcome this limitation, we propose consistency models, a new…

Machine Learning · Computer Science 2023-06-01 Yang Song , Prafulla Dhariwal , Mark Chen , Ilya Sutskever

Human-centered images often suffer from severe generic degradation during transmission and are prone to human motion blur (HMB), making restoration challenging. Existing research lacks sufficient focus on these issues, as both problems…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Jue Gong , Tingyu Yang , Jingkai Wang , Zheng Chen , Xing Liu , Hong Gu , Yulun Zhang , Xiaokang Yang

Diffusion models have shown promising results in speech enhancement, using a task-adapted diffusion process for the conditional generation of clean speech given a noisy mixture. However, at test time, the neural network used for score…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-17 Bunlong Lay , Jean-Marie Lemercier , Julius Richter , Timo Gerkmann

This paper presents SANA-Sprint, an efficient diffusion model for ultra-fast text-to-image (T2I) generation. SANA-Sprint is built on a pre-trained foundation model and augmented with hybrid distillation, dramatically reducing inference…

Graphics · Computer Science 2025-09-30 Junsong Chen , Shuchen Xue , Yuyang Zhao , Jincheng Yu , Sayak Paul , Junyu Chen , Han Cai , Song Han , Enze Xie

Well-designed prompts have demonstrated the potential to guide text-to-image models in generating amazing images. Although existing prompt engineering methods can provide high-level guidance, it is challenging for novice users to achieve…

Multimedia · Computer Science 2026-03-27 Nailei Hei , Qianyu Guo , Zihao Wang , Yan Wang , Haofen Wang , Wenqiang Zhang

Understanding galaxy morphology evolution across cosmic time requires models that can generate realistic galaxy populations conditioned on redshift. In this work, we study efficient redshift-conditioned generative modeling for astrophysical…

Instrumentation and Methods for Astrophysics · Physics 2026-05-19 Tianyue Yang , Sandro Tacchella , Xiao Xue

Flow matching has emerged as a promising framework for training generative models, demonstrating impressive empirical performance while offering relative ease of training compared to diffusion-based models. However, this method still…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Quan Dao , Hao Phung , Trung Dao , Dimitris Metaxas , Anh Tran

Personalizing text-to-image diffusion models is crucial for adapting the pre-trained models to specific target concepts, enabling diverse image generation. However, fine-tuning with few images introduces an inherent trade-off between…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Sunghyun Park , Seokeon Choi , Hyoungwoo Park , Sungrack Yun