English
Related papers

Related papers: FastLightGen: Fast and Light Video Generation with…

200 papers

The multi-step sampling mechanism, a key feature of visual diffusion models, has significant potential to replicate the success of OpenAI's Strawberry in enhancing performance by increasing the inference computational cost. Sufficient prior…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Shitong Shao , Zikai Zhou , Lichen Bai , Haoyi Xiong , Zeke Xie

We introduce Elastic Looped Transformers (ELT), a highly parameter-efficient class of visual generative models based on a recurrent transformer architecture. While conventional generative models rely on deep stacks of unique transformer…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Sahil Goyal , Swayam Agrawal , Gautham Govind Anil , Prateek Jain , Sujoy Paul , Aditya Kusupati

Efficient video generation models are increasingly vital for multimedia synthetic content generation. Leveraging the Transformer architecture and the diffusion process, video DiT models have emerged as a dominant approach for high-quality…

Graphics · Computer Science 2026-02-27 Yuanxin Wei , Lansong Diao , Bujiao Chen , Shenggan Cheng , Zhengping Qian , Wenyuan Yu , Nong Xiao , Wei Lin , Jiangsu Du

Diffusion models and flow-matching models have enabled generating diverse and realistic images by learning to transfer noise to data. However, sampling from these models involves iterative denoising over many neural network passes, making…

Machine Learning · Computer Science 2025-06-24 Kevin Frans , Danijar Hafner , Sergey Levine , Pieter Abbeel

Recent advances in trajectory-controllable video generation have achieved remarkable progress. Previous methods mainly use adapter-based architectures for precise motion control along predefined trajectories. However, all these methods rely…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Quanhao Li , Zhen Xing , Rui Wang , Haidong Cao , Qi Dai , Daoguo Dong , Zuxuan Wu

Recent advances in text-to-image generation have primarily relied on extensive datasets and parameter-heavy architectures. These requirements severely limit accessibility for researchers and practitioners who lack substantial computational…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Xianfeng Wu , Yajing Bai , Haoze Zheng , Harold Haodong Chen , Yexin Liu , Zihao Wang , Xuran Ma , Wen-Jie Shu , Xianzu Wu , Harry Yang , Ser-Nam Lim

Video diffusion models have shown great potential in generating high-quality videos, making them an increasingly popular focus. However, their inherent iterative nature leads to substantial computational and time costs. While efforts have…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Xiaofeng Mao , Zhengkai Jiang , Fu-Yun Wang , Jiangning Zhang , Hao Chen , Mingmin Chi , Yabiao Wang , Wenhan Luo

The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Ziying Pan , Kun Wang , Gang Li , Feihong He , Yongxuan Lai

Video diffusion models (DMs) have enabled high-quality video synthesis. However, their computation costs scale quadratically with sequence length because self-attention has quadratic complexity. While linear attention lowers the cost, fully…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Yushi Huang , Xingtong Ge , Ruihao Gong , Chengtao Lv , Jun Zhang

We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and…

Videos show continuous events, yet most $-$ if not all $-$ video synthesis frameworks treat them discretely in time. In this work, we think of videos of what they should be $-$ time-continuous signals, and extend the paradigm of neural…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Ivan Skorokhodov , Sergey Tulyakov , Mohamed Elhoseiny

Training of Generative Adversarial Network (GAN) on a video dataset is a challenge because of the sheer size of the dataset and the complexity of each observation. In general, the computational cost of training GAN scales exponentially with…

Computer Vision and Pattern Recognition · Computer Science 2020-06-02 Masaki Saito , Shunta Saito , Masanori Koyama , Sosuke Kobayashi

Diffusion models are rising as a powerful solution for high-fidelity image generation, which exceeds GANs in quality in many circumstances. However, their slow training and inference speed is a huge bottleneck, blocking them from being used…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Hao Phung , Quan Dao , Anh Tran

Diffusion models have demonstrated remarkable capabilities in visual content generation but remain challenging to deploy due to their high computational cost during inference. This computational burden primarily arises from the quadratic…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Ye Tian , Xin Xia , Yuxi Ren , Shanchuan Lin , Xing Wang , Xuefeng Xiao , Yunhai Tong , Ling Yang , Bin Cui

Despite diffusion models having shown powerful abilities to generate photorealistic images, generating videos that are realistic and diverse still remains in its infancy. One of the key reasons is that current methods intertwine spatial…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Zhiwu Qing , Shiwei Zhang , Jiayu Wang , Xiang Wang , Yujie Wei , Yingya Zhang , Changxin Gao , Nong Sang

We tackle the long video generation problem, i.e.~generating videos beyond the output length of video generation models. Due to the computation resource constraints, video generation models can only generate video clips that are relatively…

Computer Vision and Pattern Recognition · Computer Science 2023-04-18 Hsin-Ping Huang , Yu-Chuan Su , Ming-Hsuan Yang

State-of-the-art video generative models typically learn the distribution of video latents in the VAE space and map them to pixels using a VAE decoder. While this approach can generate high-quality videos, it suffers from slow convergence…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Jianhong Bai , Xiaoshi Wu , Xintao Wang , Xiao Fu , Yuanxing Zhang , Qinghe Wang , Xiaoyu Shi , Menghan Xia , Zuozhu Liu , Haoji Hu , Pengfei Wan , Kun Gai

In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion. The method reaches state-of-the-art performances in terms of FID and CLIP-Score…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Clément Chadebec , Onur Tasar , Eyal Benaroche , Benjamin Aubin

Recently, with the tremendous success of diffusion models in the field of text-to-image (T2I) generation, increasing attention has been directed toward their potential in text-to-video (T2V) applications. However, the computational demands…

Computer Vision and Pattern Recognition · Computer Science 2025-01-29 Wenfeng Lin , Jiangchuan Wei , Boyuan Liu , Yichen Zhang , Shiyue Yan , Mingyu Guo

Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence,…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Tianwei Yin , Qiang Zhang , Richard Zhang , William T. Freeman , Fredo Durand , Eli Shechtman , Xun Huang