Latest Articles for Image Generation

Computer Vision and Pattern Recognition Advancements in Conditional Generation Technology

Researchers enhance image and motion generation based on user instructions.

Youyuan Zhang, Zehua Liu, Zenan Li

2025-05-20T20:55:03+00:00 ― 6 min read

Computer Vision and Pattern Recognition StyleCodes: Simplifying Image Style Sharing

StyleCodes offer an easy way to share image styles without heavy files.

Ciara Rowles

2025-05-18T14:06:40+00:00 ― 6 min read

Distributed, Parallel, and Cluster Computing Streamlining Text-to-Image Generation with DiffServe

DiffServe improves image generation speed and quality by smartly sorting requests.

Sohaib Ahmad, Qizheng Yang, Haoliang Wang

2025-05-13T07:26:40+00:00 ― 4 min read

Computer Vision and Pattern Recognition Making Diffusion Models More Accessible through Pruning

Research shows how to compress diffusion models while maintaining quality.

Samarth N Ramesh, Zhixue Zhao

2025-05-12T22:34:40+00:00 ― 6 min read

Computer Vision and Pattern Recognition D-JEPA T2I: Transforming Text into Images

Discover how D-JEPA T2I generates stunning images from text descriptions.

Dengsheng Chen, Jie Hu, Tiezhu Yue

2025-05-12T05:16:00+00:00 ― 7 min read

Computer Vision and Pattern Recognition Creating Art with Computers: A New Approach

Learn how new techniques help computers generate unique artistic images.

Jooyoung Choi, Chaehun Shin, Yeongtak Oh

2025-05-12T03:34:40+00:00 ― 6 min read

Machine Learning Evaluating Safety in Text-to-Image Models with ICER

ICER framework tests safety measures in text-to-image models effectively.

Zhi-Yi Chin, Kuan-Chen Mu, Mario Fritz

2025-05-10T23:42:40+00:00 ― 7 min read

Computer Vision and Pattern Recognition Advancements in Visual Tokenization with Factorized Quantization

Factorized Quantization improves image generation through efficient token management.

Zechen Bai, Jianxiong Gao, Ziteng Gao

2025-05-09T02:57:20+00:00 ― 5 min read

Computer Vision and Pattern Recognition Addressing Diversity in AI Image Generation

This article discusses the importance of diversity in AI-generated images.

Mischa Dombrowski, Weitong Zhang, Sarah Cechnicka

2025-05-08T02:28:00+00:00 ― 6 min read

Computer Vision and Pattern Recognition MVGenMaster: The Future of Image Generation

MVGenMaster revolutionizes 3D content creation with innovative image generation techniques.

Chenjie Cao, Chaohui Yu, Shang Liu

2025-05-08T01:12:00+00:00 ― 6 min read

Computer Vision and Pattern Recognition Improving Text-to-Image Models with Reliable Noise

Discover how noise patterns can enhance text-to-image model accuracy.

Shuangqi Li, Hieu Le, Jingyi Xu

2025-05-05T02:41:20+00:00 ― 9 min read

Cryptography and Security Analyzing Safety Measures in Text-to-Image Models

Research reveals vulnerabilities in AI image generators from prompt manipulation.

Ted Kwartler, Nataliia Bagan, Ivan Banny

2025-05-04T21:37:20+00:00 ― 6 min read

Computer Vision and Pattern Recognition Improving Image Generation with Self-Cross Guidance

New technique helps AI avoid mixing similar subjects in image creation.

Weimin Qiu, Jieke Wang, Meng Tang

2025-05-02T02:54:40+00:00 ― 7 min read

Computer Vision and Pattern Recognition Introducing FLD+: A New Way to Measure Image Quality

FLD+ improves the evaluation of computer-generated images with fewer and more accurate measures.

Pranav Jeevan, Neeraj Nixon, Amit Sethi

2025-04-30T19:09:12+00:00 ― 5 min read

Computer Vision and Pattern Recognition NitroFusion: The Future of Image Creation

Discover NitroFusion, a one-step method for creating stunning images from text.

Dar-Yen Chen, Hmrishav Bandyopadhyay, Kai Zou

2025-04-26T04:37:15+00:00 ― 5 min read

Computer Vision and Pattern Recognition RandAR: The Future of Image Generation

Discover RandAR, a new way to create images that breaks traditional boundaries.

Ziqi Pang, Tianyuan Zhang, Fujun Luan

2025-04-25T17:17:45+00:00 ― 6 min read

Computer Vision and Pattern Recognition Improving Text-to-Image Models with Attention

A fresh approach enhances image accuracy from text descriptions using attention techniques.

Eric Hanchen Jiang, Yasi Zhang, Zhi Zhang

2025-04-23T03:52:30+00:00 ― 5 min read

Computer Vision and Pattern Recognition Transforming Noise into Visual Art with Diffusion Models

Learn how diffusion models create stunning visuals from random noise.

Chicago Y. Park, Michael T. McCann, Cristina Garcia-Cardona

2025-04-22T11:13:00+00:00 ― 6 min read

Computer Vision and Pattern Recognition EcoDiff: Trimming AI's Image Generation Models

A new method for efficiently pruning image-generating AI models while preserving quality.

Yang Zhang, Er Jin, Yanfei Dong

2025-04-21T16:24:15+00:00 ― 6 min read

Computer Vision and Pattern Recognition Unmasking the Secrets of Diffusion Models

Discover how diffusion models create realistic images from text prompts.

Quang H. Nguyen, Hoang Phan, Khoa D. Doan

2025-04-20T06:56:15+00:00 ― 5 min read

Machine Learning LoRA Diffusion: Redefining Image Creation

Discover how LoRA Diffusion transforms image generation for personalized results.

Ethan Smith, Rami Seid, Alberto Hojel

2025-04-19T19:42:09+00:00 ― 9 min read

Artificial Intelligence Navigating Uncertainty in Text-to-Image AI

Exploring how machine-generated images can vary due to uncertainty.

Gianni Franchi, Dat Nguyen Trong, Nacim Belkhir

2025-04-15T00:08:33+00:00 ― 5 min read

Machine Learning Revolutionizing Image Generation with LCSS

Discover the impact of local curvature smoothing on score-based diffusion models.

Genki Osada, Makoto Shing, Takashi Nishide

2025-04-09T18:09:00+00:00 ― 6 min read

Computer Vision and Pattern Recognition Fixing AI's Image Generation Errors

Researchers develop a new method to improve text-to-image AI accuracy.

Ziyuan Qin, Dongjie Cheng, Haoyu Wang

2025-04-04T12:57:36+00:00 ― 9 min read

Computer Vision and Pattern Recognition ONE-PIC: Simplifying Image Generation with Ease

ONE-PIC makes image generation quick and accessible for everyone.

Ming Tao, Bing-Kun Bao, Yaowei Wang

2025-04-04T00:55:21+00:00 ― 7 min read

Computer Vision and Pattern Recognition ASGDiffusion: A New Way to Create Stunning Images

Discover how ASGDiffusion changes high-resolution image generation.

Yuming Li, Peidong Jia, Daiwei Hong

2025-04-02T23:14:33+00:00 ― 6 min read

Computer Vision and Pattern Recognition Negative Token Merging: The Next Big Thing in AI Art

Learn how Negative Token Merging is changing AI image generation.

Jaskirat Singh, Lindsey Li, Weijia Shi

2025-03-31T19:53:26+00:00 ― 6 min read

Computer Vision and Pattern Recognition ContRail: Transforming Railway Image Generation

A framework that creates synthetic images for railways, enhancing model training.

Andrei-Robert Alexandrescu, Razvan-Gabriel Petec, Alexandru Manole

2025-03-29T21:20:15+00:00 ― 6 min read

Computer Vision and Pattern Recognition Speeding Up Image Creation with Distillation++

Learn how Distillation++ enhances image generation through smart model collaboration.

Geon Yeong Park, Sang Wan Lee, Jong Chul Ye

2025-03-22T10:22:48+00:00 ― 7 min read

Computer Vision and Pattern Recognition Revolutionizing Visuals: The Role of Scene Graphs

A new method to evaluate AI's image and video generation using scene graphs.

Ziqi Gao, Weikai Huang, Jieyu Zhang

2025-03-19T12:33:45+00:00 ― 6 min read

Computer Vision and Pattern Recognition DECOR: Transforming Text-to-Image Models

DECOR enhances T2I models for better image generation from text prompts.

Geonhui Jang, Jin-Hwa Kim, Yong-Hyun Park

2025-03-15T06:38:42+00:00 ― 7 min read

Machine Learning Revolutionizing AI Fine-Tuning with OP-LoRA

OP-LoRA enhances AI models for specific tasks, improving efficiency and performance.

Piotr Teterwak, Kate Saenko, Bryan A. Plummer

2025-03-12T11:14:06+00:00 ― 5 min read

Machine Learning Denoising Diffusion Models: A New Wave in AI

Explore how DDMs transform random noise into valuable data.

Christopher Williams, Andrew Campbell, Arnaud Doucet

2025-03-10T20:20:17+00:00 ― 6 min read

Machine Learning Paired Wasserstein Autoencoders: A New Way to Create

Learn how paired Wasserstein autoencoders generate images based on specific conditions.

Moritz Piening, Matthias Chung

2025-03-10T10:09:55+00:00 ― 6 min read

Cryptography and Security Fighting Back Against Sneaky Image Prompts

New method aims to improve safety in text-to-image models.

Portia Cooper, Harshita Narnoli, Mihai Surdeanu

2025-03-07T12:27:54+00:00 ― 5 min read

Cryptography and Security Guarding Against Hidden Threats in AI Models

Discovering the dangers of backdoor attacks in diffusion models.

Yuning Han, Bingyin Zhao, Rui Chu

2025-03-07T11:39:45+00:00 ― 7 min read

Machine Learning LazyDiT: Speeding Up Image Generation

LazyDiT offers a smarter way to create images faster without losing quality.

Xuan Shen, Zhao Song, Yufa Zhou

2025-03-04T12:14:24+00:00 ― 5 min read

Machine Learning Pruning Transformers: Reducing Bulk Without Sacrificing Quality

Innovative pruning techniques make AI models more efficient and effective.

Xuan Shen, Zhao Song, Yufa Zhou

2025-03-04T11:26:15+00:00 ― 7 min read

Computer Vision and Pattern Recognition OmniPrism: Transforming Digital Art Creation

Revolutionize your art with OmniPrism's unique blending of styles and concepts.

Yangyang Li, Daqing Liu, Wu Liu

2025-03-03T16:58:48+00:00 ― 8 min read

Computer Vision and Pattern Recognition Causal Diffusion: Redefining Media Generation

Causal Diffusion merges autoregressive and diffusion models for innovative content creation.

Chaorui Deng, Deyao Zhu, Kunchang Li

2025-03-03T13:46:12+00:00 ― 6 min read