Imagen 3

Authors: Imagen-Team-Google, :, Jason Baldridge, Jakob Bauer, Mukul Bhutani, Nicole Brichtova, Andrew Bunner, Castrejon, Lluis, Kelvin Chan, Yichang Chen, Sander Dieleman, Yuqing Du, Zach Eaton-Rosen, Hongliang Fei, Nando de Freitas, Yilin Gao, Evgeny Gladchenko, Sergio Gómez Colmenarejo, Mandy Guo, Alex Haig, Will Hawkins, Hexiang Hu, Huilian Huang, Tobenna Peter Igwe, Kaplanis, Christos, Siavash Khodadadeh, Yelin Kim, Ksenia Konyushkova, Karol Langner, Eric H. Y. Lau, Lawton, Rory, Shixin Luo, Soňa Mokrá, Henna Nandwani, Yasumasa Onoe, Aäron van den Oord, Zarana Parekh, Jordi Pont-Tuset, Hang Qi, Qian, Rui, Deepak Ramachandran, Poorva Rane, Abdullah Rashwan, Ali Razavi, Robert Riachi, Hansa Srinivasan, Srivatsan Srinivasan, Robin Strudel, Benigno Uría, Oliver Wang, Su Wang, Austin R. Waters, Chris Wolff, Auriel Wright, Zhisheng Xiao, Hao Xiong, Keyang Xu, Marc van Zee, Jun-Lin Zhang, K. Zhang, Wenlei Zhou, Konrad Żołna, Ola Aboubakar, Canfer Akbulut, Oscar Akerlund, Isabela Albuquerque, Nina Anderson, Marco Andreetto, Lora Aroyo, Ben Bariach, David C. Barker, Sherry Ben, Dana Berman, Courtney Biles, Irina Blok, Pankil Botadra, J. William Brennan, Karla Brown, J. Buckley, Rudy Bunel, Elie Bursztein, Christina Butterfield, Ben Caine, Viral Carpenter, Norman Casagrande, Ming‐Wei Chang, Solomon Chang, Shamik Chaudhuri, Tony Chen, John M. Choi, Dmitry Churbanau, Nathan Clement, Matan Cohen, Forrester Cole, Mikhail Dektiarev, Vincent Du, Praneet Dutta, Tom Eccles, Ndidi Elue, Ashley Feden, Shlomi Fruchter, Frankie Garcia, Roopal Garg, Weina Ge, Ahmed Ghazy, Bryant Gipson, Andrew Goodman, Dawid Górny, Sven Gowal, Khyatti Gupta, Yoni Halpern, Yena Han, Susan Hao, Jamie Hayes, Heek, Jonathan, Amir Hertz, Ed Hirst, Hoogeboom, Emiel, Tingbo Hou, Heidi Howard, Mohamed Ibrahim, Dirichi Ike-Njoku, Joana Iljazi, Vlad Ionescu, William M. Isaac, Reena Jana, Gemma Jennings, Donovon Jenson, Xuhui Jia, Kerry Jones, Xiaoen Ju, Ivana Kajić, Kaplanis, Christos, Burcu Karagol Ayan, Jacob Kelly, Suraj Kothawade, Christina Kouridi, Sofia Ira Ktena, Jolanda Kumakaw, Dana Kurniawan, Dmitry Lagun, Lily Lavitas, Jason Lee, Tao Li, Marco Liang, Maggie Li-Calis, Yuchi Liu, Javier Lopez Alberca, Lorrain, Matthieu Kim, Peggy Lu, Kristian Lum, Yukun Ma, Chase Malik, John W. Mellor, Mensink, Thomas, Inbar Mosseri, Tom Murray, Aida Nematzadeh, Paul Nicholas, Nørly, Signe, João Gabriel Oliveira, Guillermo Ortiz-Jimenez, Michela Paganini, Tom Le Paine, Roni Paiss, Alicia Parrish, Anne Peckham, Vikas Peswani, Igor Petrovski, Tobias Pfaff, Alex Pirozhenko, Ryan Poplin, Utsav Prabhu, Qi Yuan, Matthew Rahtz, Cyrus Rashtchian, Charvi Rastogi, Amit Raul, Ali Razavi, Sylvestre-Alvise Rebuffi, Susanna Ricco, Felix Riedel, Dirk Robinson, Pankaj Rohatgi, Bill Rosgen, Sarah Rumbley, Moonkyung Ryu, Anthony Salgado, Salimans, Tim, Sahil Singla, Florian Schroff, Candice Schumann, Tanmay Shah, Shaw, Eleni, Shaw, Gregory, Brendan Shillingford, Kaushik Shivakumar, Dennis Shtatnov, Zach Singer, Evgeny Sluzhaev, Valerii Sokolov, Thibault Sottiaux, Florian Stimberg, Brad Stone, David Stutz, Yu-Chuan Su, Eric Tabellion, Shuai Tang, David Tao, Kurt Thomas, Gregory Thornton, Andeep Toor, Cristian Udrescu, Aayush Upadhyay, Cristina Nader Vasconcelos, Alex Vasiloff, Andrey Voynov, Amanda Walker, Luyu Wang, Miaosen Wang, Simon Wang, Stanley Wang, Qifei Wang, Y. Wang, Ágoston Weisz, Olivia Wiles, Chenxia Wu, Xingyu Federico Xu, A. Xue, Jianbo Yang, Yu Luo, Mete Yurtoglu, Ali Zand, Han Zhang, Jiageng Zhang, Catherine Zhao, Adilet Zhaxybay, Miao Zhou, S. J. Zhu, Zhenkai Zhu, Dawn Bloxwich, Mahyar Bordbar, Luis C. Cobo, Eli Collins, Shengyang Dai, Tulsee Doshi, Anca D. Dragan, Douglas Eck, Demis Hassabis, Sissie Hsiao, T Hume, Koray Kavukcuoglu, Helen King, Jack Krawczyk, Yeqing Li, Kathy Meier-Hellstern, András Orbán, Yury Pinsky, Amar Subramanya, Oriol Vinyals, Ting Yu, Yori Zwólš - arXiv 2024 cited by 143

We introduce Imagen 3, a latent diffusion model that generates high quality images from text prompts. We describe our quality and responsibility evaluations. Imagen 3 is preferred over other state-of-the-art (SOTA) models at the time of evaluation. In addition, we discuss issues around safety and representation, as well as methods we used to minimize the potential harm of our models.