Posted by
Imagen 3 is our highest quality text-to-image model, capable of generating images with even better detail, richer lighting and fewer distracting artifacts than our previous models.
We’ve significantly improved Imagen 3’s ability to understand prompts, which helps the models generate a wide range of visual styles and capture small details from longer prompts.
To be even more useful, Imagen 3 will be available in multiple versions, each optimized for different types of tasks, from generating quick sketches to high-resolution images.
Starting today, Imagen 3 is available for select creators as a private preview inside ImageFX, and you can sign up to join the waitlist. Imagen 3 is also coming soon to Vertex AI.
Greater versatility and prompt understanding
We’ve designed Imagen 3 to generate high-quality images in a wide range of formats and styles, from photorealistic landscapes to richly textured oil paintings or whimsical claymation scenes.
Imagen 3 also understands prompts written in natural, everyday language, making it easier to get the output you want without complex prompt engineering.
To help Imagen 3 capture nuances like specific camera angles or compositions in long, complex prompts, we added richer detail to the caption of each image in its training data. Given better information to learn from, Imagen 3 more accurately generates a wide range of subjects and styles.
Higher quality images
Imagen 3 generates visually rich, high-quality images, with good lighting and composition. It can accurately render small details like the fine wrinkles on a person’s hand, and complex textures like a knitted stuffed toy elephant.
Better text rendering
We’ve also significantly improved its text rendering capabilities, opening up new possibilities for use cases like stylized birthday cards, presentations and more.
Built and deployed with our latest safety and responsibility innovations
Imagen 3 was built with our latest safety and responsibility innovations, from data and model development to production.
We used extensive filtering and data labeling to minimize harmful content in datasets and reduced the likelihood of harmful outputs. We also conducted red teaming and evaluations on topics including fairness, bias and content safety.
We’re deploying Imagen 3 with our latest privacy, safety and security technologies, including our innovative watermarking tool SynthID — which embeds a digital watermark directly into the pixels of the image, making it detectable for identification but imperceptible to the human eye.
Over the next months, we’ll make Imagen 2’s popular editing features, like inpainting and outpainting, available in Imagen 3. And we’ll be expanding Imagen 3’s availability across Google products, like the Gemini app and web experience, Workspace, Ads and more.
Acknowledgements
Core contributors
Jason Baldridge, Jakob Bauer, Mukul Bhutani, Nicole Brichtova, Andrew Bunner, Kelvin Chan, Yichang Chen, Sergio Gómez Colmenarejo, Sander Dieleman, Yuqing Du, Zach Eaton-Rosen, Hongliang Fei, Yilin Gao, Evgeny Gladchenko, Mandy Guo, Alex Haig, Will Hawkins, Hexiang (Frank) Hu, Huilian Huang, Tobenna Peter Igwe, Christos Kaplanis, Siavash Khodadadeh, Yelin Kim, Ksenia Konyushkova, Karol Langner, Eric Lau, Shixin Luo, Soňa Mokrá, Henna Nandwani, Yasumasa Onoe, Aäron van den Oord, Zarana Parekh, Jordi Pont-Tuset, Hang Qi, Rui Qian, Deepak Ramachandran, Abdullah Rashwan, Robert Riachi, Hansa Srinivasan, Srivatsan Srinivasan, Robin Strudel, Benigno Uria, Oliver Wang, Su Wang, Austin Waters, Chris Wolff, Auriel Wright, Zhisheng Xiao, Keyang Xu, Marc van Zee, Junlin Zhang, Katie Zhang, Wenlei Zhou and Konrad Zolna.
Contributors
Ola Aboubakar, Canfer Akbulut, Javier Lopez Alberca, Nina Anderson, Marco Andreetto, Lora Aroyo, Burcu Karagol Ayan, Ben Bariach, Sherry Ben, Dana Berman, Irina Blok, Pankil Botadra, Jenny Brennan, Karla Brown, Elie Bursztein, Viral Carpenter, Norman Casagrande, Ming-Wei Chang, Solomon Chang, Shamik Chaudhuri, Tony Chen, John Choi, Yu-Chuan Su, Dmitry Churbanau, Nathan Clement, Matan Cohen, Forrester Cole, Vincent Du, Praneet Dutta, Tom Eccles, Ndidi Elue, Ashley Feden, Shlomi Fruchter, Frankie Garcia, Roopal Garg, Ahmed Ghazy, Bryant Gipson, Dawid Górny, Yoni Halpern, Susan Hao, Amir Hertz, Ed Hirst, Tingbo Hou, Mohamed Ibrahim, Dirichi Ike-Njoku, Vlad Ionescu, William Isaac, Xuhui Jia, Gemma Jennings, Donovon Jenson, Kerry Jones, Suraj Kothawade, Jolanda Kumakaw, Dana Kurniawan, Dmitry Lagun, Tao Li, Maggie Li-Calis, Yuchi Liu, Kristian Lum, Chase Malik, John Mellor, Inbar Mosseri, Tom Murray, Aida Nematzadeh, Paul Nicholas, João Gabriel Oliveira, Michela Paganini, Roni Paiss, Alicia Parrish, Anne Peckham, Tobias Pfaff, Alex Pirozhenko, Ryan Poplin, Utsav Prabhu, Yuan Qi, Cyrus Rashtchian, Charvi Rastogi, Amit Raul, Ali Razavi, Susanna Ricco, Felix Riedel, Dirk Robinson, Pankaj Rohatgi, Bill Rosgen, Sarah Rumbley, Anthony Salgado, Florian Schroff, Candice Schumann, Tanmay Shah, Kaushik Shivakumar, Dennis Shtatnov, Zach Singer, Thibault Sottiaux, Brad Stone, Eric Tabellion, Shuai Tang, David Tao, Kurt Thomas, Andeep Tor, Aayush Upadhyay, Cristina Vasconcelos, Andrey Voynov, Amanda Walker, Miaosen Wang, Simon Wang, Stanley Wang, Qifei Wang, Yuxiao Wang, Olivia Wiles, Mete Yurtoglu, Andrew Xue, Ali Zand, Han Zhang, Catherine Zhao, Miao Zhou, Shengqi Zhu and Zhenkai Zhu
Advisors
Dawn Bloxwich, Mahyar Bordbar, Luis C. Cobo, Eli Collins, Tulsee Doshi, Anca Dragan, Douglas Eck, Nando de Freitas, Demis Hassabis, Tom Hume, Koray Kavukcuoglu, Helen King, Yeqing Li, Kathy Meier-Hellstern, Oriol Vinyals and Yori Zwols