Jump to Content

Imagen 3

Our highest quality text-to-image model

Try it on Gemini

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.

Greater detail,
fewer artifacts

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.

  • Greater versatility and prompt understanding

  • Higher quality images

  • Better text rendering

AI generated image of three women stand together laughing, with one woman slightly out of focus in the foreground. The sun is setting behind the women, creating a lens flare and a warm glow

Prompt: Three women stand together laughing, with one woman slightly out of focus in the foreground. The sun is setting behind the women, creating a lens flare and a warm glow

AI generated image of detailed illustration of majestic lion roaring proudly in a dream-like jungle, purple white line art background, clipart on light violet paper texture

Prompt: Detailed illustration of majestic lion roaring proudly in a dream-like jungle, purple white line art background, clipart on light violet paper texture

AI generated image of a claymation scene. A medium wide shot of an elderly woman. She is wearing flowing clothing. She is standing in a lush garden watering the plants with an orange watering can

Prompt: Claymation scene. A medium wide shot of an elderly woman. She is wearing flowing clothing. She is standing in a lush garden watering the plants with an orange watering can

From Doodles to masterpieces

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.

Greater versatility and prompt understanding

Imagen 3 understands prompts written in natural, everyday language, making it easier to get the output you want without complex prompt engineering.

Numerous origami paper cranes, in various colors and patterns, float over a blurred cityscape with rooftops bathed in warm sunlight.

Trained on details,
delivering on precision

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.

The word "light" formed from colorful feathers arranged on a black background.

Prompt: Word “light” made from various colorful feathers, black background

a comic book panel of a young boy and his father on a grassy field, staring at the setting sun over a body of water. The boy says “The sun will rise again” in a speech bubble.

Prompt: A single comic book panel of a boy and his father on a grassy hill, staring at the sunset. A speech bubble points from the boy's mouth and says: The sun will rise again. Muted, late 1990s coloring style

The entrance to a grand, stone building with the words "Central Library" engraved above the doorway. The doorway is framed by two columns and features a set of large wooden doors with glass panes.

Prompt: A photograph of a stately library entrance with the words "Central Library" carved into the stone

Better text rendering

We’ve significantly improved its text rendering capabilities, opening up new possibilities for use cases like stylized birthday cards, presentations and more.

Safety from development to deployment

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.

Acknowledgements

Core contributors

Jason Baldridge, Jakob Bauer, Mukul Bhutani, Nicole Brichtova, Andrew Bunner, Kelvin Chan, 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, 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, Ali Razavi, 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, Wenlei Zhou and Konrad Zoln.

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, Xuhui Jia, Gemma Jennings, Donovon Jenson, Kerry Jones, Yelin Kim, 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, 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, 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, Kathy Meier-Hellstern, Oriol Vinyals and Yori Zwols