Ultra-fast option
Test dozens of ideas instantly. Imagen 4 comes with a mode that’s up to 10x faster than our previous model.
Our leading text-to-image model, engineered for creativity
Create realistic images of landscapes, plants, people and animals with true-to-life details.
Capture extreme close-ups with richer colors, textures and gradients — for images that look like they can be touched.
Imagen 4 can render diverse art styles with greater accuracy — from photo realism and impressionism to abstract and illustration.
Photorealistic images, sharper clarity, improved spelling and typography. Bring your imagination to life faster than ever before.
Test dozens of ideas instantly. Imagen 4 comes with a mode that’s up to 10x faster than our previous model.
Push the limits of creativity further than ever before with enhanced colors, styles, details and text rendering.
Imagen 4 is optimized for creativity, generating images with up to 2k resolution.
Diffusion models don’t have the real-world knowledge of LLMs. Users may still see artefacts on complicated compositions — especially in images with small faces, text rendering, and thin structures.
Imagen sometimes struggles to create centered images — like a circle perfectly aligned in the center of the image.
Imagen responds reliably to text prompts, but when it’s given nonsensical prompts (like emojis or a random string of characters), the outputs can be unpredictable.
We use extensive filtering and data labeling to minimize harmful content in datasets and reduce the likelihood of harmful outputs. We also conduct red teaming and evaluations on content safety, including child safety, and representation.
We're releasing Imagen 4 with our latest privacy, safety and security features. This includes SynthID, our tool that embeds an invisible digital watermark directly into an image, allowing it to be identified as AI generated.
Cartwheel’s text-to-animation platform uses Imagen to create new 3D character animations.
Experimenting with Imagen 3 in its AI video creation toolset.
Supercharge your creativity and productivity
Use images as prompts to visualize your ideas
The fastest path from prompt to production
Get started building with cutting-edge AI models
Test, tune, and deploy enterprise-ready generative AI
Core contributors
Gabriel Barcik, Jakob Bauer, Dana Berman, Nicole Brichtova, Lluis Castrejon, Matan Cohen, Sander Dieleman, Yuqing Du, Praneet Dutta, Jess Gallegos, Yilin Gao, Evgeny Gladchenko, Susan Hao, Ruba Haroun, Ed Hirst, Tobenna Peter Igwe, Xuhui Jia, Siavash Khodadadeh, Pavel Khrushkov, Karol Langner, Rory Lawton, Yinxiao Li, Yandong Li, Shixin Luo, Michael Mathieu, Soňa Mokrá, Aäron van den Oord, Lily Pagan, Zarana Parekh, Noam Petrank, Jordi Pont-Tuset, Hang Qi, Deepak Ramachandran, Poorva Rane, Ali Razavi, Robert Riachi, Dirk Robinson, James Thornton, Felix Riedel, Evgeny Sluzhaev, Hansa Srinivasan, Srivatsan Srinivasan, Benigno Uria, Cristina Vasconcelos, Oliver Wang, Simon Wang, Austin Waters, Daniel Winter, Chris Wolff, Zhisheng Xiao, Keyang Xu, Andrew Xue, Xin Yuan, Katie Zhang and Yang Zhao.
Contributors
Faiz Abdul, Reut Aharony, Oscar Akerlund, Marco Andreetto, Reggie Ballesteros, Ben Bariach, Praseem Banzal, Sherry Ben, Tarun Bharti, Mukul Bhutani, Jon Blanton, Irina Blok, Pankil Botadra, Jenny Brennan, Andrew Bunner, Viral Carpenter, Norman Casagrande, Kelvin Chan, Srimon Chatterjee, Yutian Chen, Ahmed Chowdhury, Shirley Chung, Salil Deshmukh, Vincent Du, Zach Eaton-Rosen, Tom Eccles, Ndidi Elue, Hongliang Fei, Frankie Garcia, Roopal Garg, Mark Graham, Bryant Gipson, Abhinash Giri, Andrew Goodman, Gitartha Goswami, Mandy Guo, Khyatti Gupta, Shashank Gupta, Shan Han, Anja Hauth, Allen He, Jonathan Heek, Amir Hertz, Emiel Hoogeboom, Cath Hope, Yedid Hoshen, Priyanka Hubli, Russell Iskander, Xiaoen Ju, Ashyana Kachra, Tariq Kane, Ori Kelner, DY Kim, Yelin Kim, Ksenia Konyushkova, Vika Koriakin, Suraj Kothawade, Dana Kurniawan, Fiona Lang, Jason Lee, Amir Lellouche, Tao Li, Xin Li, Ricky Liang, Junjie Liu, Yuchi Liu, Matthieu Kim Lorrain, Yukun Ma, Thomas Mensink, Michael Milne, Mark Murphy, Aida Nematzadeh, Signe Nørly, Yasumasa Onoe, Roni Paiss, Igor Petrovski, Andrew Pierson, Ryan Poplin, Amit Raul, Javier Rey, Susanna Ricco, Sarah Rosston, Shahriar Rouf, Nataniel Ruiz, Moonkyung Ryu, Tim Salimans, Sahil Singla, Candice Schumann, Tanmay Shah, Eleni Shaw, Gregory Shaw, Tomer Stolik , Hagai Taitelbaum, Santhosh Thangaraj, Hossein Talebi, Hannah Teufel, Nick Tombari, Andeep Toor, Utkarsh Tripathi, Cristian Udrescu, Shanthal Vasanth, Paul Vicol, Neal Wadhwa, Emma Wang, Qifei Wang, Yuxiao Wang, Ágoston Weisz, Olivia Wiles, Sanghyun Woo, Auriel Wright, Allen Wu, Chenxia Wu, Hao Xiong, Jeffrey Yang, Jimmy Yang, Shiran Zada, Dan Zhang, Catherine Zhang, John Zhang, William Zhu, Zhenkai Zhu and Martin Zlocha.
Advisors
Jason Baldridge, Dawn Bloxwich, Mahyar Bordbar, Luis C. Cobo, Eli Collins, Tulsee Doshi, Anca Dragan, Douglas Eck, Demis Hassabis, Tom Hume, Koray Kavukcuoglu, Helen King, Dmitry Lagun, Yeqing Li, Yael Pritch, Huisheng Wang, Miaosen Wang, Oriol Vinyals, Ronny Votel, Ting Yu and Yori Zwols.