At OpenAI, we have long believed image generation should be a primary capability of our language models. That’s why we’ve built our most advanced image generator yet into GPT‑4o. The result—image generation that is not only beautiful, but useful.
Whiteboard session Meaningful words Comic strip Science experiment
A wide image taken with a phone of a glass whiteboard, in a room overlooking the Bay Bridge. The field of view shows a woman writing, sporting a tshirt wiith a large OpenAI logo. The handwriting looks natural and a bit messy, and we see the photographer's reflection.
"Transfer between Modalities:
Suppose we directly model
p(text, pixels, sound) [equation]
with one big autoregressive transformer.
* image generation augmented with vast world knowledge
* next-level text rendering
* native in-context learning
* unified post-training stack
* varying bit-rate across modalities
* compute not adaptive"
* model compressed representations
* compose autoregressive prior with a powerful decoder"
On the bottom right of the board, she draws a diagram:
"tokens -> [transformer] -> [diffusion] -> pixels"
selfie view of the photographer, as she turns around to high five him
## Useful image generation
From the first cave paintings to modern infographics, humans have used visual imagery to communicate, persuade, and analyze—not just to decorate. Today's generative models can conjure surreal, breathtaking scenes, but struggle with the workhorse imagery people use to share and create information. From logos to diagrams, images can convey precise meaning when augmented with symbols that refer to shared language and experience.
GPT‑4o image generation excels at accurately rendering text, precisely following prompts, and leveraging 4o’s inherent knowledge base and chat context—including transforming uploaded images or using them as visual inspiration. These capabilities make it easier to create exactly the image you envision, helping you communicate more effectively through visuals and advancing image generation into a practical tool with precision and power.
## Improved capabilities
We trained our models on the joint distribution of online images and text, learning not just how images relate to language, but how they relate to each other. Combined with aggressive post-training, the resulting model has surprising visual fluency, capable of generating images that are useful, consistent, and context-aware.
A picture is worth a thousand words, but sometimes generating a few words in the right place can elevate the meaning of an image. 4o’s ability to blend precise symbols with imagery turns image generation into a tool for visual communication.
Street signs Menu Invitation
Create a photorealistic image of two witches in their 20s (one ash balayage, one with long wavy auburn hair) reading a street sign.
a city street in a random street in Williamsburg, NY with a pole covered entirely by numerous detailed street signs (e.g., street sweeping hours, parking permits required, vehicle classifications, towing rules), including few ridiculous signs at the middle: (paraphrase it to make these legitimate street signs)"Broom Parking for Witches Not Permitted in Zone C" and "Magic Carpet Loading and Unloading Only (15-Minute Limit)" and "Reindeer Parking by Permit Only (Dec 24–25)
Violators will be placed on Naughty List." The signpost is on the right of a street. Do not repeat signs. Signs must be realistic.
one witch is holding a broom and the other has a rolled-up magic carpet. They are in the foreground, back slightly turned towards the camera and head slightly tilted as they scrutinize the signs.
Composition from background to foreground:
streets + parked cars + buildings -> street sign -> witches. Characters must be closest to the camera taking the shot
### Multi-turn generation
Because image generation is now native to GPT‑4o, you can refine images through natural conversation. GPT‑4o can build upon images and text in chat context, ensuring consistency throughout. For example, if you’re designing a video game character, the character’s appearance remains coherent across multiple iterations as you refine and experiment.
Video game Concrete poem Sticker
Give this cat a detective hat and a monocle
turn this into a triple A video games made with a 4k game engine and add some User interface as overlay from a mystery RPG where we can see a health bar and a minimap at the top as well as spells at the bottom with consistent and iconography
update to a landscape image 16:9 ratio, add more spells in the UI, and unzoom the visual so that we see the cat in a third person view walking through a steampunk manhattan creating beautiful contrast and lighting like in the best triple A game, with cool-toned colors
create the interface when the player opens the menu and we see the cat's character profile with his equipment and another page showing active quests (and it should make sense in relationship with the universe worldbuilding we are describing in the image)
credit creator: Manuel Sainsily
### Instruction following
GPT‑4o’s image generation follows detailed prompts with attention to detail. While other systems struggle with ~5-8 objects, GPT‑4o can handle up to 10-20 different objects. The tighter binding of objects to their traits and relations allows for better control.
Organized objects Empty city Wine glass Invisible elephant Math equation
A square image containing a 4 row by 4 column grid containing 16 objects on a white background. Go from left to right, top to bottom. Here's the list:
6. purple infinity sign
7. black and white polka dot bowtie
9. an orange cat wearing a black baseball cap
10. a map with a treasure chest
11. a pair of googly eyes
12. a thumbs up emoji
13. a pair of scissors
14. a blue and white giraffe
15. the word "OpenAI" written in cursive
16. a rainbow-colored lightning bolt
### In-context learning
GPT‑4o can analyze and learn from user-uploaded images, seamlessly integrating their details into its context to inform image generation.
Triangle wheeled vehicle Chainsaw Woman Building
now put this in a photo taken in new york city.
Native image generation enables 4o to link its knowledge between text and images, resulting in a model that feels smarter and more efficient.
Code-generated image Cocktail recipes Weather infographic Whale guide Matcha instructions
Code Example (Three.js)
Unknown component type: {componentType} make an image of what this means to you
## Photorealism and style
Training on images reflecting a vast variety of image styles allows the model to create or transform images convincingly.
](https://images.ctfassets.net/kftzwdyauwt9/2R9czqCiP1nqec6UED0AJd/0f24e9e9299c871ffd3d5b76f5635d16/roope-car.png?w=3840&q=90&fm=webp)
A candid paparazzi-style photo of Karl Marx hurriedly walking through the parking lot of the Mall of America, glancing over his shoulder with a startled expression as he tries to avoid being photographed. He’s clutching multiple glossy shopping bags filled with luxury goods. His coat flutters behind him in the wind, and one of the bags is swinging as if he’s mid-stride. Blurred background with cars and a glowing mall entrance to emphasize motion. Flash glare from the camera partially overexposes the image, giving it a chaotic, tabloid feel.
A candid paparazzi-style photo of Karl Marx hurriedly walking through the parking lot of the Mall of America, glancing over his shoulder with a startled expression as he tries to avoid being photographed. He’s clutching multiple glossy shopping bags filled with luxury goods. His coat flutters behind him in the wind, and one of the bags is swinging as if he’s mid-stride. Blurred background with cars and a glowing mall entrance to emphasize motion. Flash glare from the camera partially overexposes the image, giving it a chaotic, tabloid feel.
A candid paparazzi-style photo of Karl Marx hurriedly walking through the parking lot of the Mall of America, glancing over his shoulder with a startled expression as he tries to avoid being photographed. He’s clutching multiple glossy shopping bags filled with luxury goods. His coat flutters behind him in the wind, and one of the bags is swinging as if he’s mid-stride. Blurred background with cars and a glowing mall entrance to emphasize motion. Flash glare from the camera partially overexposes the image, giving it a chaotic, tabloid feel.
Our model isn’t perfect. We’re aware of multiple limitations at the moment which we will work to address through model improvements after the initial launch.
Cropping Hallucinations High binding problems Precise graphing Multilingual text rendering Editing precision Dense information with small text
We’ve noticed that GPT‑4o can occasionally crop longer images, like posters, too tightly, especially near the bottom.
In line with our Model Spec, we aim to maximize creative freedom by supporting valuable use cases like game development, historical exploration, and education—while maintaining strong safety standards. At the same time, it remains as important as ever to block requests that violate those standards. Below are evaluations of additional risk areas where we're working to enable safe, high-utility content and support broader creative expression for users.
Provenance via C2PA and internal reversible searchAll generated images come with C2PA metadata, which will identify an image as coming from GPT‑4o, to provide transparency. We’ve also built an internal search tool that uses technical attributes of generations to help verify if content came from our model.
Blocking the bad stuffWe’re continuing to block requests for generated images that may violate our content policies, such as child sexual abuse materials and sexual deepfakes. When images of real people are in context, we have heightened restrictions regarding what kind of imagery can be created, with particularly robust safeguards around nudity and graphic violence. As with any launch, safety is never finished and is rather an ongoing area of investment. As we learn more about real-world use of this model, we’ll adjust our policies accordingly.
For more on our approach, visit the image generation addendum to the GPT‑4o system card.
Using reasoning to power safetySimilar to our deliberative alignment work, we’ve trained a reasoning LLM to work directly from human-written and interpretable safety specifications. We used this reasoning LLM during development to help us identify and address ambiguities in our policies. Together with our multimodal advancements and existing safety techniques developed for ChatGPT and Sora, this allows us to moderate both input text and output images against our policies.
## Access and availability
4o image generation rolls out starting today to Plus, Pro, Team, and Free users as the default image generator in ChatGPT, with access coming soon to Enterprise and Edu. It’s also available to use in Sora. For those who hold a special place in their hearts for DALL·E, it can still be accessed through a dedicated DALL·E GPT.
Developers will soon be able to generate images with GPT‑4o via the API, with access rolling out in the next few weeks.
Creating and customizing images is as simple as chatting using GPT‑4o - just describe what you need, including any specifics like aspect ratio, exact colors using hex codes, or a transparent background. Because this model creates more detailed pictures, images take longer to render, often up to one minute.
](https://images.ctfassets.net/kftzwdyauwt9/4mDKmV3ex9OT8wyAFGDAQS/1b0e1baacb80125e1f92e66dbdf1e32a/Alex_Duffy1.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/30DNW3QcEb1BosJhJqPAfA/56e4708045e63d40d5fe31c122da2bfb/August_Kamp_2.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/2ukMfLwQHGEnwMbS43M3Hf/6f5fa57419fdc16ca603e41c1ac290ff/August_Kamp_3.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/2KZaGKW5emVRwnYBMcMYCP/560cd7d513aed92b4a943b66b6b5e836/August_Kamp_4.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/2PVNlktDwuJJgAlrviWfF1/bf374f33e21c41e770068f4f66a22394/August_Kamp_5.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/39oS3hSQqMSqHHNAS0q3DB/0624bcc17a3e7a3fd318a1eb5c63146e/August_Kamp.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/5WdHD3ToXx1mj13bjDhdQh/46c283533309492585f3538a5ed3a2fd/August_Kamp_1_.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/37BlQeBhtmTAazdT7LyRIU/7e6472d3ba12c22748cf14a670c0a725/Copy_of_Isa.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/2pRf2V2Zmd1YF7GfBtfRwG/92ac8188795fcdd4be9152a27a971289/Copy_of_Isa2.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/2D1UY4SXAHAxN0uCGT4KCd/43da3a5152c1a823fdf2bed6acea5cf8/Derya_Unutmaz1.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/1jRz4YFkVwGIVQC6yz5DJV/af2ed5507df32860b8b82a4a326c437e/Derya2.jpg?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/1hakInZjBH5SENKVLD68Gl/0140eb82eae9e5cd2f1fbc7ef8f5c46c/Derya3.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/3viXLb1u1ZsUXju6gc0Izh/51b37635165df801077399b26e6c0ff5/Elene_6.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/6EoS1QOv0KOi4aESduy0cU/12705b1ca86abce06bf7366f98e9a8c7/Elene_Chekurishvili.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/5sKaN7iVvtLlzGJQtFmfMg/4ef6d51d2e54d4effd3019401401deb1/Elene3.jpeg?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/1iA7pHLA84KDCRIuoG5pTk/ae8e52600bfbd53a10a749dcd78b2382/Elene4.jpeg?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/5MPmWWYE3fDk6M5QSpA0X8/ac729246785fc8d052be4427085bbcda/Elene5.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/2CrXaGuZ3fcCIyKNcDaiRr/26fb7c949919a2de82f7b8340ad4e708/Eugenio_Marongiu.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/6JJh92fHC6diXnnj0rz6DP/53a43e30200729a648cfda1faa6328a5/Eugenio2.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/tZr3EpmNfrkZBQAIYMffM/d85415f7a01a49718adf2509bb9ad8f1/Minh_Do1.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/1TQS4fCbgIOjdnML4u6i5o/bc81b9ff76e503e32b69dbf447a967e6/niceaunties.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/1TYYxCnSFWzwoEOHJ7OlfC/767ce4ec94b972138598cce0be1e8d79/Roope_2.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/2Gr22uAGGIQjmDBQt2ccKx/620417fa3b9667f7e95a1fd98c692203/Roope_3.png?w=3840&q=90&fm=webp)
](https://images.ctfassets.net/kftzwdyauwt9/5neXFSFNWbbdhruFManjbU/3a084e08790a90af52cb7005372539b9/Roope_Rainisto1.png?w=3840&q=90&fm=webp)
credit creator: Alex Duffy
credit creator: Alex Duffy
credit creator: Alex Duffy
## Livestream replay
Gabriel Goh: Image Generation
Jackie Shannon: ChatGPT Product
Mengchao Zhong, Wayne Chang: ChatGPT Engineering
Rohan Sahai: Sora Product and Engineering
Brendan Quinn, Tomer Kaftan: Inference
Prafulla Dhariwal: Multimodal Organization
Foundational Research
Allan Jabri, David Medina, Gabriel Goh, Kenji Hata, Lu Liu, Prafulla Dhariwal
Aditya Ramesh, Alex Nichol, Casey Chu, Cheng Lu, Dian Ang Yap, Heewoo Jun, James Betker, Jianfeng Wang, Long Ouyang, Li Jing, Wesam Manassra
Research Contributors
Aiden Low, Brandon McKinzie, Charlie Nash, Huiwen Chang, Ishaan Gulrajani, Jamie Kiros, Ji Lin, Kshitij Gupta, Yang Song
Multimodal Organization
Andrew Gibiansky, Yang Lu
Gildas Chabot, James Park Lennon
Arshi Bhatnagar, Dragos Oprica, Rohan Kshirsagar, Spencer Papay, Szi-chieh Yu, Wesam Manassra, Yilei Qian
Hazel Byrne, Jennifer Luckenbill, Mariano López
Brendan Quinn, Tomer Kaftan
Alyssa Huang, Jacob Menick, Nick Stathas, Ruslan Vasilev, Stanley Hsieh
ChatGPT Product Lead
ChatGPT Engineering Leads
Mengchao Zhong, Wayne Chang
Andrew Sima, Annie Cheng, Benjamin Goh, Boyang Niu, Dian Ang Yap, Duc Tran, Edede Oiwoh, Eric Zhang, Ethan Chang, Jeffrey Dunham, Jay Chen, Kan Wu, Karen Li, Kelly Stirman, Mengyuan Xu, Michelle Qin, Ola Okelola, Pedro Aguilar, Rocky Smith, Rohit Ramchandani, Sara Culver, Sean Fitzgerald, Vlad Fomenko, Wanning Jiang, Wesam Manassra, Xiaolin Hao, Yilei Qian
Rohan Sahai, Wesam Manassra
Sora Product and Engineering
Boyang Niu, David Schnurr, Gilman Tolle, Joe Taylor, Joey Flynn, Mike Starr, Rajeev Nayak, Rohan Sahai, Wesam Manassra
Alex Beutel, Andrea Vallone, Botao Hao, Brendan Quinn, Cameron Raymond, Chong Zhang, David Robinson, Eric Wallace, Filippo Raso, Huiwen Chang, Ian Kivlichan, Irina Kofman, Keren Gu-Lemberg, Kristen Ying, Madelaine Boyd, Meghan Shah, Michael Lampe, Owen Campbell-Moore, Rohan Sahai, Rodrigo Riaza Perez, Sam Toizer, Sandhini Agarwal, Troy Peterson
Adam Cohen, Adam Wells, Ally Bennett, Ashley Pantuliano, Carolina Paz, Claudia Fischer, Declan Grabb, Gaby Sacramone-Lutz, Lauren Jonas, Ryan Beiermeister, Shiao Lee, Tom Stasi, Tyce Walters, Ziad Reslan, Zoe Stoll
## Marketing & Comms
Comms and Marketing Leads
Minnia Feng, Natalie Summers, Taya Christianson
Alex Baker-Whitcomb, Ashley Tyra, Bailey Richardson, Gaby Raila, Marselus Cayton, Scott Ethersmith, Souki Mansoor
## Design & Creative
Kendra Rimbach, Veit Moeller
Adam Brandon, Adam Koppel, Angela Baek, Cary Hudson, Dana Palmie, Freddie Sulit, Jeffrey Sabin Matsumoto, Leyan Lo, Matt Nichols, Thomas Degry, Vanessa Antonia Schefke, Yara Khakbaz
Aditya Ramesh, Aidan Clark, Alex Beutel, Ben Newhouse, Ben Rossen, Che Chang, Greg Brockman, Hannah Wong, Ishaan Singal, Jason Kwon, Jiacheng Feng, Jiahui Yu, Joanne Jang, Johannes Heidecke, Kevin Weil, Mark Chen, Mia Glaese, Nick Turley, Raul Puri, Reiichiro Nakano, Rui Shu, Sam Altman, Shuchao Bi, Vinnie Monaco
Our Research * Research Index * Research Overview * Research Residency * OpenAI for Science * Economic Research
Latest Advancements * GPT-5.3 Instant * GPT-5.3-Codex * GPT-5 * Codex
Safety * Safety Approach * Security & Privacy * Trust & Transparency
ChatGPT * Explore ChatGPT(opens in a new window) * Business * Enterprise * Education * Pricing(opens in a new window) * Download(opens in a new window)
Sora * Sora Overview * Features * Pricing * Sora log in(opens in a new window)
API Platform * Platform Overview * Pricing * API log in(opens in a new window) * Documentation(opens in a new window) * Developer Forum(opens in a new window)
For Business * Business Overview * Solutions * Contact Sales
Company * About Us * Our Charter * Foundation * Careers * Brand
Support * Help Center(opens in a new window)
More * News * Stories * Livestreams * Podcast * RSS
Terms & Policies * Terms of Use * Privacy Policy * Other Policies
(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)
OpenAI © 2015–2026 Manage Cookies
English United States
