Skip to main content

Research

DALL·E 3

DALL·E 3 understands significantly more nuance and detail than our previous systems, allowing you to easily translate your ideas into 
exceptionally accurate images.

Try in ChatGPT(opens in a new window)
A Dutch still life featuring an arrangement of tulips in a fluted vase. The lighting in the scene is subtle, casting gentle highlights on the flowers and emphasizing their delicate textures and natural beauty.
White Cycladic houses with blue accents and vibrant magenta bougainvillea in a serene Greek island setting.
An illustration of an avocado sitting in a therapist's chair, saying 'I just feel so empty inside' with a pit-sized hole in its center. The therapist, a spoon, scribbles notes.
A 2D animation of a folk music band composed of anthropomorphic autumn leaves, each playing traditional bluegrass instruments, amidst a rustic forest setting dappled with the soft light of a harvest moon.
sky
A middle-aged Tongan woman twirls against a deep black backdrop, her curly hair stormy. Her attire, like marble and porcelain shards, catches the light, creating a dreamlike, fragmented yet fluid scene.
A spacious, serene room influenced by modern Japanese aesthetics with a view of a cityscape outside of the window.
Photo of a lychee-inspired spherical chair, with a bumpy white exterior and plush interior, set against a tropical wallpaper.
A tranquil, anime-style koi pond in a serene Japanese garden, featuring blossoming cherry trees.
cat-nap

About DALL·E 3

DALL·E 3 is now available to all ChatGPT users, as well as to developers through our API.

Modern text-to-image systems have a tendency to ignore words or descriptions, forcing users to learn prompt engineering. DALL·E 3 represents a leap forward in our ability to generate images that exactly adhere to the text you provide.

A woman underneath a cherry blossom tree is setting up a picnic on a yellow checkered blanket around sunset. Behind her, a small, calm body of water containing a boat with 4 figures on their way to a Pagoda in the middle of the water.
Even with the same prompt, DALL·E 3 significantly improves upon DALL·E 2.
An expressive painting of a chocolate chip cooking being dunked in a glass of milk. It sits next to an image created by Dall-E 3 depicting the same thing.

DALL·E 2 · An expressive oil painting of a chocolate chip cookie being dipped in a glass of milk, depicted as an explosion of flavors.

An expressive painting of a chocolate chip cooking being dunked in a glass of milk. It sits next to an image created by DALL.E 2 depicting the same thing.

DALL·E 3 · An expressive oil painting of a chocolate chip cookie being dipped in a glass of milk, depicted as an explosion of flavors.

DALL·E 3 is built natively on ChatGPT, which lets you use ChatGPT as a brainstorming partner and refiner of your prompts. Just ask ChatGPT what you want to see in anything from a simple sentence to a detailed paragraph.

When prompted with an idea, ChatGPT will automatically generate tailored, detailed prompts for DALL·E 3 that bring your idea to life. If you like a particular image, but it’s not quite right, you can ask ChatGPT to make tweaks with just a few words.

DALL·E 3 will be available to ChatGPT Plus and Enterprise customers in early October. As with DALL·E 2, the images you create with DALL·E 3 are yours to use and you don't need our permission to reprint, sell or merchandise them.

Focus on safety

Like previous versions, we’ve taken steps to limit DALL·E 3’s ability to generate violent, adult, or hateful content.

  • Preventing harmful generations

    DALL·E 3 has mitigations to decline requests that ask for a public figure by name. We improved safety performance in risk areas like generation of public figures and harmful biases related to visual over/under-representation, in partnership with red teamers—domain experts who stress-test the model—to help inform our risk assessment and mitigation efforts in areas like propaganda and misinformation.

  • Internal testing

    We’re also researching the best ways to help people identify when an image was created with AI. We’re experimenting with a provenance classifier—a new internal tool that can help us identify whether or not an image was generated by DALL·E 3—and hope to use this tool to better understand the ways generated images might be used. We’ll share more soon.

Creative control

DALL·E 3 is designed to decline requests that ask for an image in the style of a living artist. Creators can now also opt their images out from training of our future image generation models.

Read research paper(opens in a new window)Opt out your images (opens in a new window)
Artistic textile representation of a beach scene with deep blue and turquoise yarn waves, sandy yarn beach, and tan yarn palm trees under a white yarn sun.
A small felt star sits is surrounded by dark clouds.
A large cactus made of Lego sits in the middle of a desert scene. Smaller cacti and sand surround the main cactus, also made with Lego.
Sculptural artwork of a woman's face constructed from paper and ceramic shards, capturing a moment of disintegration with flowing hair and vivid blue and white fragments.
A bright, colorful scene foused on a papercraft goat standing infront of a small pond. There are trees, castles, a rainbow, and other creatures behind the goat, also depicted as papercraft.
A realistic dome with stained glass windows sits in the middle of the desert, surrounded by cacti and other desert foliage.
A closeup image of a large red cap mushroom made of clay. Next to it is a much smaller red cap mushroom.
An astronaut walks across an alien planet. Above them in the sky, a rocket flying over the silhouette of another planet.
A yellow flower in the style of classic botanical illustrations.
A realistic bowl of ramen full of many toppings, including a soft boiled egg, vegetables, and meat.
An elegant glass bowl sits on top of a table. The table cloth is white lace with a delicate floral pattern. Inside the bowl are many glass cherries. It is overly full, and some have spilled onto the table cloth.
Oceanside sunset in San Juan.
An inviting, comfortable lounge chair sitting next to an arched window with sun streaming through.
An ebroidery hoop depicts an intricate embroidery of a clown fish inside an anemone. Thread, needle, and scissors surround the hoop.
Art deco style poster advertising travel to Venus, featuring stylized clouds and mountain landscapes in shades of yellow and orange with celestial bodies in the background.
A minimap diorama of a cafe adorned with indoor plants. Wooden beams crisscross above, and a cold brew station stands out with tiny bottles and glasses.

Credits

Core research and execution

Gabriel Goh, James Betker, Li Jing, Aditya Ramesh

Research contributors—primary

Tim Brooks, Jianfeng Wang, Lindsey Li, Long Ouyang, Juntang Zhuang, Joyce Lee, Prafulla Dhariwal, Casey Chu, Joy Jiao

Research contributors—secondary

Jong Wook Kim, Alex Nichol, Yang Song, Lijuan Wang, Tao Xu

Inference optimization

Connor Holmes, Arash Bakhtiari, Umesh Chand, Zhewei Yao, Samyam Rajbhandari, Yuxiong He

Product—primary

Yufei Guo, Luke Miller, Joyce Lee, Wesam Manassra, Anton Tananaev, Chester Cho, Rachel Lim, Meenaz Merchant

Product—secondary

Dave Cummings, Rajeev Nayak, Sriya Santhanam

Safety—primary

Sandhini Agarwal, Michael Lampe, Katarina Slama, Kim Malfacini, Bilva Chandra, Ashyana-Jasmine Kachra, Rosie Campbell, Florencia Leoni Aleman, Madelaine Boyd, Shengli Hu, Johannes Heidecke

Safety—secondary

Lama Ahmad, Chelsea Carlson, Henry Head, Andrea Vallone, CJ Weinmann, Lilian Weng

Communications

Alex Baker-Whitcomb, Ryan Biddy, Ruby Chen, Thomas Degry, Niko Felix, Elie Georges, Lindsey Held, Chad Nelson, Kendra Rimbach, Natalie Summers, Justin Wang, Hannah Wong, Kayla Wood

Legal and public policy

Che Chang, Jason Kwon, Fred von Lohmann, Ashley Pantuliano, David Robinson, Tom Rubin, Thomas Stasi

Special thanks

Alec Radford, Mark Chen, Katie Mayer, Misha Bilenko, Mikhail Parakhin, Bob McGrew, Mira Murati, Greg Brockman, Sam Altman