DALL•E Mini is an open-source version of OpenAI's DALL•E and DALL•E 2

  • Description

    DALL·E Mini is an open-source AI model – created by Boris Dayma and based off of OpenAI’s DALL·E and DALL·E 2 – that can generate images from any prompt you give it.

    DALL·E Mini is trained by looking at millions of images from the internet with their associated captions. Over time, it learns how to draw an image from a text prompt.

    Some of the concepts are learnt from memory as it may have seen similar images. However, it can also learn how to create unique images that don't exist such as "the Eiffel tower is landing on the moon" by combining multiple concepts together.

    Accomplice uses the DALL·E Mega training set, which is the largest version of DALL·E Mini, trained and contains several improvements over the original DALL·E Mini.

    NOTE: DALL·E Mini is still training and will continue improving over time.

  • Batch size

    This model creates 6 images per credit

  • Created by

    Last built about 1 month ago



Browse images created using DALL•E Mini

a dog dribbling a basketball
the sounds of my of dreams painted by remedios varo
a tiger wearing sunglasses
a blue jay with a high top fade
Draymond Green in royal blue and yellow by Andy Warhol
dinosaur in a post apocalyptic wasteland
Daft Punk eating a tall stack of pancakes
huge shark with other fish in an aquarium
Jesus Christ suffering on the cross to save us from our sins
cheeseburger driving a car
Watercolor Wondrous Futurism Cat
Chris Hemsworth by Shepard Fairey
Tom Hiddleston in green and gold by Shepard Fairey
4th of july celebration parade
3d photorealistic robot head on black background

Try this model for free

Signup today to use on this and any of the other models Accomplice has to offer

Start creating