Dall·E

Generated art from text descriptions.

OpenAI’s DALL·E 2 is an AI system that can create realistic images and art from natural language descriptions. It has 4x greater resolution than DALL·E 1, its predecessor, and various safety mitigations have been implemented to prevent misuse.DALL·E 2 uses a process called “diffusion” which starts with a pattern of random dots and gradually alters that pattern towards an image when it recognizes specific aspects of that image. It can create original, realistic images and art from a text description, combine concepts, attributes, and styles, and make realistic edits to existing images from a natural language caption. It can also take an image and create different variations of it inspired by the original.The system has been trained on a limited dataset to prevent the generation of violent, hate, and adult images. Automated and human monitoring systems also guard against misuse. DALL·E 2 has been deployed in phases based on learning from real-world use and is now available in beta. OpenAI hopes that DALL·E 2 will empower people to express themselves creatively and help us understand how advanced AI systems see and understand our world.

Ai Promptly
Submitter

Featured on March 30, 2022

Share:

H2O AI

Create, deploy and monitor ML models on a platform.