Dall-E

An online marketplace enables people to buy text prompts designed to produce consistent output from the new generation of text-to-image generators.

A homebrew re-creation of OpenAI’s DALL·E model is the latest internet sensation. Craiyon has been generating around 50,000 user-prompted images daily, thanks to its ability to produce visual mashups like Darth Vader ice fishing and photorealistic Pokemon characters.

OpenAI’s text-to-image generator DALL·E 2 produces pictures with uncanny creativity on demand. Has it invented its own language as well? Ask DALL·E 2 to generate an image that includes text, and often its output will include seemingly random characters.

OpenAI’s DALL·E got an upgrade that takes in text descriptions and produces images in styles from hand-drawn to photorealistic. The new version is a rewrite from the ground up. It uses the earlier CLIP zero-shot image classifier to represent text descriptions.

While models like GPT-3 and EfficientNet, which work on text and images respectively, are responsible for some of deep learning’s highest-profile successes, approaches that find relationships between text and images made impressive

The emerging generation of trillion-parameter models needs datasets of billions of examples, but the most readily available source of examples on that scale — the web — is polluted with bias and antisocial expressions. A new study examines the issue.

Two new models show a surprisingly sharp sense of the relationship between words and images. OpenAI, the for-profit research lab, announced a pair of models that have produced impressive results in multimodal learning: DALL·E.