OpenAI DALL·E: Creating Images from Text
Publication Title
OpenAIPublication/Creation Date
January 5 2021Creators/Contributors
OpenAI (creator)Aditya Ramesh (creator)
Mikhail Pavlov (creator)
Gabriel Goh (creator)
Scott Gray (creator)
Media Type
Corporate PaperPersuasive Intent
AdvertisementDiscursive Type
InventionsDescription
"DALL·E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions, using a dataset of text–image pairs. We’ve found that it has a diverse set of capabilities, including creating anthropomorphized versions of animals and objects, combining unrelated concepts in plausible ways, rendering text, and applying transformations to existing images."HCI Platform
OtherTechnology Keywords
Artificial Intelligence (AI), Neural Networks, Transformers, Text-to-Image Generation, Generative Adversarial Networks (GAN), Natural Language Processing (NLP)Source
https://openai.com/blog/dall-e/Related Objects
Language Models are Few-Shot Learners (OpenAI GPT-3)WALL-E: Our Disappointing Future
Why everyone is talking about an image generator released by an Elon Musk-backed A.I. lab
GPT-4 Will Have 100 Trillion Parameters — 500x the Size of GPT-3
Artificial General Intelligence Is Not as Imminent as You Might Think
DeepMind researcher claims new ‘Gato’ AI could lead to AGI, says ‘the game is over!’
DALL·E 2 Explained