Dall-E is a model based on GPT-3 that generates images using a short text caption. The name "DALL-E" is a portmanteau of the artist Salvador Dalí and Pixar’s WALL·E . For example, if you asked for an armchair like an avocado, what might it look like?
This explanatory video is quite accessible and has lots of cool images.
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.
Like GPT-3, DALL·E is a transformer language model. It receives both the text and the image as a single stream of data containing up to 1280 tokens, and is trained using maximum likelihood to generate all of the tokens, one after another.
A token is any symbol from a discrete vocabulary; for humans, each English letter is a token from a 26-letter alphabet. DALL·E’s vocabulary has tokens for both text and image concepts. Specifically, each image caption is represented using a maximum of 256 BPE-encoded tokens with a vocabulary size of 16384, and the image is represented using 1024 tokens with a vocabulary size of 8192.
The images are preprocessed to 256x256 resolution during training. Similar to VQVAE,1415 each image is compressed to a 32x32 grid of discrete latent codes using a discrete VAE1011 that we pretrained using a continuous relaxation.1213 We found that training using the relaxation obviates the need for an explicit codebook, EMA loss, or tricks like dead code revival, and can scale up to large vocabulary sizes.
This training procedure allows DALL·E to not only generate an image from scratch, but also to regenerate any rectangular region of an existing image that extends to the bottom-right corner, in a way that is consistent with the text prompt.
We recognize that work involving generative models has the potential for significant, broad societal impacts. In the future, we plan to analyze how models like DALL·E relate to societal issues like economic impact on certain work processes and professions, the potential for bias in the model outputs, and the longer term ethical challenges implied by this technology.
Well, this is a real challenge for science fiction fans. I usually enjoy making up my own mental pictures when given a science fictional description, but WALL-E could give you some discrete examples.
What quotes would you use?
Scroll down for more stories in the same category. (Story submitted 1/7/2021)
AI Note-Taking From Google Meet
'... the new typewriter that could be talked to, and which transposed the spoken sound into typed words.' - Dr. David H. Keller, 1934.
Technovelgy (that's tech-novel-gee!)
is devoted to the creative science inventions and ideas of sf authors. Look for
the Invention Category that interests
you, the Glossary, the Invention
Timeline, or see what's New.
A System To Defeat AI Face Recognition
'...points and patches of light... sliding all over their faces in a programmed manner that had been designed to foil facial recognition systems.'
Smart TVs Are Listening!
'You had to live -- did live, from habit that became instinct -- in the assumption that every sound you made was overheard...'