OpenAI introduces two new GPT-3 models: CLIP, which classifies images into categories from arbitrary text, and DALL·E, which can generate images from text
With GPT-3, OpenAI showed that a single deep-learning model could be trained to use language in a variety of ways simply by throwing it vast amounts of text.
MIT Technology Review Will Heaven
Related Coverage
- DALL·E: Creating Images from Text OpenAI · Justin Jay Wang
- AI draws dog-walking baby radish in a tutu BBC · Jane Wakefield
- Say hello to OpenAI's DALL-E, a GPT-3-powered bot that creates weird images from text The Next Web · Thomas Macaulay
- AI illustrator draws imaginative pictures to go with text captions New Scientist · Chris Stokel-Walker
- Neural network creates images from text FlowingData · Nathan Yau
- OpenAI's DALL ·E borrows from the GPT-3 and creates high-fidelity images from text Neowin · Ather Fawaz
- DALL ·E by OpenAI: Creating — Images from Text — It's the 5th of January 2021 … Towards Data Science · Vlad Alex
- OpenAI's DALL-E creates plausible images of literally anything you ask it to TechCrunch · Devin Coldewey
- For Its Latest Trick, OpenAI's GPT-3 Generates Images From Text Captions Synced
- OpenAI's new model can draw images from a written description Axios · Bryan Walsh
- OpenAI debuts DALL-E for generating images from text VentureBeat · Khari Johnson
Analysis
Discussion
-
@calebwatney
Caleb Watney
on x
RIP stock photography https://openai.com/... https://twitter.com/...
-
@deljohnsonvc
Del Johnson
on x
I've gently suggested that this sort of technology will make many of the current startup ideas I see being pitched completely obsolete. Follow this closely. https://twitter.com/...
-
@danielrakh
@danielrakh
on x
People think AI is coming for truck drivers first? Boy do i have news for you... https://twitter.com/...
-
@dillonliam
Liam Dillon
on x
Tag yourself. I'm Gamer Avo Chair second row, second from left. I'm staying the hell away from Giant Pit Avo Chair bottom row middle https://www.technologyreview.com/ ... https://twitter.com/...
-
@neil_chilson
Neil Chilson
on x
How long until twitter's little GIF widget actually generates the GIFs? I'm sick of no good results for “Exasperated and tired dachshund wearing red bowtie and pointing emphatically at text of 47 U.S.C. § 230.” https://twitter.com/...
-
@adamludwin
Adam Ludwin
on x
humans had a good run https://twitter.com/...
-
@dflieb
David Lieb
on x
We on Google Photos spend a lot of time on the inverse of this, and I'll say, this is quite impressive. https://twitter.com/...
-
@gdb
Greg Brockman
on x
CLIP — our new neural network for classifying images into categories based on arbitrary text. Works like GPT-3's semantic search, but for images: https://andrewmayneblog.wordpress.com/ ... Maybe a path towards vision nets that don't make silly mistakes: https://openai.com/... htt…
-
@mark_riedl
Mark O. Riedl
on x
“DALL·E is the kind of system that Riedl imagined submitting to the Lovelace 2.0 test, a thought experiment... for measuring artificial intelligence. It assumes that one mark of intelligence is the ability to blend concepts in creative ways.” https://twitter.com/...
-
@ilyasut
Ilya Sutskever
on x
An NN takes a list of category names, and outputs (in a zero-shot manner) a visual classifier. It beats RN50 on ImageNet zero-shot, while being far more robust to unusual images: https://openai.com/... https://twitter.com/...
-
@humansofflat
@humansofflat
on x
They deliberately castrated this tool so people wouldn't use it to make porn https://twitter.com/...
-
@0x49fa98
Zero HP Lovecraft
on x
They limited the possible inputs to this tool out of fear of what it could show you. Its generative capacity is limitless, infinite, obscene. You can ask it for anything Abby Shapiro's nudes. The true face of any anon. A picture of your future wife. The girl reading this. https:/…
-
@fcain
Fraser Cain
on x
This is absolutely mind melting. Open AI can generate nearly unlimited images of a chair that looks like an avocado. https://www.technologyreview.com/ ...
-
@liv_boeree
Liv Boeree
on x
Wow - this AI can now generate unique images *entirely* from text prompts. Impressive, although somewhat disappointed the available prompts are so... vanilla. Also GG, illustrators https://twitter.com/...
-
@techreview
@techreview
on x
Researchers asked an AI model to draw “an avocado armchair.” The results show how we might make artificial intelligence smarter. https://www.technologyreview.com/ ...
-
@wongmjane
Jane Manchun Wong
on x
oh yes, evil boba 🧋😈 https://openai.com/... https://twitter.com/...
-
@sama
Sam Altman
on x
I was going to show a few more examples but honestly it's just worth 5 minutes of your time to go play around with different combinations: https://openai.com/...
-
@sama
Sam Altman
on x
And, for fun, generated images of “an illustration of a baby shark in a wizard hat wielding a blue light saber”. (You can try other combinations here: https://openai.com/...) https://twitter.com/...
-
@km
Kanyi Maqubela
on x
This is worth a close look for *anybody* curious about the future. So many creative processes stand to be changed. https://twitter.com/...
-
@viss
@viss
on x
... i wanna get into this and see if it'll write assessment reports for me. but im gonna start with using it to do all the slides for my next con talk, which will be “how to vet your security vendors” https://twitter.com/...
-
@jonathanberte
Jonathan Berte
on x
What's the future of creativity and intellectual property rights if an AI model generates the next chair design? https://www.technologyreview.com/ ...
-
@esyudkowsky
Eliezer Yudkowsky
on x
Consider this your notice, if you're a manga artist: you have N years left before you're out of a job. I wish that I had any grasp whatsoever how to relate N to announcements like these. My initial sense is N=2, wisely adjusted upwards to “actually after the end of the world”. ht…
-
@mmasnick
Mike Masnick
on x
I, for one, am looking forward to the copyright lawsuits over who holds the copyright for these images (in many cases the answer should be “no one, they're public domain"). https://twitter.com/...