Two Minute Papers
❤️ Check out Perceptilabs and sign up for a free demo here: https://www.perceptilabs.com/papers
📝 The blog post on “DALL·E: Creating Images from Text” is available here:
https://openai.com/blog/dall-e/
Tweet sources:
– Code completion: https://twitter.com/gdm3000/status/1151469462614368256
– Website layout: https://twitter.com/sharifshameem/status/1283322990625607681
– Population data: https://twitter.com/pavtalk/status/1285410751092416513
🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Aleksandr Mashrabov, Alex Haro, Alex Serban, Alex Paden, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bruno Mikuš, Bryan Learn, Christian Ahlin, Eric Haddad, Eric Lau, Eric Martel, Gordon Child, Haris Husic, Jace O’Brien, Javier Bustamante, Joshua Goller, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Michael Albrecht, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Ramsey Elbasheer, Robin Graham, Steef, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh.
If you wish to support the series, click here: https://www.patreon.com/TwoMinutePapers
Thumbnail background image credits: https://pixabay.com/images/id-3202725/
Károly Zsolnai-Fehér’s links:
Instagram: https://www.instagram.com/twominutepapers/
Twitter: https://twitter.com/twominutepapers
Web: https://cg.tuwien.ac.at/~zsolnai/
#openai #dalle
This is insane, as a programmer and designer, I'm jumping up and down right now
yes but can we fap to it?
This dudes voice is kinda like … Ren’s voice
I heard"samurai-zation" and I thought, "how cool would that be…?"
Guys, let's be honest!
When we heard "make image from text", we would immediately think about 1 thing. JUST 1 THING.
So this is how they came up with all those Pokémons…
When I watch these videos I can't sleep because my mind is filled with possibilities
This will open up areas of creating media to people who have almost no skill with programming or computers in general. How is this not considered Turing complete??
I heard him say that we can try it ourselves with a link, but I don't think DALL-E is available to the public in any form yet.
Holy cow! The Matrix is coming!!
This could produce logos better than some professional logo designers I've had dealings with!
What if you put people's name there?
So it could create game assets which would make an artists job either easier or obsolete?
"Photo of the national animal of Vatican City" produces pictures of pigeons lol
Everyone knows what everyone is really thinking…..
I'm so happy i found this channel, so interesting and eye opening. I wish I was smart to create things like this :/
Can't find anywhere to properly try it out on the OpenAI website, only limited examples one can change minor aspects of; can anyone give me a link to the real deal as shown here?
This is great. I saw GPT-3 presentation video also. As a tech guy, I understood its value. I would request you to specify "how to apply this" or "how it can be used" in general terms, that will make video more appreciated by layman or common people.
He's talking like GSP in UFC
for free? i dont think so since open ai became "closedai" and you have to pay for every request
I had a thought that Instagram and face book are reverse image AI 🤔🤔
broooooooooooo
Right, the future of rule34 is here.
I need a paper to tell me which field to retrain in..
oh my this is a paradigm before us
Bro you are just killing me 🥲
That AI clearly never seen an x-ray of an owl in a field before. Could tell it was just pretending.. 4:51 😏🦉
Why no tutorial or link to website so we can try? The link you have in comments is one perceptilabs???!
I imagine that one day you will be able to generate movies with be using a given plot. Also, animes with atleast like 200 episodes it will be able too create new episodes and make up the plot using an ai that generates the plot based on the plot style and ai will use its imagination to make a good plot. And then another ai will make the episode.
As an artist it's time to learn programming and machine learning…
I wonder if this now allows someone to create a comic book without having to draw a single line.
this is literally unbelievable
KÁROLY
Can I implement it by myself from the DALL-E source code on GitHub?
I would appreciate if someone could tell me how to create my proper images from text using dalle-e. Thanks