OpenAI’s DALL-E 2: Even More Beautiful Results! 🤯

❤️ Train a neural network and track your experiments with Weights & Biases here: 📝 The paper “Hierarchical Text-Conditional Image Generation with CLIP Latents“ is available here: 📝 Our Separable Subsurface Scattering paper with Activision-Blizzard: 📝Our earlier papers with the caustics: Try it out: (runs through gradio, which is pretty cool, check it out!) ❤️ Watch these videos in early access on our Patreon page or join us here on YouTube: - - 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Balfanz, Alex Haro, Andrew Melnychuk, Benji Rabhan, Bryan Learn, B Shang, Christian Ahlin, Eric Martel, Geronimo Moralez, Gordon Child, Ivo Galic, Jace O’Brien, Jack Lukic, Javier Bustamante, John Le, Jonas, Jonathan, Kenneth Davis, Klaus Busse, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Michael Albrecht, Michael Tedder, Nevin Spoljaric, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Rajarshi Nigam, Ramsey Elbasheer, Steef, Taras Bobrovytsky, Ted Johnson, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi. If you wish to appear here or pick up other perks, click here: Thumbnail background design: Felícia Zsolnai-Fehér - 00:00 What is DALL-E 2? 01:40 DALL-E 1 vs DALL-E 2 02:15 1 - It can make videos 03:04 2 - Leonardo da Apple 03:19 3 - Robot learns a new language 03:28 4 - New AI-generated drinks! 04:12 5 - Toilet car 04:27 6 - Lightbulbs! 04:56 7 - Murals 05:11 8 - Darth Ant 05:23 9 - Text! 06:14 10 - Pro photography 06:28 Subsurface scattering! 07:10 Try it out yourself! 07:45 Changing the world Tweet sources: Fantasy novel: Leonardo: Encyclopedia: Modernize: Robot learning: Drinks: Toilet car: Lightbulb: Murals: Darth Ant: Sign: Hand: Károly Zsolnai-Fehér’s links: Instagram: Twitter: Web: ~zsolnai/