As usual with deep learning, scaling up is paying off.
Show this thread
DALL-E is the kind of application that you'd expect deep learning to be able to pull off in theory (people have been building various early prototype of text-guided image generation since 2015) that becomes really magical when done at a crazy scale.
-
-
-
In the future, we'll have applications that generate photorealistic movies from a script, or new video games from a description. It's only a matter of years at this point.https://twitter.com/fchollet/status/1294413865610956800 …
Show this thread -
One application that I hope someone will build within 15 years: high-fidelity renderings of your dreams from EEG recordings.https://twitter.com/fchollet/status/475533363793498112 …
Show this thread -
Something that is super tractable to build right now if you invest in the right dataset, and that would have a lot of practical value, would be a rendering aid for animated movies.https://twitter.com/fchollet/status/917529514397253633 …
Show this thread
End of conversation
New conversation -
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
the king has spoken
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Do you think this is the only way? It can be extremely practical in my domain (design) but I'd rather it could be used in a more domain specific way, with also smaller scale. But is the initial scale the necessary step to that kind of distillation?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
As an admirer of both Dali and WALL-E I gotta say BRAVO
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
So language model isn't just a smart database, right?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Definitely true. These results are of a kind where one gets the impression, something intelligent is at work.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.