What if I told you that a super-advanced Artificial Intelligence technology could generate images from text captions? That would be magic, isn’t it? However, this time, it is becoming a reality!
In this video, we’ll look at “DALL-E,” which is a neural network trained to create and draw images from text captions. Although this technology is still in development, we will explore some of the mind-boggling demonstrations and discuss the possibilities of A.I. in digital imaging.
I hope you enjoy this video. Thank you so much for watching 🙂
â–º TIMESTAMPS:
00:00 Introduction
00:55 How it works?
01:38 Simple Context Combination
04:48 Modifying Objects
06:47 Complex Object Modification
08:05 Simultaneously Controlling Multiple Objects
10:58 Comparison with Google Images
11:35 Changing the Perspective
13:09 Modify the 3D Style of an Object
14:03 Generate a 3d Head of a Well-Known Figure
15:08 X-Ray Vision
15:42 Adding Actual Text in the Scene
16:52 Fashion Designing Applications
18:02 Bizzare Combinations
19:11 Conclusion
â–º HELP US CREATE MORE FREE VIDEOS:
Support us at Patreon: https://www.patreon.com/piximperfect
â–º SHARE: https://goo.gl/IUhnUl
â–ºLET’S CONNECT:
Facebook: http://facebook.com/piximperfect
Twitter: https://twitter.com/piximperfect
Instagram: https://www.instagram.com/piximperfect
source
