Ai that makes thumbnails (or any image)
Chapters
A video about using AI to generate youtube thumbnails. I explore the classic GAN method and compare it with a newer method called diffusion. One turns out to be better than the other!
Reviewed by Andrew Carr: https://twitter.com/andrew_n_carr
Disclaimer: All thumbnails were deleted after use. I do not aggregate youtube data.
The losses are not exactly inverse for the generator and discriminator because the two are not trained on the same data.
LINKS
Twitter: https://twitter.com/max_romana
Discord: https://discord.gg/ZsrAAByEnr
Patreon: https://www.patreon.com/emergentgarden
The life engine: https://thelifeengine.net
SOURCES
Original GAN Paper: https://proceedings.neurips.cc/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf
Face interpolation: https://www.youtube.com/watch?v=6E1_dgYlifc
BigGAN Paper: https://arxiv.org/abs/1809.11096
https://thispersondoesnotexist.com
Flower Gan: https://twitter.com/dvsch/status/1527890938386857984
Katydid: https://www.youtube.com/watch?v=S4Bl4zipCQk
Mantis: https://www.youtube.com/watch?v=mP6rdSaASaA
Diffusion Paper: https://arxiv.org/abs/2006.11239
Diffusion beats GANs: https://arxiv.org/abs/2105.05233?curius=520
Blog Post: https://gretel.ai/blog/diffusion-models-for-document-synthesis
Diffusion explanation: https://www.youtube.com/watch?v=HoKDTa5jHvg
Diffusion Visualization: https://twitter.com/zzznah/status/1537042940475883520
Water Diffusion: https://www.youtube.com/watch?v=polW950ZilE
Dall-E 2: https://openai.com/dall-e-2/
Imagen: https://imagen.research.google/
CogView: https://arxiv.org/abs/2105.13290
Parti: https://parti.research.google/
TIMESTAMPS
MUSIC
https://www.youtube.com/watch?v=gPBmAOaTFK4
Science & Technology
#artificial intelligence
#ai
#gan
#deep learning
#machine learning