Text to Image: Part 2 -- how image diffusion works in 5 minutes

[@sisyphusofephyra7801]

I saw 5 similar before this one. This one was the only who explained it in depth and in a digestible way.

[@somethingness]

You are so good at explaining all of this!

[@emilygocrazyy]

The video is great to lead me understand the diffusion paper and Dalle2 !! Thank you Steve!!! Just a quick note, 2:18 in the video, the mapping of random images to raspberry image is not necessary 1-to-1 mapping. For DDPM, the random noise maps to the entire data distribution, which means if you sample one noise image, it could be decoded to different raspberry through different random trajectories.

[@dgnu]

dude your videos are insane quality thank you for making them

[@onmountdoom]

Great videos, don’t stop making them please

[@ujjwalbhoota]

Great explaination!

[@mads7401]

This is awesome, thank you :)

[@aliyilmaz852]

thanks for explaining things for noobs like me

[@hx11hx1]

wow

[@JohnDlugosz]

Re inappropriate images: I'm surprised that nobody's made a version that generates nothing *but* inappropriate images, trained on the huge amount of existing Internet porn. Imagine the transfer capability of DALL-E applied to

[@MODEST500]

Why would you need that ?

[@Yobs2K]

@@MODEST500 you are too innocent for the internet

[@ashifismail9606]

Combine all your knowledge to a paid course, i would love to buy it

[@xiahua8548]

You really like chocolate guacamole hah?

[@miraculixxs]

For some reason up votes on this video are not counted 😮