How AI Image Generators Work (Stable Diffusion / Dall-E) - Computerphile

AI image generators are massive, but how are they creating such interesting images? Dr Mike Pound explains what's going on.

Thumbnail image partly created by DALL-E with the prompt: "Computerphile YouTube Video presenter Mike Pound Explains Diffusion AI methods thumbnail with green computer style title text on a black background with grey binary"


This video was filmed and edited by Sean Riley.

[InfinityDz]

Glad to have finally found someone I can actually listen to about AI, someone that doesn't hype things up and isn't trying to sell me something.

[Qman]

Stable diffusion doesn't actually actually apply noise to images, it uses a compressed low dimensional latent representation of the image and applies noise to that. The model is running in this abstract latent space, and then the autoencoder recreates the image afterwards.

[ayushdhar]

A deep dive on the google colab code would be amazing!

[kgsz]

Came here by accident and man, aren't you the gifted one? I was engrossed in the video knowing barely anything about the technologies and techniques uses, and I don't feel dumber -- that's an achievement :)
Thanks again, will pop here often.

[wlockuz]

Finally! Ever since Stable Diffusion was released I was looking for an explainer on how it worked that wasn't "Oh it generates images from noise" or something that went too deep into technicals that I didn't understand.

Very beautifully explained Dr. Mike Pound! Hope you do another video where you dive into the code where we can see the parts which were visualized here.

One thing that's still unclear to me is how was the network trained to relate text with images and how does it utilize this information when actually producing images?

[beachdancer]

the explanation sounds like magic. It is like a sculptor saying he just chips away pieces of the stone until he finds the horse hidden inside.

[Ultimatro]

So stable diffusion is just the AI version of that sculpting joke: Start with a big block and take away the parts that dont fit

[serhat]

Can't believe Mike can effortlessly make that shape with his hand (little finger) at 5:37

[aijeveryday_guy]

I couldn't agree more! Since the release of Stable Diffusion, I've been searching for an explanation that strikes the right balance between simplicity and technicality. Your video did an excellent job of providing a clear understanding without overwhelming us with excessive technical details. Dr. Mike Pound, you have a remarkable talent for explaining complex topics in a beautifully straightforward manner!

[juliankandlhofer]

Oh i DEFINITELY want to see mike's deep dive into the code!

[Mutual_Information]

Add noise to images and train a model to undo that addition.. then you have something that maps from noise to images.

One thing I find so impressive about these researchers.. is that they would try this. It’s so bizarre.. just because, from a distance, it’s not at all clear that such a task is doable.

[carlborgen]

Would have been nice hear a bit more about the "gpt-style transformer embedding". Wouldn't those classifications have to be included in the training data already?

[housellama]

"I saw the angel in the marble and carved until I set him free. ” - Michelangelo

[dileepvr]

12:58 I'd like to hear more about that GPT-style transformer embedding of text. Was text part of the training set?

[Zothaqqua]

I tried to guess how these things work. Now I'm taking the difference between my guess and this explanation and feeding it to my neurons. Thanks!

[chaoslab]

Been listening to house music in the background (on the low down) when the odd watching computerphile / numberphile for quite a while now.
Thought it was time to fess up.
Vibing it is probably just me on this tip.

[danieletorrigiani]

Wow! Had not seen listing paper since my dad was trying to teach me basic on a commodore 64. Had no idea it was still a thing. Big jump from having to read code on paper to make sense of it to this.

[rickhobson]

I followed some of that.. but some of that also sounded a lot like Michelangelo's "start with the block of marble and carve away everything that doesnt look like "X." I will come back to watch this again after the first watching settles! Thank you for providing this.

[user__]

My favorite part is where he explains AI while drawing on printer paper from 1989 XD

[patu]

I would love to hear more about the process. Like how does it recognize that the image now looks like a frog on stilts? Seems to me like that's where the real complexity is.