วีดีโอ

This is brilliant !

excellent video!

Awesome to see easy-to-understand explanations of current research topics, keep up the great work!

Thank you for the video! This is the most clear explanation of flow matching on the internet ❤

Legend comeback 🙇! Your educational video is worth more than gold.💓🙏

Thankyou for great step by step explanation. Can you share any good resources and insights for implementing diffusion for own custom images?

Any arxiv paper with a video like this goes above any without, on my TO_READ list at least. +1

Honestly it'd be really nice to see the open source community catch up to this scale of operation one day! They are the backbone of ai progress but they rarely manage to innovate with actual public models to use

imagine it in the next 5 years

I'm building my own diffusion model myself. This is the best breakdown and visualization of the mathematics and implementation. Well done.

Very cool work, and top notch video with the little sound effects etc :D

Exciting work. Thank you for creating and sharing this explanation video.

My like comes with the 5th Symphony (9:39) 😸🎶

Just one minute in the video, you know it's extremely well done. Thanks for the video !

very cool! will you be putting the code on github?

Hi Professor, thank you for your explanation. However, I think that at 1:03 in the video, the up-sampling mechanism for image is performed by the 'decoder', not by the diffusion model. The animation here seems to suggest that the diffusion model produces the high-resolution images. Thanks for your time.

Amazing work! Thank you for sharing 😀

Amazing work!

Great video! At 1:21 should be maximizing similarity between two distributions. Or minimizing the distance between two distributions.

BRO YOU ARE EPIC

i wish this would be simpler. You know Notebook colab google and video which shows what to click etc etc....

Very good! But what surprises me is that pifu is still at the core. 4+ years and no better model has arrived? With all the developments? Anyway, great work.

I have a question: Are all distribution mentioned is distribution of a continuous variable, since we're using integral here?

The world and my brain after this: 💀

seriously one of the best educational videos I've ever watched.

Best video on diffusion!!

This is truly a great tutorial video, so well-made. Cannot believe covering so many things within only 17 minutes.

Thank you for your great work removing the need of the audience to know much prior knowledge before they could enjoy your video. For example, you mentioned maximum likelihood and explain what it is immediately. It is such a challenge to straighten all these in a 17-minute video, but you did a great work. Thank you!

I LOVE U!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

Your production on these videos is incredible

Awesome! Would also love a video on SLAM!

The linear algebra portion went by very quickly for someone who hasn't worked with them in several years. I guess this video is more tailored for current researchers?

OK, this is the best video explanation of diffusion models I saw. Ideal ratio between simplifications and depth☺👏

Great video, Can you please explain how to get the 'sparse' folder used in your project for a video ( or a folder containing video frames )?

This looks like covariance matrix 🤔

Great vid! Quick question - it wasn't clear how many of these second-order matrices we're making. One for each patch, right? A single one for the whole image wouldn't provide us with local information. The explanation confused me a bit Also, if I understand correctly, the intuition is that the second-order matrix helps us compute the curvature of the edge in the patch. And checking the eigenvalues provides us with info on that curvature. Is my mind in the right place? 😅

Awesome post, Jiang, thank you so much for the great job! Anyway, a small comment/question on your video (without too much importance, I assume). At minute 5:56 you comment that (direct derivation of formula (7) in the paper "Denoising Diffusion Probabilistic Models"), mu^hat_t(x_t,x_0) is on the line joining x_0 and x_t. And, while this is approximately true for "normal" beta_t scheduling, I think that the estimated mean as a function of x_0 and x_t need not be exactly on such a line since, in general, the respective multipliers of x_0 and x_t in such an equation need not (in general) add up to one. In fact, in "normal" scheduling, as t increases, it seems that this sum keeps progressively moving away from 1, so that although obviously mu_t will continue to be a simple linear combination of both x_t and x_0, the fact is that it will progressively move away (although by a small amount) from this line. Would you agree with this observation? Greetings, and again, congratulations for the video and thank you very much for clarifying us the inners of diffusion models!

You are a god of presenting things in such a concise and intuitive way! Thank you very much, Professor! It really, really helps.

BRAVO! No one ever have explained the diffusion model in such an easy way with all the details.

Thanks for a great video! What are we talking in terms of space use of the material? All the diffrent samples i find is always extremely short. Or what is the limitations?

Matrix incoming

Still have no clue. I don't think I ever will though.

The cat photograph used in the video belongs to Tombili (chubby in Turkish), a street cat from Istanbul. Tombili was known for its stylish sitting pose

Like having your dad do you homework. Grow up and get other creating yourself. So many fake artists are incoming with this crap

Sora = THE MATRIX pre alpha version 0.1

too much blah blah how can i make my video is the point

So in other words you feed it copyrighted videos and it spits those copyrighted videos out again? So much for "AI"

It doesnt use keyframes for long video gen. They most likely train by cutting chunks of the space-time latent out, and having it predict the missing frames.

When we can use this?

Oh god this is horrible