How I trained a simple Text to Image Diffusion Model on my laptop from scratch!

In just 15 points, we talk about everything you need to know about Generative AI Diffusion models - from the basics to Latent Diffusion Models (LDMs) and Text-to-Image conditional Latent diffusion models. I also train a diffusion model with Pytorch on my laptop to demonstrate how it all works.

To access the full code repo && 15 minute code walkthrough video && 4000+ word script && 15+ animations && powerpoint slides used in this video (as well as others on my channel), please consider supporting us on Patreon or YT! It helps the channel massively, so thanks for considering.

#diffusion #ai #machinelearning #generativeai

Related videos:

Papers:

Timestamps:
0:00 - Intro
1:40 - 1
2:43 - 2
3:24 - 3
5:59 - 4
8:09 - 5
9:49 - 6
11:07 - 7
11:55 - 8
14:11 - 9
16:15 - 10
18:49- 11
19:48 - 12
21:03 - 13
22:07 - 14
23:27 - 15

[thanhphamduy]

As a ComfyUI user (a tool working with Stable Diffusion), I've always been curious about how the Stable Diffusion Model creates images. After reading many articles and watching countless YouTube videos that were either too academic or too superficial, this is the only video that really satisfied my curiosity. Thank you so much for making such a valuable video. Wishing your channel continued growth and looking forward to more great content like this!

[csmith]

You brought some serious points to light that I couldn’t previously see, thank you!

[mayank_]

great content with so many deep concepts..

[zendr]

Awesome video Mate❤
Looking forward to the next one.

[rishiroy]

You know sir i found out your channel pure accidentally. But thank god i found it . What ever you are teaching us in absolute gold.
But there is this one thing that i gotta ask. I am really curious to know about your background. You never shared your linkedin profile with us. How come you know your shit so deeply?
Finally sir, you are awesome. Have a nice day.

[jqkclzy]

I really love your channel, Keep up the good work

[hilmiyafia]

This is a very informative video, thank you so much! Please talk and explain how to code Rectified Flow Neural Network next 🙏🙏 And how it is different from Stable Diffusion 🤔

[tanvikumari]

ThankYou! for your Great work. How can I avail the Dataset for Conditional Generative model ?

[marinepower]

Good video! I'm very impressed with your results. But, one thing I'm confused about is, during sampling, there was a +σ_t * z term. I assume z is noise, but what is the sigma term? What defines how much extra noise to add each sampling step?

[hjups]

Great Job! Especially considering that these models are not easy to train.
I also never considered training CelebA with text conditioning, which seemed to produce good results given the training time.
A critique: you made a mistake when describing CLIP and with cross-attention. CLIP uses a transformer image encoder and a transformer text encoder, which are jointly trained - it may be possible to use a frozen VAE for the image encoder, but that would probably constrain the latent space and prevent strong semantic alignment.
For cross-attention, K and V come from CLIP whereas Q comes from the image tokens (you reversed them on your slide). Flipping them would also likely work, but then the cross-attention is modulating existing image features rather than introducing new features based on the conditioning.

[naveengeorge]

Great video...
If possible provide code also...