આગળ
But how do AI images and videos actually work? | Guest video by Welch Labs 38 મિનિટ 
Учусь юзать тело 🕺| Baby Steps 22 મિનિટ 
How We Built The ISS 37 મિનિટ 
HOPE YOU'LL STAY 3 મિનિટ 
Europe's Most Remote Island Village (400 people live here) 41 મિનિટ 
$10,000 Power Washer! 1 મિનિટ 
Digging A SECRET GARAGE Part 3 21 મિનિટ 
Why do some people have a better sense of direction than others? - Oliver Baumann 6 મિનિટ 
Samsung Z Fold/Flip 8 Hands on - Fold ULTRA?? 17 મિનિટ 
Why NASA Is Sending This Truck To The Moon 24 મિનિટ 
Scary Cat in the Hat Trend Causing Panic 10 મિનિટ 
Why Are There No Short Arch Dams? 17 મિનિટ 
What should security leaders do with AI? They don’t know. 30 મિનિટ 
One Piece of News From Every Country in the World (Pt 2) 38 મિનિટ 
I've Been Thinking 1 મિનિટ 
What is a "Body Farm"? | Fascinating Horror Shorts 1 મિનિટ 
What If You Dove Into Saturn? 1 મિનિટ 
I Opened A FAKE Apple Store 18 મિનિટ 
California's Water Problem 20 મિનિટ 
Sawing a Dam in Half (on Purpose) 21 મિનિટ 
Name That Infrastructure (Ep. 13) #shorts 1 મિનિટ 
Name That Infrastructure (Ep. 5) #shorts 1 મિનિટ 
Name That Infrastructure (Ep. 15) #shorts 1 મિનિટ 
Man Turns WWII-Era Stone Ruin Into Dream Home In Just One Year | Start To Finish @luxonbushcraft 44 મિનિટ 
Nobody Uses These Common Objects Correctly 17 મિનિટ 
Name That Infrastructure (Ep. 12) #shorts 1 મિનિટ 
Men Transform Abandoned French House Under $80,000 | Start to Finish by @petitcopeau 
Are Beavers Actually Good at Dams? 20 મિનિટ 
The Surprisingly Large Carbon Footprint of Rice #science #scishow #rice #climatechange 1 મિનિટ 
Why even the best aquariums can’t give animals what they need 2 મિનિટ 
Which of these is the best idea? 🤷♂️ #batmobile #batman #engineering 1 મિનિટ 
How do you reconstruct an old story? 1 મિનિટ 
There’s something wrong with Hallmark’s youtube channel 19 મિનિટ 
I Promise you this is NOT Stupid 10 મિનિટ 
The illusion of the ‘self’ | The Gray Area 43 મિનિટ 
LSD May Lead to a New Kind of Medicine 25 મિનિટ 
Prohibition - OverSimplified 34 મિનિટ 
This Spillway Failed On Purpose 20 મિનિટ 
Let's Go on a Field Trip! 3 મિનિટ 
It’s not to stop you from rolling over 2 મિનિટ 
Sex-Triggered Asthma?! #science #scishow #asthma #romance 1 મિનિટ 
The Bizarre Bases of Antenna Towers 19 મિનિટ 
Scientists Can't Agree On The First Ancient City 26 મિનિટ 
Peppa Pig WINS the DUCK RACE for Baby EVIE! 🦆🏆 | BRAND NEW Peppa Pig Full Episodes | 4 Hours 243 મિનિટ 
100% Infill is the only way to go 😅 #3dprinting #engineering #icks 2 મિનિટ 
A giant basketball shoe. Inside the basketball shoe, there are many basketball courts and goals; ... 1 મિનિટ 
A dream come true... #batman #batmobile #dreamgarage 1 મિનિટ 
Match Day #PeppaPig #Shorts 1 મિનિટ 
Crash Course Hosts Read Comments 2 મિનિટ 
When did we start using passports? - Kristin Surak 7 મિનિટ 
The Stolen Recipe | Detective Cartoon | Educational | Sheriff Labrador | Kids Cartoon | BabyBus 32 મિનિટ Diffusion models, CLIP, and the math of turning text into images Welch Labs Book: https://www.welchlabs.com/resources/imaginary-numbers-book Sections 0:00 - Intro 3:37 - CLIP 6:25 - Shared Embedding Space 8:16 - Diffusion Models & DDPM 11:44 - Learning Vector Fields 22:00 - DDIM 25:25 - Dall E 2 26:37 - Conditioning 30:02 - Guidance 33:39 - Negative Prompts 34:27 - Outro 35:32 - About guest videos Special Thanks to: Jonathan Ho - Jonathan is the Author of the DDPM paper and the Classifier Free Guidance Paper. https://arxiv.org/pdf/2006.11239 https://arxiv.org/pdf/2207.12598 Preetum Nakkiran - Preetum has an excellent introductory diffusion tutorial: https://arxiv.org/pdf/2406.08929 Chenyang Yuan - Many of the animations in this video were implemented using manim and Chenyang’s smalldiffusion library: https://github.com/yuanchenyang/smalldiffusion Cheyang also has a terrific tutorial and MIT course on diffusion models https://www.chenyang.co/diffusion.html https://www.practical-diffusion.org/ Other References All of Sander Dieleman’s diffusion blog posts are fantastic: https://sander.ai/ CLIP Paper: https://arxiv.org/pdf/2103.00020 DDIM Paper: https://arxiv.org/pdf/2010.02502 Score-Based Generative Modeling: https://arxiv.org/pdf/2011.13456 Wan2.1: https://github.com/Wan-Video/Wan2.1 Stable Diffusion: https://huggingface.co/stabilityai/stable-diffusion-2 Midjourney: https://www.midjourney.com/ Veo: https://deepmind.google/models/veo/ DallE 2 paper: https://cdn.openai.com/papers/dall-e-2.pdf Code for this video: https://github.com/stephencwelch/manim_videos/tree/master/_2025/sora Written by: Stephen Welch, with very helpful feedback from Grant Sanderson Produced by: Stephen Welch, Sam Baskin, and Pranav Gundu Technical Notes The noise videos in the opening have been passed through a VAE (actually, diffusion process happens in a compressed “latent” space), which acts very much like a video compressor - this is why the noise videos don’t look like pure salt and pepper. 6:15 CLIP: Although directly minimizing cosine similarity would push our vectors 180 degrees apart on a single batch, overall in practice, we need CLIP to maximize the uniformity of concepts over the hypersphere it's operating on. For this reason, we animated these vectors as orthogonal-ish. See: https://proceedings.mlr.press/v119/wang20k/wang20k.pdf Per Chenyang Yuan: at 10:15, the blurry image that results when removing random noise in DDPM is probably due to a mismatch in noise levels when calling the denoiser. When the denoiser is called on x_{t-1} during DDPM sampling, it is expected to have a certain noise level (let's call it sigma_{t-1}). If you generate x_{t-1} from x_t without adding noise, then the noise present in x_{t-1} is always smaller than sigma_{t-1}. This causes the denoiser to remove too much noise, thus pointing towards the mean of the dataset. The text conditioning input to stable diffusion is not the 512-dim text embedding vector, but the output of the layer before that, [with dimension 77x512](https://stackoverflow.com/a/79243065) For the vectors at 31:40 - Some implementations use f(x, t, cat) + alpha(f(x, t, cat) - f(x, t)), and some that do f(x, t) + alpha(f(x, t, cat) - f(x, t)), where an alpha value of 1 corresponds to no guidance. I chose the second format here to keep things simpler. At 30:30, the unconditional t=1 vector field looks a bit different from what it did at the 17:15 mark. This is the result of different models trained for different parts of the video, and likely a result of different random initializations. Premium Beat Music ID: EEDYZ3FP44YX8OWT
Packages published by the creator behind this video.
This creator has not set their rates yet. Send a request and we will pass it on — the price is agreed before anything is charged.
A recurring seat in my content. Subscribers enter a queue — or a random draw when there are more subscribers than slots — and appear in the video itself, in the credits, or in the description.
per month
Price on request
A guaranteed appearance of at least 10 seconds in my next video. Price depends on where in the runtime the insert lands.
Price on request
A guaranteed appearance of at least 10 seconds inside a Short cut from one of my existing videos.
one-off
Price on request