அடுத்தது
But how do AI images and videos actually work? | Guest video by Welch Labs 38 நிமி 
Sea Wall 10 நிமி 
Samsung S26 Ultra Hands on - What's ACTUALLY New? 15 நிமி 
Exploring the World's Largest $100 Billion Failed Ghost City (why did nobody move here?) 26 நிமி 
My Take on The New Apple 12 நிமி 
“The Biggest Android Update Ever” 13 நிமி 
NO SAFETY ON A BODY 2 நிமி 
Я загрузил ИИ в Скайрим… и создал чудовище 😈 26 நிமி 
Red gold: The world's most expensive spice - Carolyn Beans 7 நிமி 
How Disney Built A Realistic Lightsaber 17 நிமி 
How the Channel Tunnel Works 24 நிமி 
Law professor calls the new pardon system “anarchy” #shorts 1 நிமி 
Lindsey Clancy and the surprisingly simple solution to helping moms with postpartum depression 2 நிமி 
I've Been Thinking 1 நிமி 
What is a "Body Farm"? | Fascinating Horror Shorts 1 நிமி 
Seas #TeamSeas 3 நிமி 
The Los Angeles Aqueduct is Wild 23 நிமி 
The shoes that broke walking 9 நிமி 
Free Energy Motor Generator #science #funny #electrical 2 நிமி 
How to be less neurotic | The Gray Area 38 நிமி 
Why Roads Get Washboards 18 நிமி 
This Spillway Failed On Purpose 20 நிமி 
How are holograms possible? 47 நிமி 
Woman Rescues Flooded Car And Restores It Back To New | By @Flame-Frame-VN 
The Physics Behind the Thumb Trick 18 நிமி 
Name That Infrastructure (Ep. 9) #shorts 1 நிமி 
Practical Magic (1998) - The Exorcism of Nicole Kidman! (10/11) | Movieclips 6 நிமி 
When did we start using passports? - Kristin Surak 7 நிமி 
There’s something wrong with Hallmark’s youtube channel 19 நிமி 
I Tried All The Best (and Worst) Doorbells 18 நிமி 
The Craziest Experiment Humans Have Ever Built 18 நிமி 
What is sumo, and why is it so popular? - Lee Thompson 6 நிமி 
The Future of Trivia Gaming #electronics #trivia #experience #funny 2 நிமி 
Nonalcoholic drinks SHOULD cost more. Here's why. 10 நிமி 
How to remove AI from your life 3 நிமி 
The Stinky Fish Sauce Ancient Romans Couldn’t Live Without 14 நிமி 
How We Built the ISS - Part 2 29 நிமி 
Recreating an Ancient Pump (with no moving parts) 14 நிமி 
Reading & Writing Latin American literature: Crash Course Latin American Literature #13 11 நிமி 
The Dark Side of the World’s Lightest Structural Metal 16 நிமி 
One Piece of News From Every Country in the World (Pt 2) 38 நிமி 
We've Been At It 2 நிமி 
Why People Thought "Aliens" Made These Rocks 12 நிமி 
Did AFRICANS ever Colonize anything? 17 நிமி 
Cruise Party | Safety Rules for Kids | Good Habits | Sheriff Labrador | Kids Cartoon | BabyBus 29 நிமி 
AI News: Microsoft Finally Reveals Their Plan! 31 நிமி 
X-Ray Machine at the Airport ✈️ #shorts #peppapig 1 நிமி 
Peppa Pig Tales⏰ Peppa & Evie WAIT for the TRAIN! 🚂 LEGO DUPLO Peppa Pig Episodes 31 நிமி 
The Pi Song 4.0 (Memorize 400 Digits Of π) 6 நிமி 
Peppa Meets a Hedgehog 🦔 #shorts #peppapig 1 நிமி 
A dream come true... #batman #batmobile #dreamgarage 1 நிமி 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