Következő
But how do AI images and videos actually work? | Guest video by Welch Labs 38 perc 
Apple Intelligence scares me 1 perc 
Mesa 4 perc 
DEADERA 2 perc 
Я загрузил ИИ в Скайрим... и вот чот вышло 🤣 23 perc 
The Hidden Engineering Behind the Falkirk Wheel 16 perc 
How Earthquake Bearings Work 19 perc 
Новогодняя нарезка (Лучшее за 2025) 82 perc 
Учусь юзать тело 🕺| Baby Steps 22 perc 
The Magnet Suspension Bike 27 perc 
Jump or Burn: The Luxor Balloon Crash | Fascinating Horror 12 perc 
How a crucial battleground candidate is rethinking AI safety 2 perc 
What’s Happened?? #secretgarage 2 perc 
BETA SQUAD MAFIA GAME: ALL STAR EDITION 54 perc 
Your Website Is Just 1 of 37 Signals Now #shorts 1 perc 
Bankrupt - Hooters 19 perc 
Recreating an Ancient Pump (with no moving parts) 14 perc 
6 Americans vs 1 Secret British Person 57 perc 
Can't Believe He's Talking About It 20 perc 
Men Transform Abandoned French House Under $80,000 | Start to Finish by @petitcopeau 
The Wild Story of the Teton Dam Failure 20 perc 
Name That Infrastructure (Ep. 7) #shorts 1 perc 
Billy Cole’s Horrifying Final Stand | Fright Night 3 perc 
Stopping the Unstoppable 16 perc 
Woman Rescues Flooded Car And Restores It Back To New | By @Flame-Frame-VN 
Lessons From Training Composer At Cursor And Building Meta/Nvidia Compute Clusters | YC Paper Club 77 perc 
Sawing a Dam in Half (on Purpose) 21 perc 
The Steam Machine Killer 2 perc 
What Made The Bahamas’s “Atlantis” Rocks? 1 perc 
The Unlikely Rise of the Indian Space Program 29 perc 
Is the path to parenthood becoming a luxury? 2 perc 
Crazy Larper Scammed $1.3 Million from Victims 23 perc 
Exploring the World's Largest $100 Billion Failed Ghost City (why did nobody move here?) 26 perc 
Will gas prices decide the midterms? | America, Actually 28 perc 
How We Built The ISS 37 perc 
We've Been At It 2 perc 
The Insane Engineering of the F-14 Tomcat 30 perc 
Earthquakes Explained: Crash Course Geology #14 12 perc 
The First Punic War - OverSimplified (Part 1) 28 perc 
How To Survive Being Eaten 10 perc 
Name That Infrastructure (Ep. 15) #shorts 1 perc 
Is the Secret to Treating Schizophrenia in... Engineering? 23 perc 
How Do Minerals Form?: Crash Course Geology #5 10 perc 
BABY EVIE AT THE AQUARIUM #PeppaPig #Shorts 1 perc 
Jumping in Muddy Puddles 🌧️ #shorts #peppapig 1 perc 
BAT-GARAGE Tour + BAT-SIGNAL Restoration (MEMBERS EXCLUSIVE) 12 perc 
The World’s Best Diet Doesn’t Make You Lose Weight 13 perc 
Our projects create A LOT of damage #Aiper #AiperIrriSense2 #SummerWithAiper #PrimeDay #2026PrimeDay 2 perc 
Sleepover With Cousin Chloe #PeppaPig #Shorts 1 perc 
What’s really happening in the ocean’s “dark zones” 32 perc 
Tales VS Toys: Valentine's Spy Mission 💗 #PeppaPig #Shorts #toys #toyplay 1 perc 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