Nākamais
But how do AI images and videos actually work? | Guest video by Welch Labs 38 min 
Hijack 6 min 
How Tech Companies Lie to You. 25 min 
Why Are There No Short Arch Dams? 17 min 
1950's ATV Concept Build Part 2 18 min 
Животный сервер! 🐀🐷🐤 (GTARP) 9 min 
California’s Tallest Bridge Has Nothing Underneath 18 min 
Are Beavers Actually Good at Dams? 20 min 
The Hunt for Xesh 34 min 
Exploring the Paranoid Country with 374,142 Bunkers to Hide Everyone (how is this possible?) 35 min 
The Childhood Game Collection - Scott The Woz 138 min 
BETA SQUAD MAFIA GAME: YOUTUBER ALL STARS EDITION 68 min 
What a Wild Journey 23 min 
The Second Punic War - OverSimplified (Part 2) 38 min 
Who’s afraid of an open-weight model? GLM, context bombing and post-Black Hat attacks 27 min 
I Thought this would be Safe! 17 min 
Worst Movie of the Year Just Dropped 23 min 
How a crucial battleground candidate is rethinking AI safety 2 min 
How I Scammed MrBeast For $100,000 38 min 
Evil Ed’s Terrifying Wolf Transformation | Fright Night 5 min 
Billy Cole’s Horrifying Final Stand | Fright Night 3 min 
How are holograms possible? 47 min 
Man Builds DIY Off-Grid WOODEN HOUSE In The Mountains | Start To Finish By @CountryBoy-82 
Name That Infrastructure (Ep. 6) #shorts 1 min 
Practical Magic (1998) - The Exorcism of Nicole Kidman! (10/11) | Movieclips 6 min 
Do Retention Ponds Actually Work? 18 min 
Woman Rescues Flooded Car And Restores It Back To New | By @Flame-Frame-VN 
Why NASA Is Sending This Truck To The Moon 24 min 
The Weirdest Tool in Underwater Construction 18 min 
Why Roads Get Washboards 18 min 
Why This Olympic Sport Bothers Physicists 17 min 
Why we can’t stop thinking about aliens | The Gray Area 48 min 
Jakey - Pine Barrens (Official Music Video) 5 min 
Solar Farms in Space - Reflect Orbital 32 min 
The truth behind the millennial "midlife crisis" | The Gray Area 52 min 
Why America’s Tank Failed in Ukraine 23 min 
How Scientists Build Consensus: Crash Course Scientific Thinking #5 11 min 
3 things you may not know about the Declaration of Independence #shorts 1 min 
The Insane Engineering of the F-14 Tomcat 30 min 
The First Punic War - OverSimplified (Part 1) 28 min 
How did ocean invertebrates end up on Mt. Everest?! 1 min 
How To Survive Being Eaten 10 min 
Are birds getting smaller? #shorts #science #scishow #climatechange 1 min 
What Dinosaurs, Pyramids, and the Atomic Bomb Have in Common 2 min 
We Made a Knife that can CUT THROUGH ANYTHING! 7 min 
wHeRE's tHe PowEr ArmOR? 😵💫🤖 #fallout #engineering #videogames 1 min 
Is Kosovo Serbian or Albanian? 23 min 
Daddy Pig Drives on the Wrong Side in Italy 🚗 #shorts #peppapig 1 min 
The Most Overhyped and Underhyped New AI Models 27 min 
I put jet engines on a SLED and broke a WORLD RECORD 27 min 
What’s ACTUALLY Happening in North Korea 46 min 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
Valsts
Amerikas Savienotās Valstis
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