Ďalšie
But how do AI images and videos actually work? | Guest video by Welch Labs 38 min 
Берегись Паука! 🕷️ (Fever Meme) 18 min 
Dark Secrets Hidden in America’s Most Isolated Islands (nobody comes here) 39 min 
Why Sagrada Familia Took 144 Years to Complete 25 min 
The Insane Engineering of the P-38 Lightning 27 min 
An Engineer's Perspective on the Texas Floods 24 min 
The Ultimate 2026 Battery Test 12 min 
What is sumo, and why is it so popular? - Lee Thompson 6 min 
Меня обижают (Мозоль) 15 min 
Заперт с Монстром 🤣 | Murky Divers 17 min 
$100 vs $100,000 Holiday: Asia Edition 63 min 
The Strangest Operating System in History | Fascinating Horror Shorts 1 min 
This Cheese is Rotting, Maggot-Infested, Illegal and... Delicious? | Fascinating Horror Shorts 1 min 
Abandoned - Terrible's Hotel & Casino (Jean, Nevada) 20 min 
Replacing Yourself with AI is Stupid 14 min 
You Can Still be Prescribed Leeches | Fascinating Horror Shorts 1 min 
Why American Houses Are So Flimsy 15 min 
Can I help Harry find his estranged mother from this childhood cemetery photo? 28 min 
Do Retention Ponds Actually Work? 18 min 
Man Builds DIY Off-Grid WOODEN HOUSE In The Mountains | Start To Finish By @CountryBoy-82 
Name That Infrastructure (Ep. 12) #shorts 1 min 
How to undo the damage of sitting all day | The Gray Area 42 min 
Billy Cole’s Horrifying Final Stand | Fright Night 3 min 
Man Turns an Empty Space into a Dream Garage | @SmartEasyDIYer 
How to SHOOT & EDIT B-Roll For Beginners! 11 min 
Name That Infrastructure (Ep. 3) #shorts 1 min 
Practical Magic (1998) - The Love Curse Kills Sally's Husband (1/11) | Movieclips 3 min 
The new midlife crisis 2 min 
The Age of Broken Video Games 14 min 
NASA’s Next Monster Telescope 22 min 
Member Update "WHERES THE VIDEOS FURZE" 5 min 
How deportations changed Latinos’ minds on Trump 2 min 
What Bothers Physicists About Black Holes (Interview with Brian Cox) 74 min 
The $1 Trillion Problem Diamonds Can Solve 17 min 
Are birds getting smaller? #shorts #science #scishow #climatechange 1 min 
Earth to Mars in 10 Days 27 min 
Bridge Demolition is Complicated 18 min 
How did Earth form?: Crash Course Geology #2 10 min 
How Private Equity Ruined American Youth Sports 19 min 
What Dinosaurs, Pyramids, and the Atomic Bomb Have in Common 2 min 
Prohibition - OverSimplified 34 min 
This substance could revolutionize human waste 10 min 
You’ll never look at it the same after this video 6 min 
villager-noise.mp4 ⛏️🟩 #minecraft #makeitreal 2 min 
Ever walk into a room and forget what you were doing? - Gabriel Radvansky 6 min 
4 ways to tell a great story 6 min 
Making my Skull BULLETPROOF with Real Life Adamantium!? 25 min 
AI News: An INSANE Week… Here’s What Matters 31 min 
How To Survive Being Eaten 10 min 
The dark origins of Disney fairy tales - Claudia Schwabe 6 min 
Granny Pig’s Chickens 🐔 #shorts #peppapig 1 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
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