ਅਗਲਾ
But how do AI images and videos actually work? | Guest video by Welch Labs 38 ਮਿੰਟ 
The Shoe That Broke Running 16 ਮਿੰਟ 
Glass is glass 5 ਮਿੰਟ 
None an Island 4 ਮਿੰਟ 
Why do some people have a better sense of direction than others? - Oliver Baumann 6 ਮਿੰਟ 
Earth to Mars in 10 Days 27 ਮਿੰਟ 
What If You Just Keep Digging? 11 ਮਿੰਟ 
How We Built The ISS 37 ਮਿੰਟ 
Someone Lived This 4 ਮਿੰਟ 
Hurricane vs. Tiny Houses 23 ਮਿੰਟ 
The Mysterious Swiss Lake Monster | Fascinating Horror Shorts 1 ਮਿੰਟ 
The New Moist Cr1TiKaL 2 ਮਿੰਟ 
Why do Human Feet Wash up on This Beach? | Fascinating Horror Shorts 1 ਮਿੰਟ 
EXTREME HIDE & SEEK IN FOOTBALL STADIUM 46 ਮਿੰਟ 
How Long Can We Secretly Live In A Grocery Store? 64 ਮਿੰਟ 
This 1950's ATV Concept ? 15 ਮਿੰਟ 
The Bath Curse Tablets | Fascinating Horror Shorts 1 ਮਿੰਟ 
HEATWAVE SOLVED 2 ਮਿੰਟ 
This Poodle Killed Three People | Fascinating Horror Shorts 1 ਮਿੰਟ 
The Weirdest Tool in Underwater Construction 18 ਮਿੰਟ 
Every US Electrical Outlet Explained 22 ਮਿੰਟ 
Practical Magic (1998) - Love Spell or True Romance? (9/11) | Movieclips 3 ਮਿੰਟ 
Kling 2.6 generates clean cinematic and highly consistent videos on higgsfield #aivideo 1 ਮਿੰਟ 
What's Under Your Feet in New York City? 23 ਮਿੰਟ 
From Garden to Jar | Preserving Cucumbers & Tomatoes for Winter 🌿🍅 26 ਮਿੰਟ 
Fixing the Most Dangerous Dam in the World 23 ਮਿੰਟ 
Name That Infrastructure (Ep. 10) #shorts 1 ਮਿੰਟ 
I Said Yes to Every Email for a Month! (Again) 31 ਮਿੰਟ 
LORN - PAWO 3 ਮਿੰਟ 
Is it possible that we are sharing the same stories? 1 ਮਿੰਟ 
Gen Z is done with both political parties | America, Actually 35 ਮਿੰਟ 
Flamethrower Underware! 12 ਮਿੰਟ 
The Future of Trivia Gaming #electronics #trivia #experience #funny 2 ਮਿੰਟ 
Who will be president in 2028? We made our picks. | America, Actually 44 ਮਿੰਟ 
What Bothers Physicists About Black Holes (Interview with Brian Cox) 74 ਮਿੰਟ 
NASA's Plutonium Problem 2 ਮਿੰਟ 
3 Million! 1 ਮਿੰਟ 
Animals & Shapeshifters: Crash Course Latin American Literature #10 10 ਮਿੰਟ 
Stopping the Unstoppable 16 ਮਿੰਟ 
Why America’s Tank Failed in Ukraine 23 ਮਿੰਟ 
The Hidden Engineering of Runways 19 ਮਿੰਟ 
Crash Course Geology Preview 3 ਮਿੰਟ 
Together, we can save the planet #shorts #earthday 1 ਮਿੰਟ 
The Basement: Thomas Campbell | NASA Secrets, Binaural Beats, Simulation Theory 251 ਮਿੰਟ 
Learn About Emotions and Feelings | Back to School | Kids Songs | BabyBus 23 ਮਿੰਟ 
AI News: Claude Opus 4.8, Insane Omni Use-Case, and A Dog Translator? 23 ਮਿੰਟ 
There's no way you found the last one 👀 #mecchachameleon #challenge #powerarmor #hacksmith 1 ਮਿੰਟ 
The missing ingredient in how we learn 6 ਮਿੰਟ 
Cameroon’s Deadly Lake Bomb Has Been Defused 14 ਮਿੰਟ 
Peppa Pig WINS the DUCK RACE for Baby EVIE! 🦆🏆 | BRAND NEW Peppa Pig Full Episodes | 4 Hours 243 ਮਿੰਟ 
Should you rinse your dishes before placing them in the dishwasher? - Rachel Yang 6 ਮਿੰਟ 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