Следващо
But how do AI images and videos actually work? | Guest video by Welch Labs 38 мин 
Dark Secrets Hidden in America’s Most Isolated Islands (nobody comes here) 39 мин 
The Craziest Experiment Humans Have Ever Built 18 мин 
N 2 мин 
iPhone Duo/18 Pro Hands On - I wasn’t ready 17 мин 
Exploring the Paranoid Country with 374,142 Bunkers to Hide Everyone (how is this possible?) 35 мин 
NO SAFETY ON A BODY 2 мин 
Orphanage 2 мин 
Это голограмма или телепорт? Что это? #Shorts 1 мин 
Greatest Silence 3 мин 
The "Ride The Ducks" Disaster | Fascinating Horror 14 мин 
Abandoned - Nara Dreamland 17 мин 
The Largest Biological Attack in US History | Fascinating Horror 11 мин 
I've Been Thinking 1 мин 
Your Business Is Invisible to AI (And You Can't Even See It) #shorts 2 мин 
I entered an ultra marathon where you literally race the sea (and it was brutal) 23 мин 
Can I help Harry find his estranged mother from this childhood cemetery photo? 28 мин 
I Travelled Around The Entire Earth With $0: AUSTRALIA 72 мин 
No Way 13 мин 
Recreating an Ancient Pump (with no moving parts) 14 мин 
They Call It A "Drowning Machine" | Fascinating Horror Shorts 1 мин 
From Garden to Jar | Preserving Cucumbers & Tomatoes for Winter 🌿🍅 26 мин 
How to be less neurotic | The Gray Area 38 мин 
How to undo the damage of sitting all day | The Gray Area 42 мин 
Practical Magic (1998) - The Love Curse Kills Sally's Husband (1/11) | Movieclips 3 мин 
Name That Infrastructure (Ep. 12) #shorts 1 мин 
Practical Magic (1998) - Midnight Margarita Magic (5/11) | Movieclips 2 мин 
Olympic weightlifting, explained 9 мин 
The Steam-Cooled STEAM Machine 26 мин 
How Did Tuberculosis Get So Bad? #science #scishow #tuberculosis #health 1 мин 
Steam Frame Review - This Changes Everything 24 мин 
Why Are There No Short Arch Dams? 17 мин 
Lorn - Acid Rain (Official Music Video) 3 мин 
Neutron stars gave you jewelry. #shorts #science #SciShow 1 мин 
Why you're sick of rainy days #science #SciShow #sick #biology #illness #rain 1 мин 
The Mystery Behind Earth’s Missing Rocks: Crash Course Geology #16 11 мин 
What's Under Your Feet in New York City? 23 мин 
The Dark Side of the World’s Lightest Structural Metal 16 мин 
The First Punic War - OverSimplified (Part 1) 28 мин 
How Water Shapes the Land: Crash Course Geology #9 10 мин 
How Firefly is Revolutionizing the Logistics of Spaceflight | Full Documentary 49 мин 
The Surprisingly Large Carbon Footprint of Rice #science #scishow #rice #climatechange 1 мин 
This is NUTS 1 мин 
Why does catnip make cats go crazy? - Jaap de Roode 5 мин 
You’ll never look at it the same after this video 6 мин 
AI Can Now Read Ultrasounds #science #scishow #pregnancy #medicine 1 мин 
AI News: Microsoft Finally Reveals Their Plan! 31 мин 
What could this project be? 👀🥬 (Members' Update #46) 4 мин 
The World's Most Ignored War Explained 33 мин 
100% Infill is the only way to go 😅 #3dprinting #engineering #icks 2 мин 
$1 Robot vs $200,000 Robot 21 мин 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