ቀጣይ
But how do AI images and videos actually work? | Guest video by Welch Labs 38 ደቂቃ 
My First FAILURE!! 9 ደቂቃ 
Exploring Japan's Remote Border with Russia (no one comes here) 26 ደቂቃ 
Meet the slow loris, the only venomous primate in existence - Stephanie A. Poindexter 6 ደቂቃ 
This Machine makes me WEIGHTLESS!! 25 ደቂቃ 
Sea Wall 10 ደቂቃ 
Куда смотришь? 😍 (Arknights: Endfield) 18 ደቂቃ 
Why does catnip make cats go crazy? - Jaap de Roode 5 ደቂቃ 
The Hidden Engineering Behind the Falkirk Wheel 16 ደቂቃ 
The Shoe That Broke Running 16 ደቂቃ 
Kidneys for sale | The Gray Area 48 ደቂቃ 
How the Iran War Spiked Oil Prices 18 ደቂቃ 
Jump or Burn: The Luxor Balloon Crash | Fascinating Horror 12 ደቂቃ 
Huge Copyright Strike Situation 18 ደቂቃ 
I Thought this would be Safe! 17 ደቂቃ 
The Story Of Shriya Shah-Klorfine | Fascinating Horror 13 ደቂቃ 
The illusion of the ‘self’ | The Gray Area 43 ደቂቃ 
Law professor calls the new pardon system “anarchy” #shorts 1 ደቂቃ 
Actually a Wild Situation 24 ደቂቃ 
Essential Skills for Becoming an AI Engineer: RAG, AI Agents, & More 11 ደቂቃ 
Practical Magic (1998) - The Exorcism of Nicole Kidman! (10/11) | Movieclips 6 ደቂቃ 
California’s Tallest Bridge Has Nothing Underneath 18 ደቂቃ 
Man Renovates 2-Story Old House And Gives It A New Life | Start To Finish By @officialnuera1 15 ደቂቃ 
Man Turns an Empty Space into a Dream Garage | @SmartEasyDIYer 
Kling 2.6 generates clean cinematic and highly consistent videos on higgsfield #aivideo 1 ደቂቃ 
Practical Magic (1998) - Sally Finds Her Perfect Man (7/11) | Movieclips 3 ደቂቃ 
Practical Magic (1998) - Sisterly Witchy Mischief (4/11) | Movieclips 2 ደቂቃ 
Sneak peek at the making of a TED-Ed animation #shorts 1 ደቂቃ 
Flamethrower Underware! 12 ደቂቃ 
Why is getting bitten by a rabid animal so dangerous? - Charles Rupprecht 7 ደቂቃ 
Why This Robot Kills Weeds With Lasers 15 ደቂቃ 
Plasma Globe is a ⚡Shocking⚡🔥Fire Hazard🔥 12 ደቂቃ 
The Hidden Engineering of Floating Bridges 18 ደቂቃ 
The Age of Broken Video Games 14 ደቂቃ 
What technology can't give you | The Gray Area 45 ደቂቃ 
Is the Secret to Treating Schizophrenia in... Engineering? 23 ደቂቃ 
The Insane Engineering of the V-22 Osprey 24 ደቂቃ 
How the US' Only District Works 19 ደቂቃ 
The illusion that broken the internet 10 ደቂቃ 
Why the Perfect Red Is Impossible to Make 13 ደቂቃ 
Why Texas Wins 20 ደቂቃ 
Is the Yellowstone volcano going to erupt again? 🌋 2 ደቂቃ 
Name That Infrastructure (Ep. 16) #shorts 1 ደቂቃ 
MURAL #PeppaPig #Shorts 1 ደቂቃ 
AI News: The New Model That's As Good As Fable 20 ደቂቃ 
TOMBSTONE vs ORBITRON (VIDEO #6/6) 15 ደቂቃ 
TURBANATOR 2: CANADA DAY 🇨🇦(Dark Humor) 5 ደቂቃ 
The missing ingredient in how we learn 6 ደቂቃ 
We finally know why it's so good for you 7 ደቂቃ 
The Only 19 Skills to Make Money in the AI Era 26 ደቂቃ 
Row Your Boat Song 🚣 #shorts #peppapig 1 ደቂቃ 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