Prossimo
But how do AI images and videos actually work? | Guest video by Welch Labs 38 min 
The Bizarre Bases of Antenna Towers 19 min 
The Physics Behind the Thumb Trick 18 min 
Why avalanches are most deadly when they stop - Simon Trautman 6 min 
How Tech Companies Lie to You. 25 min 
UNDEAD DOGS 1 min 
I spent $12,000 on the THINNEST Tech 25 min 
Solar Farms in Space - Reflect Orbital 32 min 
An Engineer's Perspective on the Texas Floods 24 min 
The Hidden Engineering of Niagara Falls 16 min 
The Secret Tunnel Air Compressor!!! 3 min 
4 ways to tell a great story 6 min 
Hurricane vs. Tiny Houses 23 min 
How 60 Minutes got inside the world of pardon brokers #shorts 2 min 
I Pranked America's Most Racist Man 35 min 
Abandoned - Nara Dreamland 17 min 
One Piece of News From Every Country in the World (Pt 2) 38 min 
The Story of Bill Stephens | Fascinating Horror Shorts 1 min 
Kidneys for sale | The Gray Area 48 min 
Practical Magic (1998) - The Witches Fly on Halloween! (11/11) | Movieclips 2 min 
The Los Angeles Aqueduct is Wild 23 min 
The Wild Story of the Teton Dam Failure 20 min 
Fixing the Most Dangerous Dam in the World 23 min 
How to undo the damage of sitting all day | The Gray Area 42 min 
They Call It A "Drowning Machine" | Fascinating Horror Shorts 1 min 
Man Turns an Empty Space into a Dream Garage | @SmartEasyDIYer 
This Spillway Failed On Purpose 20 min 
The Steam Machine Killer 2 min 
The Insane Engineering of the V-22 Osprey 24 min 
13 most EXPENSIVE Tech Fails of all time 24 min 
The Grid That Doubles the Strength of the Ground 19 min 
The New Hunt for the Colossal Squid 19 min 
How a crucial battleground candidate is rethinking AI safety 2 min 
Why Latino voters have turned on Trump | America, Actually 31 min 
NVIDIA CEO Jensen Huang's Vision for the Future 64 min 
Why the Perfect Red Is Impossible to Make 13 min 
Earth's Crust and Mantle Explained: Crash Course Geology #3 11 min 
The Weirdest New Battery is... Rust 10 min 
Is There A Shortcut To Treating Tuberculosis? #science #scishow #tuberculosis #health 1 min 
Name That Infrastructure (Ep. 8) #shorts 1 min 
How Scientists Build Consensus: Crash Course Scientific Thinking #5 11 min 
The Pig War - OverSimplified 39 min 
3 Million! 1 min 
TOMBSTONE vs ORBITRON (VIDEO #6/6) 15 min 
Sleepover With Cousin Chloe #PeppaPig #Shorts 1 min 
Peppa Gets a NEW SUPER Squashpuff! #PeppaPig #Shorts 1 min 
How to attack (and defend) a medieval castle - Connor C. Wilson 6 min 
Building Robotic Hands | Real Life Power Armor (Part 5/6) 24 min 
Granny Pig’s Chickens 🐔 #shorts #peppapig 1 min 
They’re Not British. They’re Not Independent. So What Are They? 17 min 
Why is getting bitten by a rabid animal so dangerous? - Charles Rupprecht 7 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
Pacchetti pubblicati dal creatore dietro questo video.
Questo creatore non ha ancora impostato le sue tariffe. Invia una richiesta e la inoltreremo — il prezzo viene concordato prima che venga addebitato qualcosa.
Un posto ricorrente nei miei contenuti. Gli abbonati entrano in una coda — o in un'estrazione casuale quando ci sono più abbonati che slot — e appaiono nel video stesso, nei crediti o nella descrizione.
al mese
Prezzo su richiesta
Un'apparizione garantita di almeno 10 secondi nel mio prossimo video. Il prezzo dipende da dove cade l'inserzione nella durata.
Prezzo su richiesta
Un'apparizione garantita di almeno 10 secondi in uno Short tagliato da uno dei miei video esistenti.
una tantum
Prezzo su richiesta