Als Nächstes
But how do AI images and videos actually work? | Guest video by Welch Labs 38 Min. 
1950's ATV Concept Build Part 2 18 Min. 
How can you overcome writer’s block? 1 Min. 
Очень много смеха 🤣 (GTARP) 14 Min. 
How We Built the ISS - Part 2 29 Min. 
Buying a 1 euro House in Italy - is it a scam? 42 Min. 
Dark Secrets Hidden in America’s Most Isolated Islands (nobody comes here) 39 Min. 
Digging A SECRET GARAGE Part 3 21 Min. 
The Hidden Engineering of Floating Bridges 18 Min. 
What's Under Your Feet in New York City? 23 Min. 
$100 vs $100,000 Holiday: Asia Edition 63 Min. 
Jump or Burn: The Luxor Balloon Crash | Fascinating Horror 12 Min. 
GUESS THE ACTOR FT IDRIS ELBA 45 Min. 
How a crucial battleground candidate is rethinking AI safety 2 Min. 
Eating Cheap VS Expensive Food 16 Min. 
The Story Of The Black Tom Explosion | Fascinating Horror 11 Min. 
The Japanese Tsunami That Killed 20,000 People | Fascinating Horror 12 Min. 
DLSS 5 is NOT What We Expected 19 Min. 
EXTREME HIDE & SEEK IN FOOTBALL STADIUM 46 Min. 
Every US Electrical Outlet Explained 22 Min. 
This Spillway Failed On Purpose 20 Min. 
Kling 2.6 generates clean cinematic and highly consistent videos on higgsfield #aivideo 1 Min. 
Are Beavers Actually Good at Dams? 20 Min. 
They Call It A "Drowning Machine" | Fascinating Horror Shorts 1 Min. 
The Hidden Engineering Behind the Falkirk Wheel 16 Min. 
Name That Infrastructure (Ep. 16) #shorts 1 Min. 
Practical Magic (1998) - The Exorcism of Nicole Kidman! (10/11) | Movieclips 6 Min. 
NASA’s Next Monster Telescope 22 Min. 
Why the US is Struggling to Land on the Moon 20 Min. 
A MAGA influencer tests the GOP midterm message. Is it working? | America, Actually 26 Min. 
Are birds getting smaller? #shorts #science #scishow #climatechange 1 Min. 
Cancelled - American Heartland Theme Park 20 Min. 
Why you're sick of rainy days #science #SciShow #sick #biology #illness #rain 1 Min. 
What Dinosaurs, Pyramids, and the Atomic Bomb Have in Common 2 Min. 
Lorn - Acid Rain (Official Music Video) 3 Min. 
The twin experiment that broke genetics research 17 Min. 
Janus Is Two-Faced #scishow #science #space 1 Min. 
The Fungus You Should Actually Be Worried About 18 Min. 
The Weirdest Tool in Underwater Construction 18 Min. 
How Will the Golden Dome Work? 23 Min. 
Bridge Demolition is Complicated 18 Min. 
The Bizarre Bases of Antenna Towers 19 Min. 
Can Baldness Be Reversed? 9 Min. 
THE WAIT IS OVER, THE POWER ARMOR IS BACK! #fallout #powerarmor #engineering 1 Min. 
Which of these is the best idea? 🤷♂️ #batmobile #batman #engineering 1 Min. 
Peppa's Sandcastle DISASTER ⛱️🌊 #PeppaPig #Shorts #Summer #LEGODUPLO 1 Min. 
What to do if you live in the path of a volcano - Arianna Soldati 6 Min. 
Peppa Makes Perfume 🌸 #shorts #peppapig 1 Min. 
Is Kosovo Serbian or Albanian? 23 Min. 
Newest addition to my lab 😏 #cnc #3Ddesign #engineering 1 Min. 
The Pi Song 4.0 (Memorize 400 Digits Of π) 6 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
Pakete, die vom Creator hinter diesem Video veröffentlicht wurden.
Dieser Creator hat seine Preise noch nicht festgelegt. Sende eine Anfrage und wir leiten sie weiter – der Preis wird vereinbart, bevor etwas berechnet wird.
Ein wiederkehrender Platz in meinen Inhalten. Abonnenten kommen in eine Warteschlange – oder in eine Zufallsziehung, wenn es mehr Abonnenten als Plätze gibt – und erscheinen im Video selbst, in den Credits oder in der Beschreibung.
pro Monat
Preis auf Anfrage
Ein garantierter Auftritt von mindestens 10 Sekunden in meinem nächsten Video. Der Preis hängt davon ab, wo in der Laufzeit die Einfügung landet.
Preis auf Anfrage
Ein garantierter Auftritt von mindestens 10 Sekunden in einem Short aus einem meiner bestehenden Videos.
einmalig
Preis auf Anfrage