পরবর্তী
But how do AI images and videos actually work? | Guest video by Welch Labs 38 মিনিট 
Bluey Phone Review 5 মিনিট 
Я загрузил ИИ в Скайрим… и создал чудовище 😈 26 মিনিট 
FARR 3 মিনিট 
Every US Electrical Outlet Explained 22 মিনিট 
$10,000 Power Washer! 1 মিনিট 
I Transformed My Body in 90 days. 20 মিনিট 
(VR) Я мистер Мисикс! | Rick and Morty: Virtual Rick-ality 18 মিনিট 
SEGA SUNSET 4 মিনিট 
Sam Altman Shows Me GPT 5... And What's Next 66 মিনিট 
Neighbours reaction #secretgarage 2 মিনিট 
So You Want to Build a Tunnel... 21 মিনিট 
Overboard From A Cruise Ship | Fascinating Horror 12 মিনিট 
People Are Very Mad at Sony for This 13 মিনিট 
What if Your Hand Didn't Belong to You? | Fascinating Horror Shorts 1 মিনিট 
The Failed Logistics of Hurricane Katrina 21 মিনিট 
Lifting the covers of the #secretgarage 2 মিনিট 
Members have a think about this DOOR? 7 মিনিট 
4 ways to tell a great story 6 মিনিট 
Kling 2.6 generates clean cinematic and highly consistent videos on higgsfield #aivideo 1 মিনিট 
Fixing the Most Dangerous Dam in the World 23 মিনিট 
Man Builds Amazing WORKSHOP With Garden In His Backyard | Start To Finish By @machikane_base 
Restoring The Weirdest Xbox 360 Controller - Retro Console Restoration & Repair 15 মিনিট 
Hurricane vs. Tiny Houses 23 মিনিট 
The Los Angeles Aqueduct is Wild 23 মিনিট 
The Hidden Engineering of Floating Bridges 18 মিনিট 
Nobody Uses These Common Objects Correctly 17 মিনিট 
Steam Frame Review - This Changes Everything 24 মিনিট 
The Truth About Egg Freezing 22 মিনিট 
China’s Plan to Block All Submarines 21 মিনিট 
Are birds getting smaller? #shorts #science #scishow #climatechange 1 মিনিট 
The Insane Engineering of the P-38 Lightning 27 মিনিট 
How do you pray when you don’t believe in God? 3 মিনিট 
Ads in Video Games 20 মিনিট 
Everything you need to know about bird flu - Benjamin Anderson 7 মিনিট 
Neutron stars gave you jewelry. #shorts #science #SciShow 1 মিনিট 
How The Space Shuttle Worked | Full Documentary 78 মিনিট 
We finally know why it's so good for you 7 মিনিট 
Why the Perfect Red Is Impossible to Make 13 মিনিট 
3 Million! 1 মিনিট 
Vegetarian Diets Are... Hot #shorts #science #SciShow 1 মিনিট 
Name That Infrastructure (Ep. 15) #shorts 1 মিনিট 
How Long Does Sperm REALLY Live? #science #scishow #STEM #hankgreen 1 মিনিট 
Why You Don’t Trust Tap Water 27 মিনিট 
Jumping in Muddy Puddles 🌧️ #shorts #peppapig 1 মিনিট 
Boo Boo at the Fun Fair! 🎡 #PeppaPigTales #Shorts #LEGODUPLO 1 মিনিট 
Do Penguins Control the Weather? 8 মিনিট 
Peppa Pig Learns How to Make DONUTS! 🍩 Food Factory | BRAND NEW Peppa Pig Tales Episodes | 35 Mins 36 মিনিট 
How the Mormon Church Made $293 Billion 71 মিনিট 
Peppa VS Candy: EPIC Cooking Challenge 🔥🧑🍳 #PeppaPig #Shorts 1 মিনিট 
Using a Schlieren Lens to Visualize Air Flow! (Members Update #47) 8 মিনিট 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
দেশ
মার্কিন যুক্তরাষ্ট্র
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