A seguir
But how do AI images and videos actually work? | Guest video by Welch Labs 38 min 
How We Built The ISS 37 min 
UNDEAD DOGS 1 min 
NO SAFETY ON A BODY 2 min 
Glass is glass 5 min 
Я загрузил ИИ в Скайрим... и вот чот вышло 🤣 23 min 
The Hidden Engineering of Floating Bridges 18 min 
Recreating an Ancient Pump (with no moving parts) 14 min 
The Craziest Experiment Humans Have Ever Built 18 min 
World's First Touchscreen MacBook 1 min 
Why Gravity Is A Lie, explained in Zero G 23 min 
I Tested NASA's New Space Suit (Ft. Axiom Space) 26 min 
Replacing Yourself with AI is Stupid 14 min 
So You Want to Build a Tunnel... 21 min 
India’s internet war 9 min 
Spreading Poop Everywhere Situation is Crazy 12 min 
Magnetic Floating Skateboard. 1 min 
Valve's Steam Frame is okay... but I love other things about it 2 min 
I Pranked America's Most Racist Man 35 min 
Woman Rescues Flooded Car And Restores It Back To New | By @Flame-Frame-VN 
Practical Magic (1998) - Sisterly Witchy Mischief (4/11) | Movieclips 2 min 
Kling 2.6 generates clean cinematic and highly consistent videos on higgsfield #aivideo 1 min 
Essential Skills for Becoming an AI Engineer: RAG, AI Agents, & More 11 min 
From Garden to Jar | Preserving Cucumbers & Tomatoes for Winter 🌿🍅 26 min 
From Garden to Jar | Preserving Bell Peppers for Winter 🫙🌶️🍃 31 min 
The Los Angeles Aqueduct is Wild 23 min 
Name That Infrastructure (Ep. 15) #shorts 1 min 
What does a parent owe their child? | The Gray Area 27 min 
Kidneys for sale | The Gray Area 48 min 
Infrared Touchscreens #technology #electronic #experiment 1 min 
These Plants Have Digital Twins #science #scishow #plant #xray 1 min 
Election deniers on the ballot 2 min 
I Built a Bike that COOKS Pizza!! 19 min 
How to be less neurotic | The Gray Area 38 min 
How Liquid Dampers in Skyscrapers Work 20 min 
Why men can’t get hard 9 min 
Changing the future, one student voice at a time #shorts 1 min 
Why do gay people sound like that? 6 min 
Do Retention Ponds Actually Work? 18 min 
Happy Teacher Appreciation Week! 1 min 
Intro to Geology: Crash Course Geology #1 10 min 
How porn completely changes your brain 9 min 
The NFL's Concussion Crisis 22 min 
Edgar Allan Poe's story of the Red Death - Iseult Gillespie 8 min 
Daddy Pig Drives on the Wrong Side in Italy 🚗 #shorts #peppapig 1 min 
How the Mormon Church Made $293 Billion 71 min 
The Force is strong with this build. The instructions are not #tbt #hacksmith #makeitreal #starwars 2 min 
AI News: OpenAI Absolutely Cooked This Week! 35 min 
George’s Balloon 🎈 #shorts #peppapig 1 min 
Our rocket had performance issues. Please respect its privacy. #rocket #fail #engineering 1 min 
Should Kids Still Go To College? (Answering All Your Questions) 48 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
Pacotes publicados pelo criador deste vídeo.
Este criador ainda não definiu suas tarifas. Envie uma solicitação e nós a repassaremos — o preço é acordado antes de qualquer cobrança.
Um lugar recorrente no meu conteúdo. Os assinantes entram em uma fila — ou em um sorteio aleatório quando há mais assinantes do que vagas — e aparecem no próprio vídeo, nos créditos ou na descrição.
por mês
Preço sob consulta
Uma aparição garantida de pelo menos 10 segundos no meu próximo vídeo. O preço depende de onde a inserção cai no tempo de execução.
Preço sob consulta
Uma aparição garantida de pelo menos 10 segundos em um Short extraído de um dos meus vídeos existentes.
único
Preço sob consulta