Seuraava
But how do AI images and videos actually work? | Guest video by Welch Labs 38 min 
Actually Stranded on a Deserted Island for 42 Hours (real emergency) 37 min 
Hijack 6 min 
The tragedy of Cassandra, the princess who predicted the fall of Troy - Iseult Gillespie 5 min 
The Weirdest Tool in Underwater Construction 18 min 
The Napoleonic Wars - OverSimplified (Part 2) 32 min 
Bretagne 3 min 
The Hidden Engineering of Runways 19 min 
What If I Fell Into A Black Hole? 20 min 
I tested every new Apple Product! 15 min 
The Real Gear I Use in My YouTube Studio! (Complete Tour) 12 min 
The Most Surreal Holiday Photo | Fascinating Horror Shorts 1 min 
4,000,000 - Q&A 11 min 
Sunday on 60 Minutes: Patrick Clancy 1 min 
Why American Houses Are So Flimsy 15 min 
Plasma Globe is a ⚡Shocking⚡🔥Fire Hazard🔥 12 min 
Crashed By A Crocodile? The Filair Let-410 Crash | Fascinating Horror 11 min 
How a Super El Niño affects the global climate 7 min 
The Pig War - OverSimplified 39 min 
Fixing the Most Dangerous Dam in the World 23 min 
Man Turns an Empty Space into a Dream Garage | @SmartEasyDIYer 
An Engineer's Perspective on the Texas Floods 24 min 
The Los Angeles Aqueduct is Wild 23 min 
Plato’s infamous Ship of State thought experiment - Michael Vazquez 6 min 
Name That Infrastructure (Ep. 1) #shorts 1 min 
Essential Skills for Becoming an AI Engineer: RAG, AI Agents, & More 11 min 
How to be less neurotic | The Gray Area 38 min 
Kidneys for sale | The Gray Area 48 min 
Why some of California's billionaires are fleeing 2 min 
Something Huge Is Coming... 3 min 
The Steam Machine Killer 2 min 
Why Can't I Vote Online? 13 min 
The right’s anti-Muslim midterms strategy 2 min 
Steam Frame Review - This Changes Everything 24 min 
I Promise you this is NOT Stupid 10 min 
Why Sagrada Familia Took 144 Years to Complete 25 min 
Spain’s temperatures are HIGH rn 🔥 1 min 
The Stinky Fish Sauce Ancient Romans Couldn’t Live Without 14 min 
The Terrible Design of Newark Airport 17 min 
Is it Possible to Prepare for an Earthquake?: Crash Course Geology #15 13 min 
Janus Is Two-Faced #scishow #science #space 1 min 
What your ball size says about you 8 min 
Why NASA Is Racing Back To The Moon 11 min 
Building Robotic Hands | Real Life Power Armor (Part 5/6) 24 min 
Nobody talks about this part of India (the 7 sisters) 21 min 
I Tried To Make Something In America (The Smarter Scrubber Experiment) - Smarter Every Day 308 49 min 
EXTREME Hide & Seek (Hunting my Employees 2024) 24 min 
Covering the POWER ARMOR in this SUPER ALLOY | Real Life Power Armor (Part 9/6) 30 min 
Engineer guessing these "geniuses" 🤔 #engineering #fifa 1 min 
Peppa Pig WINS the DUCK RACE for Baby EVIE! 🦆🏆 | BRAND NEW Peppa Pig Full Episodes | 4 Hours 243 min 
Lasers vs Lightning- Which Is More Powerful? 29 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
Tämän videon tekijän julkaisemat paketit.
Tämä tekijä ei ole vielä asettanut hintojaan. Lähetä pyyntö, niin välitämme sen eteenpäin — hinta sovitaan ennen kuin mitään veloitetaan.
Toistuva paikka sisällössäni. Tilaajat menevät jonoon — tai satunnaiseen arvontaan, kun tilaajia on enemmän kuin paikkoja — ja esiintyvät itse videossa, krediiteissä tai kuvauksessa.
kuukaudessa
Hinta pyynnöstä
Taattu esiintyminen vähintään 10 sekunniksi seuraavassa videossani. Hinta riippuu siitä, mihin kohtaan kestoa lisäys sijoittuu.
Hinta pyynnöstä
Taattu esiintyminen vähintään 10 sekunniksi Shortissa, joka on leikattu olemassa olevasta videostani.
kertamaksu
Hinta pyynnöstä