Aylık katılım
aylıkİçeriğimde tekrarlayan bir koltuk. Aboneler bir kuyruğa girer — veya yuvalardan daha fazla abone olduğunda rastgele çekilişe — ve videonun kendisinde, jenerikte veya açıklamada görünür.
aylık
Fiyat talep üzerine
Sıradaki
But how do AI images and videos actually work? | Guest video by Welch Labs 38 dk 
The Second Punic War - OverSimplified (Part 3) 50 dk 
Это голограмма или телепорт? Что это? #Shorts 1 dk 
Blade Runner 11 dk 
STRAIGHT PIPES 2 dk 
ONE OF US 3 dk 
The Second Punic War - OverSimplified (Part 2) 38 dk 
The Napoleonic Wars - OverSimplified (Part 2) 32 dk 
The Grid That Doubles the Strength of the Ground 19 dk 
Mesa 4 dk 
How Nike Lost Its Way 19 dk 
Are Beavers Actually Good at Dams? 20 dk 
How Disney Built A Realistic Lightsaber 17 dk 
The Strangest Operating System in History | Fascinating Horror Shorts 1 dk 
How a broken heart affects your body 6 dk 
Why do Human Feet Wash up on This Beach? | Fascinating Horror Shorts 1 dk 
So hot underground it smokes!! 1 dk 
Recreating an Ancient Pump (with no moving parts) 14 dk 
I've Been Thinking 1 dk 
Evil Ed’s Terrifying Wolf Transformation | Fright Night 5 dk 
Name That Infrastructure (Ep. 7) #shorts 1 dk 
Name That Infrastructure (Ep. 15) #shorts 1 dk 
Man Turns an Empty Space into a Dream Garage | @SmartEasyDIYer 
Practical Magic (1998) - The Exorcism of Nicole Kidman! (10/11) | Movieclips 6 dk 
The Blob’s Epic Practical Horror Finale | The Blob 7 dk 
Plato’s infamous Ship of State thought experiment - Michael Vazquez 6 dk 
Nobody Uses These Common Objects Correctly 17 dk 
Sneak peek at the making of a TED-Ed animation #shorts 1 dk 
Jakey - DRIVE OFF A BRIDGE (Official Video) 5 dk 
The Dark Side of the World’s Lightest Structural Metal 16 dk 
India’s internet war 9 dk 
The Shoe That Broke Running 16 dk 
The Problems with China's Space Program 17 dk 
Something Huge Is Coming... 3 dk 
13 most EXPENSIVE Tech Fails of all time 24 dk 
The Failed Logistics of Hurricane Katrina 21 dk 
Scientists Finally Figured Out Why This River Flows Uphill 12 dk 
Spain’s temperatures are HIGH rn 🔥 1 dk 
Crash Course Hosts Read Comments 2 dk 
3 ways to choose a sunscreen #shorts 1 dk 
Germ Theory Is Older Than You Think 1 dk 
Why do male nipples exist? 1 dk 
Lily Gladstone Reads Comments 3 dk 
The dark origins of Disney fairy tales - Claudia Schwabe 6 dk 
AI News: GPT-5.6 and the new Super App are a Massive Leap! 39 dk 
My bed is basically a JARVIS at night 💤 #eightsleep #sleepingpod #engineering 1 dk 
1000+ hours of Learning Claude in 15 Minutes (Beginner to Pro) 15 dk 
Is the Secret to Treating Schizophrenia in... Engineering? 23 dk 
Peppa Makes Perfume 🌸 #shorts #peppapig 1 dk 
Those Ancient Giant Fungi Weren’t Fungi After All 15 dk 
The Fungus You Should Actually Be Worried About 18 dk But how do AI images and videos actually work? | Guest video by Welch Labs
2025 38 dk
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
Ülke
Amerika Birleşik Devletleri
Bu yaratıcıyla çalış
Bu videonun arkasındaki yaratıcı tarafından yayınlanan paketler.
Bu yaratıcı henüz ücretlerini belirlemedi. Bir talep gönderin, biz iletelim — fiyat, herhangi bir ücret alınmadan önce kararlaştırılır.
Garantili yerleştirme — yeni video
tek seferlikBir sonraki videomda en az 10 saniyelik garantili bir görünüm. Fiyat, yerleştirmenin çalışma süresinin neresine denk geldiğine bağlıdır.
- İlk 1–3 dakika
- Videonun ortası
- Videonun sonu
Fiyat talep üzerine
- İlk 1–3 dakika
- Videonun ortası
- Videonun sonu
Garantili yerleştirme — Short
tek seferlikMevcut videolarımdan birinden kesilmiş bir Short içinde en az 10 saniyelik garantili bir görünüm.
tek seferlik
Fiyat talep üzerine