Model Architectures · Go deeper
Diffusion Models
How Stable Diffusion, DALL-E, and Midjourney create images from pure noise — by learning to run destruction in reverse.
- 50 min lesson
- advanced level
- Narrated presentation
What you’ll learn
- Forward noising process
- Learned reverse denoising
- Text conditioning via cross-attention
- Classifier-free guidance
- Latent diffusion
- Sampling steps vs. quality
Inside this lesson
A narrated, slide-by-slide presentation with 1 prediction exercise, 1 knowledge check, 1 video. You answer as you go, and the platform checks your work.