Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 5 - Architectures

Short summary

Stanford graduate lecture on diffusion models and large vision architectures, covering U-Net evolution, Diffusion Transformers (DiT), multimodal variants, and advanced positional encoding techniques. Requires deep neural network background; designed for AI product builders and researchers.

• •Covers U-Net and Diffusion Transformer architectures with timeline evolution
• •Explores multimodal DiT models and state-of-the-art implementations (FLUX.1, Qwen-Image)
• •Technical deep-dive into position embeddings (RoPE) and adaptive layer normalization

Generated with AI, which can make mistakes.