RoPE and diffusion timestep embedding share the same sinusoidal skeleton and even the same frequency table. This note builds both from angular frequency up, and explains what base / max_period actually control.
Theory is clean, but training is messy. This note covers 5 essential engineering tricks—from Timestep Shifting to 3D RoPE—that stabilize training and boost performance.
A technical note on the shift from noise prediction (DDPM) to velocity prediction (Flow Matching), and how CFG acts as a vector field modifier.
From DiT to Hunyuan Video, adaLN-Zero remains the gold standard for conditioning. Here’s how this zero-initialized module works and why it persists in the era of Flow Matching.