Before Diffusion: Looking Back at VQGAN, the Pre-Diffusion Foundation of Image Generation

makeitrad1 · x · 2026-09-11

@makeitrad1 shares a "Before Diffusion" piece revisiting VQGAN — the technique that encoded images as discrete tokens and laid groundwork for generative vision before diffusion models took over.

Original post →

More from Multimodal

Multimodal channel →