CFG-free Distillation: Fast Generation Without Guidance
Eliminating the 2x computational cost of CFG. Achieving same quality with single forward pass.
CFG-free Distillation: Fast Generation Without Guidance
Eliminating the 2x computational cost of Classifier-Free Guidance. Achieving CFG quality with a single forward pass.
TL;DR
- Problem: CFG requires two forward passes (conditional + unconditional) = 2x cost
- Solution: Distill CFG effect into a single model
The rest of this series is paid
- ✓ The whole “Diffusion models: DDPM to DiT” series: 6 posts in English, 3 in Korean
- ✓ 6 Jupyter notebooks
- ✓ One payment, no expiry. Opens when you sign in with the email you pay with.
The series pass needs no account to pay. The subscription needs a free account.