Parallel Decoding Distillation cuts video diffusion to 4‑8 steps, boosting speed and diversity
NVIDIA’s Parallel Decoding Distillation predicts several denoising steps per forward pass, letting diffusion and flow‑matching models generate video with just 4‑8 function evaluations. The method works with any pre‑trained model and delivers state‑of‑the‑art quality while boosting video diversity.