MiniMax-H3-Acc-LoRAs-ComfyUI

Papers using or citing this model 1

• Parallel Decoding Distillation for Fast Image and Video Generation 11 citations · 2026 · arXiv (Cornell University) · arXiv

  Generation in video diffusion or flow models is computationally expensive due to the slow and iterative sampling process. Current state-of-the-art (SOTA) acceleration methods heavily rely on variational score distillation (VSD) and...