pdmd2026/pdmd_4NFE_full

PDMD 4-NFE MiniMax-H3 transformer

Paper (arXiv) · Project page

Full transformer weights (MiniMaxH3Transformer3DModel, bf16) of a 4-step (4 NFE) student distilled from MiniMax-H3 with Projected Distribution Matching Distillation (PDMD). It is a drop-in replacement for the transformer/ of the base model; every other component comes from the base model. The same model is also available as a LoRA in pdmd2026/pdmd_4NFE_lora.

import torch
from diffusers import MiniMaxH3Transformer3DModel

transformer = MiniMaxH3Transformer3DModel.from_pretrained(
    "pdmd2026/pdmd_4NFE_full", torch_dtype=torch.bfloat16
)

Sample with 4 denoising steps using the base model's released scheduler configuration (shift 12 / 3).

Citation

@misc{wang2026pdmdprojecteddistributionmatching,
      title={PDMD: Projected Distribution Matching Distillation for Video Diffusion Models},
      author={Zimo Wang and Junkun Yuan and Angtian Wang and Haotian Yang and Canyu Zhang and Siyuan Yuan and Xingchang Huang and Bo Liu and Yizhi Wang and Yiding Yang and Chongyang Ma and Gordon Guocheng Qian},
      year={2026},
      eprint={2609.35768},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2609.35768},
}