PTD checkpoints

Four-step and six-step MiniMax-H3 adapter checkpoints trained by EPFL VITA Lab based on Parametric Trajectory Distillation for Few-Step Video Generation (PTD).

Checkpoints

Directory Recipe Sampling steps Size
ptd_h3_4step/ h3_4step 4 11.5 GB
ptd_h3_6step/ h3_6step 6 17.2 GB

Each directory contains a torch.distributed.checkpoint state dict with per-hop LoRA adapters and training-only heads. Inference uses the adapters and ignores the heads. Training settings, hop grids and provenance are recorded in ptd_info.json.

Usage

Code and setup instructions: PTD inference (standalone and ComfyUI).

For standalone inference, pass the checkpoint directory as --ckpt and its matching recipe from the table as --recipe.

License

These adapters are Model Derivatives under the MiniMax H3 Community License Agreement. See LICENSE-MiniMax-H3.txt and NOTICE for terms and attribution.

Citation

@misc{feng2026ptd,
  title  = {Parametric Trajectory Distillation for Few-Step Video Generation},
  author = {Feng, Lan and Karkus, Peter and Igl, Maximilian and Berner, Julius and Chen, Yuxiao and
            Tan, Shuhan and Alahi, Alexandre and Ivanovic, Boris and Pavone, Marco},
  year   = {2026},
  note   = {Under review}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for epfl-vita/PTD-weights

Adapter
(162)
this model