Hi everyone,
We are excited to share MiniMax-H3-PTD-LoRAs, a collection of few-step video generation acceleration weights trained by our team.
These weights are trained based on the awesome method proposed in the recent paper “Parametric Trajectory Distillation for Few-Step Video Generation” (by Lan Feng et al., 2026). We applied their PTD method to the MiniMax-H3 33B model and successfully baked it into lightweight LoRA adapters!
**Hugging Face Repo:** [huggingface.co](http://huggingface.co)
**Credits to the Original Paper:** [github.io](http://github.io)
What’s Inside?
We’ve provided a quick-start inference script in our Hugging Face Model Card. Feel free to try them out and let us know your feedback or show us your generated videos!
Kudos to the original authors for such an amazing distillation method!
Best, Taobao Content AI Team
source & further reading
discuss.huggingface.co — original article
Rakarrack-0.6.1 port making progress! ( AI assisted )
Cloud Storage Poll
Welcome to Haiku basic(Haiku Docs, Haiku slide and Haiku sheets)