Downloads · 30 days
0
VPT
zhengzhou/VPT
VPT is a machine learning model from zhengzhou. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
VPT is a fine-tuning framework that improves the physical consistency of pretrained video diffusion models (e.g. Wan2.1-T2V) while preserving their visual quality.
Access
Public
Updated Jul 5, 2026
Repo size
10.3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.zip10.2 GB · 99%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 5, 2026
- Updated
- Jul 5, 2026
- SHA
- edacaa97
Model card
From the Hugging Face model README
VPT: Enhancing Video Physical Consistency via Role-aware Joint Training and Modality-decoupled Denoising
VPT is a fine-tuning framework that improves the physical consistency of pretrained video diffusion models (e.g. Wan2.1-T2V) while preserving their visual quality.
- License
- apache-2.0
- Created
- Jul 5, 2026
- Updated
- Jul 5, 2026