Downloads · 30 days
62
15% of all-time downloads
zen-world
zenlm/zen-world
zen-world is a text-to-video model from zenlm. Use it when you need video from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
All-time downloads
423
Public
Parameters
14.3B
69.1 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors57.2 GB · 83%
At a glance
- Task
- Text-to-Video
- Library
- diffusers
- License
- apache-2.0
- Model type
- t2v
- Access
- Public
- Created
- Nov 13, 2025
- Updated
- Jun 26, 2026
- SHA
- 48735e63
Base models
Model card
From the Hugging Face model README
Zen World
Text-to-video generation model.
Derived from Wan-AI/Wan2.1-T2V-14B (Apache-2.0); repackaged by Zen.
Overview
This repository repackages Alibaba Wan2.1-T2V-14B (WanModel DiT, dim 5120 / 40 layers, Wan2.1 VAE + umt5-xxl text encoder). No weights were trained from scratch by Zen.
Developed/repackaged by Hanzo AI and the Zoo Labs Foundation.
Model Details
| Attribute | Value |
|---|---|
| Base model | Wan-AI/Wan2.1-T2V-14B |
| Architecture | WanModel (DiT), 14B |
| License | Apache 2.0 |
License & Attribution
Apache 2.0. This is a derivative repackaging of Wan2.1-T2V-14B by Alibaba (Wan team), released under the Apache License 2.0. All rights and attribution for the underlying model belong to the original authors.
NOTICE
This product includes the Wan2.1-T2V-14B model developed by Alibaba (Wan-AI team), licensed under the Apache License 2.0.
- Task
- Text-to-Video
- Library
- diffusers
- Type
- t2v
- License
- apache-2.0
- Languages
- en
- Created
- Nov 13, 2025
- Updated
- Jun 26, 2026