zen-director

Text/image-to-video generation model.

Derived from Wan-AI/Wan2.2-TI2V-5B (Apache-2.0); repackaged by Zen.

WARNING - incomplete upload: The model weights in this repository are INCOMPLETE. Only one of the diffusion transformer shards is present (diffusion_pytorch_model-00003-of-00003.safetensors); the remaining shards are missing, so this repo is not loadable as-is until the full weight set is re-uploaded.

Overview

This repository repackages Alibaba Wan2.2-TI2V-5B (WanModel DiT, ti2v, dim 3072 / 30 layers, in_dim 48, Wan2.2 VAE). 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/Wan2.2-TI2V-5B
Architecture	WanModel (DiT), 5B, ti2v
License	Apache 2.0
Status	Weights incomplete (missing shards)

License & Attribution

Apache 2.0. This is a derivative repackaging of Wan2.2-TI2V-5B 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 Wan2.2-TI2V-5B model developed by Alibaba (Wan-AI team), licensed under the Apache License 2.0.