zen-video-i2v

Repackaged from Wan-AI/Wan2.2-I2V-A14B (Apache-2.0, Alibaba Wan team); NOT trained from scratch.

zen-video-i2v is a faithful re-host of the Wan2.2-I2V-A14B image-to-video MoE diffusion model under the zenlm namespace. The high-noise and low-noise expert weights, the Wan VAE, the umT5-XXL text encoder, tokenizer, and configs are byte-for-byte the upstream release. No fine-tuning or modification has been performed.

License

Apache License 2.0, inherited unchanged from upstream Wan-AI/Wan2.2-I2V-A14B. Credit belongs to the Alibaba Wan team. See the bundled NOTICE.

Attribution

Upstream model: Wan-AI/Wan2.2-I2V-A14B
Upstream authors: Alibaba Wan team
Upstream license: Apache-2.0

Downloads last month: -

Model tree for zenlm/zen-video-i2v

Base model

Wan-AI/Wan2.2-I2V-A14B

Finetuned

(85)

this model