Instructions to use zenlm/zen-video-i2v with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zenlm/zen-video-i2v with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image, export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zenlm/zen-video-i2v", torch_dtype=torch.bfloat16, device_map="cuda") pipe.to("cuda") prompt = "A man with short gray hair plays a red electric guitar." image = load_image( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png" ) output = pipe(image=image, prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
Status: Experimental; superseded by zenlm/zen-director (text-and-image-to-video). Weights remain available for reproducibility.
zen-video-i2v
Image-to-video generation.
Repackaged from Wan-AI/Wan2.2-I2V-A14B (apache-2.0, Alibaba Wan). Not trained from scratch — a permissively-licensed redistribution for the OSS-clean Zen model line.
License
apache-2.0. Upstream: Wan-AI/Wan2.2-I2V-A14B by Alibaba Wan. Upstream LICENSE/NOTICE retained in-repo.
- Downloads last month
- -
Model tree for zenlm/zen-video-i2v
Base model
Wan-AI/Wan2.2-I2V-A14B