zen-voyager

Zen Voyager

Camera-controlled world exploration model for interactive scene generation.

Overview

Built on Zen MoDE (Mixture of Distilled Experts) architecture with N/A parameters.

Developed by Hanzo AI and the Zoo Labs Foundation.

Quick Start

from diffusers import AutoPipelineForText2Video
import torch

model_id = "zenlm/zen-voyager"
pipe = AutoPipelineForText2Video.from_pretrained(model_id, torch_dtype=torch.bfloat16)
pipe = pipe.to("cuda")

video_frames = pipe("A drone flying over a tropical coastline at golden hour").frames[0]

API Access

from openai import OpenAI

client = OpenAI(base_url="https://api.hanzo.ai/v1", api_key="your-api-key")
response = client.images.generate(
    model="zen-voyager",
    prompt="A drone flying over a tropical coastline at golden hour",
    size="1280x720",
)
print(response.data[0].url)

Model Details

License

Apache 2.0