---
language: en
license: apache-2.0
tags:
  - zen
  - zenlm
  - hanzo
  - zen3
  - text-to-image
  - diffusion
  - high-resolution
pipeline_tag: text-to-image
library_name: diffusers
---

# Zen3 Image Max

High-resolution variant of Zen3 Image for maximum quality image generation.

## Overview

Built on **Zen MoDE (Mixture of Distilled Experts)** architecture with 12B parameters.

Developed by [Hanzo AI](https://hanzo.ai) and the [Zoo Labs Foundation](https://zoo.ngo).

## Quick Start

```python
from diffusers import AutoPipelineForText2Image
import torch

model_id = "zenlm/zen3-image-max"
pipe = AutoPipelineForText2Image.from_pretrained(model_id, torch_dtype=torch.bfloat16)
pipe = pipe.to("cuda")

image = pipe("A serene mountain landscape at sunset, photorealistic").images[0]
image.save("output.png")
```

## API Access

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.hanzo.ai/v1", api_key="your-api-key")
response = client.images.generate(
    model="zen3-image-max",
    prompt="A serene mountain landscape at sunset",
    size="2048px",
)
print(response.data[0].url)
```

## Model Details

| Attribute | Value |
|-----------|-------|
| Parameters | 12B |
| Architecture | Zen MoDE |
| Max Resolution | 2048px |
| License | Apache 2.0 |

## License

Apache 2.0