zenlm/zen3-image-sdxl

Zen3 Image SDXL

Zen LM by Hanzo AI — High-quality text-to-image generation at 1024x1024 resolution. Based on the Zen MoDE diffusion architecture with dual text encoders.

Specs

Property	Value
Parameters	3.5B
Resolution	1024x1024
Architecture	Zen MoDE (Mixture of Distilled Experts)
Generation	Zen3

Usage

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained("zenlm/zen3-image-sdxl", torch_dtype=torch.float16)
pipe = pipe.to("cuda")

image = pipe("A futuristic Tokyo skyline at sunset").images[0]
image.save("output.png")

API Access

Available via the Hanzo AI API:

curl https://api.hanzo.ai/v1/images/generations \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -d '{"model": "zen3-image-sdxl", "prompt": "A futuristic Tokyo skyline at sunset"}'

Get your API key at console.hanzo.ai — $5 free credit on signup.

License

OpenRAIL++

---

Zen LM is developed by Hanzo AI — Frontier AI infrastructure.