lattice-open/lattice-diffuse-xl
Image generation3.4B paramssafetensorsLicense: openrail#diffusion#text-to-image
Updated Sep 24, 2026
Part of the Open Pace seed catalog. Weights are listed for the preview and become downloadable at launch.
Overview
A text-to-image diffusion model trained on captioned images with recorded provenance.
lattice-open/lattice-diffuse-xl is a 3.4B-parameter image generation model, published in safetensors under the openrail license.
Intended use
- Image generation in the domains described above.
- Research, prototypes and products that keep a person in the loop.
- Fine-tuning as a starting point for a narrower task.
How to use
# Command-line client (planned; the shape may change)
pace pull lattice-open/lattice-diffuse-xl
# Python (planned)
from openpace import load
model = load("lattice-open/lattice-diffuse-xl")Limitations
- Accuracy falls on lighting, angles and object types it rarely saw.
- Do not use it for decisions about people, such as identification or surveillance.
License
Released under openrail. Read the license file before using the weights commercially.