openpace/pace-vision-caption

Image to text900M paramssafetensorsLicense: apache-2.0en#captioning#vqa

Updated Sep 2, 2026

Part of the Open Pace seed catalog. Weights are listed for the preview and become downloadable at launch.

Overview

Short, factual image captions and simple visual questions.

openpace/pace-vision-caption is a 900M-parameter image to text model, published in safetensors under the apache-2.0 license.

Intended use

Image to text in en.
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 openpace/pace-vision-caption

# Python (planned)
from openpace import load
model = load("openpace/pace-vision-caption")

Limitations

Captions can miss small details or invent ones that are not there.
It is not built to read dense text in images.

License

Released under apache-2.0. Read the license file before using the weights commercially.