Imager-1

Imager-1 is an AI model designed to detect AI-generated images with high precision; it can detect DALL-E 2. We will soon launch imager-1-small and imager-2, which will be able to detect DALL-E 3 and other text-to-image models.

Results

🎯 Accuracy	📉 Loss	🧠 Parameters
98.18%	0.1717	50M

Validation Accuracy: 98.18% — evaluated on 15% of the dataset, never seen during training.

Validation Loss: 0.1717 — the model shows strong generalization with no signs of overfitting.

Parameters: 50M — optimized for real-world deployment, including browser inference via ONNX.

About this release

This repository contains the base model of Imager-1, released for developers and researchers who want direct access to the architecture, weights, and training pipeline.

Imager always publishes a separately verified and production-ready version of each model, tested against real-world generators before release. This base model is provided so the community can build on top of it, fine-tune it, or integrate it into their own systems.

Access to the most powerful Imager models is always granted through the official channels.

Task

Binary image classification.

Label	Meaning
0	AI-generated
1	Real

License

Apache 2.0