Imager-1-Tiny
Imager-1-Tiny is the lightweight version of the Imager family: an AI-generated image detector with 25M parameters, designed for fast inference and deployment on servers or edge devices via ONNX.
Try it
imager.cc
Upload an image and get an instant prediction
with confidence scores for both AI-generated and Real classes.
Results
| Accuracy | Loss | Parameters |
|---|---|---|
| 93.00% | 0.2417 | 25M |
Validation Accuracy: 93.00% — evaluated on 15% of the dataset, never seen during training.
Validation Loss: 0.2417 — the model shows strong generalization with no signs of overfitting.
Parameters: 25M — optimized for fast inference on servers and edge devices.
About this release
This repository contains the base model of Imager-1-Tiny, released for developers and researchers who want direct access to the 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 |