---
license: apache-2.0
tags:
- pytorch
- sid-unet
- image-segmentation
- synthetic-image-detection
- diffusion-detection
pipeline_tag: image-segmentation
library_name: sid-unet
---

# diffusion-diff-minimized-512

Official repository for **diffusion-diff-minimized-512** checkpoints, evaluated on AI-generated image detection and segmentation tasks.

## 📌 Available Versions

| Version | Best Metric Score | Best Epoch | Updated |
| :--- | :--- | :--- | :--- |
| `v1` | 0.2837402272008726 | 3 | 2026-11-02 |

- **Active Version:** `v1`
- **Best Validation Score:** `0.2837402272008726` (Epoch `3`)
- **Total Training Epochs:** `3`

---

## 🚀 Quickstart & Checkpoint Usage

### 1. Pull checkpoints using `sid-pull`
To download the latest checkpoint directly to your local workspace:
```bash
sid-pull --name KhangTruong/diffusion-diff-minimized-512
```

To pull a specific version:
```bash
sid-pull --name KhangTruong/diffusion-diff-minimized-512 --version v1
```

### 2. Resume or Fine-tune with `sid-train`
Once downloaded, resume training seamlessly:
```bash
sid-train --config configs/experiments/diffusion_diff_minimized/default.yaml --override training.epochs=40
```
Or specify explicit checkpoint path:
```bash
sid-train --resume checkpoints/checkpoint_latest.pt
```

### 3. Push new checkpoints using `sid-push`
```bash
sid-push --name KhangTruong/diffusion-diff-minimized-512 --version v2
```

---

## 📂 Repository Layout

```
KhangTruong/diffusion-diff-minimized-512/
├── README.md               # Model Card & Documentation
├── config.yaml             # Model & Training Configuration
├── manifest.json           # Catalog of all versions & metrics
├── checkpoints/            # Active / Latest Checkpoints
│   ├── checkpoint_best.pt
│   ├── checkpoint_latest.pt
│   └── checkpoint_periodic.pt
├── reports/                # Evaluation reports & plots
│   ├── training_curves.png
│   └── test_evaluation_report.json
└── versions/               # Version Archive
    └── v1/
        ├── checkpoints/
        └── reports/
```