docs: restore OpenSight community validation and preview sections
Browse files
README.md
CHANGED
|
@@ -21,6 +21,12 @@ tags:
|
|
| 21 |
|
| 22 |
Vision Transformer (ViT-Small) trained on 2.7M samples across 4,803 generators for detecting AI-generated images. Presented in [Community Forensics: Using Thousands of Generators to Train Fake Image Detectors](https://huggingface.co/papers/2411.04125) (CVPR 2025).
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
## IMPORTANT — Configuration Fix (July 2026)
|
| 25 |
|
| 26 |
**If you downloaded this model before July 22, 2026, your local copy has incorrect config and weights.** Apologies for the mess — this model was originally hastily put together as an internal proof-of-concept for a hackathon, and we never imagined it would quietly become one of the top image classification models on Hugging Face. This update is long overdue.
|
|
|
|
| 21 |
|
| 22 |
Vision Transformer (ViT-Small) trained on 2.7M samples across 4,803 generators for detecting AI-generated images. Presented in [Community Forensics: Using Thousands of Generators to Train Fake Image Detectors](https://huggingface.co/papers/2411.04125) (CVPR 2025).
|
| 23 |
|
| 24 |
+
**Uploaded for community validation as part of OpenSight** — An upcoming open-source framework for adaptive deepfake detection.
|
| 25 |
+
|
| 26 |
+
**Project OpenSight HF Spaces coming soon with an eval playground and eventually a leaderboard. Preview:**
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
|
| 30 |
## IMPORTANT — Configuration Fix (July 2026)
|
| 31 |
|
| 32 |
**If you downloaded this model before July 22, 2026, your local copy has incorrect config and weights.** Apologies for the mess — this model was originally hastily put together as an internal proof-of-concept for a hackathon, and we never imagined it would quietly become one of the top image classification models on Hugging Face. This update is long overdue.
|