Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,14 @@ datasets:
|
|
| 14 |
- Colby/autotrain-data-sdxl-detection
|
| 15 |
---
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
# Model Trained Using AutoTrain
|
| 18 |
|
| 19 |
- Problem type: Image Classification
|
|
|
|
| 14 |
- Colby/autotrain-data-sdxl-detection
|
| 15 |
---
|
| 16 |
|
| 17 |
+
# SDXL Detector
|
| 18 |
+
|
| 19 |
+
This model was created by fine-tuning the [umm-maybe AI art detector](https://huggingface.co/umm-maybe/AI-image-detector) on a dataset of Wikimedia-SDXL image pairs, where the SDXL image is generated using a prompt based upon a BLIP-generated caption describing the Wikimedia image.
|
| 20 |
+
|
| 21 |
+
This model demonstrates greatly improved performance over the umm-maybe detector on images generated by more recent diffusion models as well as non-artistic imagery (given the broader range of subjects depicted in the random sample drawn from Wikimedia).
|
| 22 |
+
|
| 23 |
+
However, its performance may be lower for images generated using models other than SDXL. In particular, this model underperforms the original detector for images generated using older models (such as VQGAN+CLIP).
|
| 24 |
+
|
| 25 |
# Model Trained Using AutoTrain
|
| 26 |
|
| 27 |
- Problem type: Image Classification
|