Update README.md
Browse files
README.md
CHANGED
|
@@ -6,4 +6,11 @@ base_model:
|
|
| 6 |
- stabilityai/stable-diffusion-3.5-medium
|
| 7 |
pipeline_tag: image-to-image
|
| 8 |
library_name: transformers
|
| 9 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
- stabilityai/stable-diffusion-3.5-medium
|
| 7 |
pipeline_tag: image-to-image
|
| 8 |
library_name: transformers
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# CLUE Model Card
|
| 12 |
+
## Model details
|
| 13 |
+
|
| 14 |
+
**Model type:** This model, named CLUE, is an advanced image forgery localization framework that synergistically combines a LoRA-tuned Stable Diffusion 3 (SD3) and Segment Anything Model (SAM). It uniquely leverages SD3's Rectified Flow mechanism to amplify subtle forensic artifacts, which enables state-of-the-art localization of forged image regions.
|
| 15 |
+
|
| 16 |
+
**Project page:** https://github.com/youqiwong/CLUE.git
|