Updated README with metadata, tags, and test link

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

README.md

@@ -1,7 +1,31 @@
+---
+license: other
+license_name: non-commercial
+license_link: LICENSE
+tags:
+  - image-to-image
+  - watermark-removal
+  - remove-watermark
+  - watermark
+  - torchscript
+  - computer-vision
+  - image-processing
+  - image-restoration
+  - image-cleaning
+pipeline_tag: image-to-image
+library_name: pytorch
+---
+
 # Fast Watermark Removal
 
 A high-performance TorchScript model for removing watermarks from images. This model uses a dual-stage architecture optimized for speed and quality.
 
+## Test the Model
+
+Try the model instantly in your browser — no setup required:
+
+**[Remove Watermarks → clearpics.ai](https://clearpics.ai/remove-watermarks)**
+
 ## Features
 
 - **Fast inference**: ~500ms per image (RTX 4090)
@@ -9,6 +33,15 @@ A high-performance TorchScript model for removing watermarks from images. This m
 - **Production-ready**: Compiled TorchScript model, no training code needed
 - **Memory efficient**: Requires 11.5GB VRAM
 
+## Technical Details
+
+- **Architecture**: Dual-stage with Swin2 Transformers
+- **Format**: TorchScript (.ts) compiled model
+- **Input**: RGB images (any resolution)
+- **Output**: RGB images (max 768px, aspect ratio preserved)
+- **Precision**: FP32 with TensorFloat32 matmul on Ampere+ GPUs
+- **Batch size**: 1
+
 ## Limitations
 
 - **Output resolution**: Limited to 768px maximum dimension (aspect ratio preserved)
@@ -34,10 +67,6 @@ A commercial license with **1536px maximum output resolution** is available for
 ### Setup
 
 ```bash
-# Clone the repository
-git clone https://huggingface.co/[your-username]/remove-watermarks-fast
-cd remove-watermarks-fast
-
 # Install dependencies
 pip install -r requirements.txt
 ```
@@ -53,7 +82,7 @@ python inference.py -i /path/to/watermarked/image.jpg -m model.ts -o output_fold
 ### Batch Processing
 
 ```bash
-python inference.py -f /path/to/images/folder -m model.ts -o output_folder
+python inference.py -f /path/to/images/folder -m model.ts
 ```
 
 ### Arguments
@@ -82,24 +111,10 @@ The model uses a two-stage pipeline:
 
 All processing (including resizing and normalization) is performed within the compiled TorchScript model for optimal performance.
 
-## Performance
-
-- **GPU**: NVIDIA RTX 3090 / A6000 or equivalent
-- **VRAM**: 11.5GB required
-- **Speed**: ~500ms per image (768px output)
-- **Batch size**: 1 (optimized for low latency)
-
 ## Future Improvements
 
 I'm actively exploring ways to enhance this model's capabilities. If you have suggestions, encounter issues, or are interested in collaborating on improvements, please reach out!
 
-## Technical Details
-
-- **Architecture**: Dual-stage with Swin2 Transformers
-- **Format**: TorchScript (.ts) compiled model
-- **Input**: RGB images (any resolution)
-- **Output**: RGB images (max 768px, aspect ratio preserved)
-- **Precision**: FP32 with TensorFloat32 matmul on Ampere+ GPUs
 
 ## License