add README and some examples

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,40 @@
 ---
 license: mit
+tags:
+- resnet
+- stable-diffusion
+- stable-diffusion-diffusers
 ---
+
+# BZH watermark detector (demo)
+
+You can use this classifier to detect watermarks generated with our [SDXL-turbo watermarking demo](https://huggingface.co/spaces/imatag/stable-signature-bzh).
+
+## Usage
+
+```py
+from transformers import AutoModel, BlipImageProcessor
+from PIL import Image
+import sys
+import torch
+
+image_processor = BlipImageProcessor.from_pretrained("imatag/stable-signature-bzh-detector-resnet18")
+model = AutoModel.from_pretrained("imatag/stable-signature-bzh-detector-resnet18", trust_remote_code=True)
+
+img = Image.open(sys.argv[1]).convert("RGB")
+inputs = image_processor(img, return_tensors="pt")
+with torch.no_grad():
+    p = torch.sigmoid(model(**inputs).logits).item()
+
+print(f"approximate p-value: {p}")
+```
+
+## Purpose
+
+This model is an approximate version of [IMATAG](https://www.imatag.com/)'s BZH decoder for the watermark embedded in our [SDXL-turbo watermarking demo](https://huggingface.co/spaces/imatag/stable-signature-bzh).
+It works on this watermark only and cannot be used to decode other watermarks.
+It will produce an approximate p-value measuring the risk of detecting a watermark an a benign (non-watermarked) image. Thresholding this value will give a hard decision on whether an image is watermarked (0) or not (1), with an approximate chance of mistakenly claiming the image is watermarked while it's not equal to the threshold. For an exact p-value, please use the [API](https://huggingface.co/spaces/imatag/stable-signature-bzh/resolve/main/detect_api.py) instead.
+
+For more details on this watermarking technique, check out our [announcement](https://www.imatag.com/blog/unlocking-the-future-of-content-authentication-imatags-breakthrough-in-ai-generated-image-watermarking) and our lab's [blog post](https://imatag-lab.medium.com/stable-signature-meets-bzh-53ad0ba13691).
+
+For watermarked models with a different key, support for payload, other perceptual compromises, robustness to other attacks, or faster detection, please [contact IMATAG](https://pages.imatag.com/contact-us-imatag).

detect_demo.py

@@ -0,0 +1,13 @@
+from transformers import AutoModel, BlipImageProcessor
+from PIL import Image
+import sys
+import torch
+
+image_processor = BlipImageProcessor.from_pretrained("imatag/stable-signature-bzh-detector-resnet18")
+model = AutoModel.from_pretrained("imatag/stable-signature-bzh-detector-resnet18", trust_remote_code=True)
+
+img = Image.open(sys.argv[1]).convert("RGB")
+inputs = image_processor(img, return_tensors="pt")
+with torch.no_grad():
+    p = torch.sigmoid(model(**inputs).logits).item()
+print(f"approximate p-value: {p}")