Update README.md

README.md

@@ -1,3 +1,80 @@
 ---
 license: mit
+pipeline_tag: image-to-image
+tags:
+- style-transfer
+- pytorch
 ---
+
+# Fast Neural Style Transfer — Starry Night
+
+This repository contains weights for a Fast Neural Style Transfer network based on Johnson et al. It is trained on the COCO val2017 dataset to instantly apply Vincent van Gogh's *The Starry Night* style to any input image.
+
+## Style Transfer Preview
+
+
+| Content Image | Stylized Output |
+| :---: | :---: |
+| <img src="before.jpg" width="400"> | <img src="after.jpg" width="400"> |
+
+---
+
+## How to Use Programmatically
+
+You can run inference using the Hugging Face `transformers` library. The script automatically downloads your weights and applies the necessary ImageNet normalization matching the training routine.
+
+### Dependencies
+Ensure you have the required packages installed:
+```bash
+pip install torch torchvision transformers pillow huggingface_hub
+```
+
+### Inference Script (`inference.py`)
+Save the following code as `inference.py`. You can run it via terminal with `python inference.py your_image.jpg`.
+
+```python
+import sys
+import torch
+from PIL import Image
+from torchvision import transforms
+from torchvision.utils import save_image
+from transformers import AutoModel
+
+# ── CONFIG ───────────────────────────────────────────────────
+REPO_ID  = "Rohanify/Brawnz-StyleTransfer"  # Your repository ID
+IMG_SIZE = 512
+DEVICE   = "cuda" if torch.cuda.is_available() else "cpu"
+# ─────────────────────────────────────────────────────────────
+
+# ── LOAD IMAGE ───────────────────────────────────────────────
+if len(sys.argv) < 2:
+    print("Usage: python inference.py path_to_input_image.jpg")
+    sys.exit(1)
+
+input_path = sys.argv[1]
+output_path = "output_styled.jpg"
+
+transform = transforms.Compose([
+    transforms.Resize((IMG_SIZE, IMG_SIZE)),
+    transforms.ToTensor(),
+    transforms.Normalize([0.485, 0.456, 0.406],
+                         [0.229, 0.224, 0.225]),
+])
+
+img = Image.open(input_path).convert("RGB")
+x   = transform(img).unsqueeze(0).to(DEVICE)
+
+# ── LOAD MODEL FROM HUGGING FACE ─────────────────────────────
+print("Loading model weights from Hugging Face Hub...")
+model = AutoModel.from_pretrained(REPO_ID, trust_remote_code=True).to(DEVICE)
+model.eval()
+
+# ── RUN INFERENCE ────────────────────────────────────────────
+print(f"Running inference on device: {DEVICE}...")
+with torch.no_grad():
+    out = model(x)
+
+# De-normalize and save output image
+save_image(out[0] * 0.5 + 0.5, output_path)
+print(f"Success! Styled image saved to: {output_path}")
+```