Add model card (README)

README.md

@@ -0,0 +1,62 @@
+---
+license: mit
+tags:
+  - image-to-image
+  - reflection-removal
+  - highlight-removal
+  - computer-vision
+---
+
+# UnReflectAnything – Pretrained Weights
+
+Pretrained weights for **UnReflectAnything**: *RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision*.
+
+- **Project**: [alberto-rota.github.io/UnReflectAnything](https://alberto-rota.github.io/UnReflectAnything/)
+- **Paper**: [arXiv](https://arxiv.org/abs/2501.12345)
+- **PyPI**: `pip install unreflectanything`
+- **Demo**: [Hugging Face Space](https://huggingface.co/spaces/AlbeRota/UnReflectAnything)
+
+## Model description
+
+These weights support the `unreflectanything` package for removing specular highlights and reflections from RGB images without polarization or multi-view input.
+
+| File | Description |
+|------|-------------|
+| `fullmodel_896.pt` | Full model checkpoint (recommended for inference) |
+| `decoder_896.pth` | Decoder weights (896px; e.g. for pretraining) |
+| `rgb_decoder.pth` | RGB decoder weights |
+| `rgb_film_decoder.pth` | RGB FiLM decoder weights |
+| `token_inpainter.pth` | Token inpainter module weights |
+
+## How to use
+
+1. **Install the package** (with optional weight-download support):
+
+   ```bash
+   pip install unreflectanything[weights]
+   ```
+
+2. **Download these weights** into the default cache:
+
+   ```bash
+   unreflectanything download-weights
+   ```
+
+   By default the CLI uses the official weights repo. To use this Hugging Face repo instead, set:
+
+   ```bash
+   export UNREFLECTANYTHING_WEIGHTS_REPO="<your-username>/<this-repo-name>"
+   unreflectanything download-weights
+   ```
+
+   Weights are stored under `~/.cache/unreflectanything/weights` (or `$XDG_CACHE_HOME/unreflectanything/weights`). Use `--output-dir` to override.
+
+3. **Run inference** with a YAML config that points `weights_path` to the downloaded directory (e.g. to `fullmodel_896.pt` for full-model inference).
+
+## Citation
+
+If you use these weights or the method, please cite the paper and/or link to this repository.
+
+## License
+
+MIT.