Enhance model card for LightSwitch with metadata, links, usage, and abstract

This PR significantly enhances the model card for LightSwitch by adding crucial information for better discoverability and usability.

It includes:
- **Metadata:**
- `pipeline_tag: image-to-image`, making the model discoverable on the Hub via https://huggingface.co/models?pipeline_tag=image-to-image.
- `library_name: diffusers`, enabling the "Use in Diffusers" code snippet for easy access.
- **Content:**
- A link to the paper: [LightSwitch: Multi-view Relighting with Material-guided Diffusion](https://huggingface.co/papers/2508.06494).
- The full abstract of the paper for a comprehensive overview.
- A link to the project page: https://yehonathanlitman.github.io/light_switch/.
- A link to the GitHub repository: https://github.com/yehonathanlitman/LightSwitch.
- A clear "Usage" section, demonstrating how to load the model with `diffusers` and explicitly directing users to the GitHub repository for detailed operational instructions due to the model's complex input requirements.
- The teaser image from the project to visually represent the model's output.
- The BibTeX citation for the paper.

Please review and merge if everything looks good.

README.md

@@ -1,3 +1,50 @@
----
-license: mit
----
+---
+license: mit
+pipeline_tag: image-to-image
+library_name: diffusers
+---
+
+# LightSwitch: Multi-view Relighting with Material-guided Diffusion
+
+This model, LightSwitch, was presented in the paper [LightSwitch: Multi-view Relighting with Material-guided Diffusion](https://huggingface.co/papers/2508.06494).
+
+Project Page: [https://yehonathanlitman.github.io/light_switch/](https://yehonathanlitman.github.io/light_switch/)
+GitHub Repository: [https://github.com/yehonathanlitman/LightSwitch](https://github.com/yehonathanlitman/LightSwitch)
+
+## Abstract
+Recent approaches for 3D relighting have shown promise in integrating 2D image relighting generative priors to alter the appearance of a 3D representation while preserving the underlying structure. Nevertheless, generative priors used for 2D relighting that directly relight from an input image do not take advantage of intrinsic properties of the subject that can be inferred or cannot consider multi-view data at scale, leading to subpar relighting. In this paper, we propose Lightswitch, a novel finetuned material-relighting diffusion framework that efficiently relights an arbitrary number of input images to a target lighting condition while incorporating cues from inferred intrinsic properties. By using multi-view and material information cues together with a scalable denoising scheme, our method consistently and efficiently relights dense multi-view data of objects with diverse material compositions. We show that our 2D relighting prediction quality exceeds previous state-of-the-art relighting priors that directly relight from images. We further demonstrate that LightSwitch matches or outperforms state-of-the-art diffusion inverse rendering methods in relighting synthetic and real objects in as little as 2 minutes.
+
+## Usage
+
+You can easily load LightSwitch components using the Hugging Face `diffusers` library. For full usage, including data preparation (masks, poses) and running the multi-view relighting, please refer to the official [GitHub repository](https://github.com/yehonathanlitman/LightSwitch).
+
+```python
+from diffusers import DiffusionPipeline
+
+# Load the pretrained model (example path from original GitHub README)
+# Note: This is a UNet2DConditionModel, typically part of a larger DiffusionPipeline.
+# The `thebluser/lightswitch-multi-fov` refers to a specific model version or pipeline on the Hub.
+pipeline = DiffusionPipeline.from_pretrained("thebluser/lightswitch-multi-fov", trust_remote_code=True)
+
+# Actual usage involves complex inputs (image, mask, intrinsics, extrinsics, envmap).
+# The model is designed for multi-view relighting and integrates with 3DGS.
+# Please consult the GitHub repository's "Running" section for detailed instructions:
+# https://github.com/yehonathanlitman/LightSwitch#running
+```
+
+<p align="center">
+  <img src="https://github.com/yehonathanlitman/LightSwitch/blob/main/assets/lightswitch_v2.svg" alt="Teaser image" width="600">
+</p>
+
+## Citation
+
+If you use any parts of our work, please cite the following:
+
+```bibtex
+@inproceedings{litman2025lightswitch,
+  author    = {Yehonathan Litman and Fernando De la Torre and Shubham Tulsiani},
+  title     = {LightSwitch: Multi-view Relighting with Material-guided Diffusion},
+  booktitle = {ICCV},
+  year      = {2025}
+}
+```