Improve model card: add metadata, links and sample usage

Hi! I'm Niels from the community science team at Hugging Face. I've opened this PR to improve the documentation for OmniStream.

The changes include:
- Adding metadata for better discoverability (`pipeline_tag`, `library_name`, and `license`).
- Adding links to the research paper, project page, and official GitHub repository.
- Including a sample usage snippet derived from your official README to help users get started with the model.

README.md

@@ -1,3 +1,57 @@
----
-license: mit
----
+---
+license: mit
+library_name: transformers
+pipeline_tag: image-feature-extraction
+---
+
+# OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams
+
+OmniStream is a unified streaming visual backbone that effectively perceives, reconstructs, and acts from diverse visual inputs. By incorporating causal spatiotemporal attention and 3D rotary positional embeddings (3D-RoPE), the model supports efficient, frame-by-frame online processing of video streams via a persistent KV-cache.
+
+- **Paper:** [OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams](https://huggingface.co/papers/2603.12265)
+- **Project Page:** [https://go2heart.github.io/omnistream/](https://go2heart.github.io/omnistream/)
+- **Repository:** [https://github.com/Go2Heart/OmniStream](https://github.com/Go2Heart/OmniStream)
+
+## Sample Usage
+
+The following code snippet demonstrates how to use OmniStream for feature extraction. Note that this requires the `model.py` file from the official repository to be present in your environment.
+
+```python
+from model import OmnistreamMultiFrameTransformer
+from transformers import AutoImageProcessor
+import torch
+import numpy as np
+
+# Load processor and model
+processor = AutoImageProcessor.from_pretrained("StreamFormer/OmniStream")
+model = OmnistreamMultiFrameTransformer.from_pretrained("StreamFormer/OmniStream").to("cuda")
+
+model.eval()
+
+# Prepare dummy input: 16 frames of 512x512 RGB images (Batch x Time, Height, Width, Channels)
+fake_pixel = np.random.randn(16, 512, 512, 3) 
+fake_input = processor(images=fake_pixel, return_tensors="pt").to("cuda") 
+
+# Reshape to (Batch, Time, Channels, Height, Width)
+fake_input["pixel_values"] = fake_input["pixel_values"].unsqueeze(0).float() 
+
+with torch.no_grad():
+    output = model(**fake_input, return_dict=True)
+
+print(output.keys())
+print(output["last_hidden_state"].shape) # last layer's hidden states
+print(output["pooler_output"].shape)      # cls token
+print(output["patch_start_idx"])         # index of the first patch of each frame
+```
+
+## Citation
+
+```bibtex
+@article{yan2026omnistream,
+  title={OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams}, 
+  author={Yibin Yan and Jilan Xu and Shangzhe Di and Haoning Wu and Weidi Xie},
+  journal={arXiv preprint arXiv:2603.12265},
+  year={2026},
+  url={https://arxiv.org/abs/2603.12265}
+}
+```