Update README.md

README.md

@@ -1,14 +1,39 @@
 ---
 license: mit
 tags:
-- diffusion
-- geolocalization
 - model_hub_mixin
 - plonk
+- geolocalization
+- diffusion
 - pytorch_model_hub_mixin
+- yfcc
+- flow
 ---
 
-This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+This is a model of the approach described in the paper ["Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation"](https://arxiv.org/abs/2412.06781)
+
+```
+@misc{dufour2024world80timestepsgenerative,
+      title={Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation}, 
+      author={Nicolas Dufour and David Picard and Vicky Kalogeiton and Loic Landrieu},
+      year={2024},
+      eprint={2412.06781},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2412.06781}, 
+}
+```
 - Code: https://github.com/nicolas-dufour/plonk
-- Paper: [More Information Needed]
-- Docs: [More Information Needed]
+- Docs:
+The model can be simply run by doing:
+```bash
+pip install diff-plonk
+```
+
+```python
+from plonk import PLONKPipeline
+
+pipeline = PLONKPipeline.from_pretrained("nicolas-dufour/PLONK_YFCC_flow")
+
+gps_coords = pipeline(images, batch_size=1024)
+```