Update README.md

README.md

@@ -14,7 +14,7 @@ license: mit
 
 ## Model description
 
-This model is a [Pix2Pix]() model trained on the [huggan/maps]() dataset. The goal for the model is to turn a satellite map into a geographic map à la Google Maps, and the other way around.
+This model is a [Pix2Pix](https://arxiv.org/abs/1611.07004) model trained on the [huggan/maps](https://huggingface.co/datasets/huggan/maps) dataset. The goal for the model is to turn a satellite map into a geographic map à la Google Maps, and the other way around.
 
 The model was trained using the [example script](https://github.com/huggingface/community-events/tree/main/huggan/pytorch/pix2pix) provided by HuggingFace as part of the [HugGAN sprint](https://github.com/huggingface/community-events/tree/main/huggan).
 
@@ -23,9 +23,18 @@ The model was trained using the [example script](https://github.com/huggingface/
 #### How to use
 
 ```python
-from huggan.pytorch.pix2pix import GeneratorUNet
+from huggan.pytorch.pix2pix.modeling_pix2pix import GeneratorUNet
+import requests
+from PIL import Image
+from torchvision.utils import save_image
+
+image = Image.open("...")
 
 generator = GeneratorUNet.from_pretrained("huggan/pix2pix-maps")
+
+pixel_values = transform(image).unsqueeze(0)
+output = generator(pixel_values)
+save_image(output, 'output.png', normalize=True)
 ```
 
 #### Limitations and bias