Add pipeline tag

This PR adds the `pipeline_tag` to the model card, which helps improve discoverability on the Hugging Face Hub by ensuring the model appears under the "image-to-image" filter: https://huggingface.co/models?pipeline_tag=image-to-image.

README.md

@@ -1,9 +1,10 @@
 ---
-license: bsd-3-clause
 language:
 - en
+license: bsd-3-clause
 tags:
 - arxiv:2506.23151
+pipeline_tag: image-to-image
 ---
 
 # MEMFOF-Tartan-T
@@ -32,4 +33,4 @@ model = MEMFOF.from_pretrained("egorchistov/MEMFOF-Tartan-T").eval().to(device)
 with torch.inference_mode():
     example_input = torch.randint(0, 256, [1, 3, 3, 1080, 1920], device=device)  # [B=1, T=3, C=3, H=1080, W=1920]
     backward_flow, forward_flow = model(example_input).unbind(dim=1)  # [B=1, C=2, H=1080, W=1920]
-```
+```