Add pipeline tag and improve model card metadata

Hi! I'm Niels from the Hugging Face community team.

This PR adds the `text-to-video` pipeline tag to the model card's metadata. This helps users discover the model when filtering by task on the Hugging Face Hub. I have also kept your original detailed documentation, including the quick start guide and inference examples, as they are very helpful for the community.

README.md

@@ -1,3 +1,7 @@
+---
+pipeline_tag: text-to-video
+---
+
 <div align="center">
 
 # Echo-Infinity
@@ -171,4 +175,4 @@ This codebase builds on the open-source implementations of:
   journal={arXiv preprint arXiv:2606.04527},
   year={2026}
 }
-```
+```