Add library_name and remove redundant tags

This PR adds the `library_name` to the model card metadata.
The provided code examples and file structure indicate that the model utilizes the `diffusers` library.
Adding this improves discoverability and clarity for users.
Additionally, the "text-to-image" and "image-to-video" tags are redundant given the `pipeline_tag: text-to-video`.

README.md

@@ -1,9 +1,8 @@
 ---
 license: apache-2.0
 pipeline_tag: text-to-video
+library_name: diffusers
 tags:
-- text-to-image
-- image-to-video
 - flux
 ---