Link the Space to its upstream model(s) and tag it

Adds `models:` and `tags:` to the README frontmatter, generated from the
spec in _shared/ rather than hand-written. `models:` is only set where the
weights are actually published on the Hub.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LJJXU9zyoDSBjApcUpteDt

README.md

@@ -7,6 +7,15 @@ sdk: docker
 pinned: false
 license: mit
 short_description: Drive a portrait from an audio track — lip sync and head...
+tags:
+  - image-to-video
+  - wavespeed
+  - infinitetalk
+  - lip-sync
+  - talking-head
+  - audio-driven
+models:
+  - MeiGen-AI/InfiniteTalk
 ---
 
 # InfiniteTalk
@@ -16,6 +25,9 @@ Drive a portrait from an audio track — lip sync and head motion.
 Runs [`wavespeed-ai/infinitetalk`](https://wavespeed.ai/models/wavespeed-ai/infinitetalk) through the
 [WaveSpeed](https://wavespeed.ai) v3 API.
 
+Upstream weights: [`MeiGen-AI/InfiniteTalk`](https://huggingface.co/MeiGen-AI/InfiniteTalk).
+
+
 ## Bring your own API key
 
 This Space does not ship an API key. Paste your own in the field at the top —