chore: update docs for readme

.gitattributes

@@ -88,3 +88,4 @@ assets/video-understanding/videos/video-understanding-vqa-01.mp4 filter=lfs diff
 assets/video-understanding/videos/video-understanding-vqa-02.mp4 filter=lfs diff=lfs merge=lfs -text
 assets/video-understanding/videos/video-understanding-vqa-03.mp4 filter=lfs diff=lfs merge=lfs -text
 assets/video-understanding/videos/video-understanding-vqa-04.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/docs/changelog/demo-05-26.webp filter=lfs diff=lfs merge=lfs -text

assets/docs/changelog/2026-05-26.md

@@ -0,0 +1,18 @@
+# 2026-05-26
+
+### Updates
+
+- **Gradio demo support:** We have added a Gradio-based demo for running and testing the model through an interactive web interface.
+- **Multimodal inference tasks:** The Gradio interface now supports **Text-to-Video Generation**, **Video Edit**, **Video Understanding**, **Text-to-Image Generation**, **Image Edit**, and **Image Understanding** in a unified UI.
+- **Local deployment:** The Gradio app can be launched locally with the following command, making it easier to try the model without writing additional inference scripts.
+
+```bash
+python3 lance_gradio.py --server-name 0.0.0.0 --server-port 7860
+```
+
+
+<p align="center">
+    <img src="./demo-05-26.png" alt="Lance Gradio Demo" width="960">
+    <br>
+    Unified Multimodal Inference in the Gradio Interface
+</p>