Update demo (#4)

- update (1d91878e213e5e7ec537e47c64d970b5aabb9197)


Co-authored-by: jingjing <[email protected]>

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/long.mp4 filter=lfs diff=lfs merge=lfs -text
+examples/bear.mp4 filter=lfs diff=lfs merge=lfs -text
+examples/dog.mp4 filter=lfs diff=lfs merge=lfs -text
+examples/running.mp4 filter=lfs diff=lfs merge=lfs -text
+examples/cake.png filter=lfs diff=lfs merge=lfs -text
+examples/painting.png filter=lfs diff=lfs merge=lfs -text

app.py

@@ -7,9 +7,24 @@ import torch
 from threading import Thread
 from transformers import AutoModelForCausalLM, AutoProcessor, TextIteratorStreamer
 
-HEADER = """
-"""
 
+HEADER = ("""
+<div style="display: flex; justify-content: center; align-items: center; text-align: center;">
+  <a href="https://github.com/DAMO-NLP-SG/VideoLLaMA3" style="margin-right: 20px; text-decoration: none; display: flex; align-items: center;">
+    <img src="https://github.com/DAMO-NLP-SG/VideoLLaMA3/blob/main/assets/logo.png?raw=true" alt="VideoLLaMA 3 🔥🚀🔥" style="max-width: 120px; height: auto;">
+  </a>
+  <div>
+    <h1>VideoLLaMA 3: Frontier Multimodal Foundation Models for Video Understanding</h1>
+    <h5 style="margin: 0;">If this demo please you, please give us a star ⭐ on Github or 💖 on this space.</h5>
+  </div>
+</div>
+<div style="display: flex; justify-content: center; margin-top: 10px;">
+  <a href="https://github.com/DAMO-NLP-SG/VideoLLaMA3"><img src='https://img.shields.io/badge/Github-VideoLLaMA3-9C276A' style="margin-right: 5px;"></a>
+  <a href="https://arxiv.org/pdf/2501.13106"><img src="https://img.shields.io/badge/Arxiv-2501.13106-AD1C18" style="margin-right: 5px;"></a>
+  <a href="https://huggingface.co/collections/DAMO-NLP-SG/videollama3-678cdda9281a0e32fe79af15"><img src="https://img.shields.io/badge/🤗-Checkpoints-ED5A22.svg" style="margin-right: 5px;"></a>
+  <a href="https://github.com/DAMO-NLP-SG/VideoLLaMA3/stargazers"><img src="https://img.shields.io/github/stars/DAMO-NLP-SG/VideoLLaMA3.svg?style=social"></a>
+</div>
+""")
 
 device = "cuda"
 model = AutoModelForCausalLM.from_pretrained(

examples/bear.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aaf1d0a2d6c9d6a43615caf4f16baaf2c35e192efa1876a0e903be230eef4b6
+size 2606962

examples/dog.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81db607d8f49e73138e3e9167b7f439d108d66be80b57c30a2c990b91ccbd9e
+size 2656649

examples/long.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b709283d14fd8f1aa225877707c5ef54773654a9263727f36b86733d642d16a4
+size 44392567

examples/running.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c9a7c0ee384aebd18e2e40928fb27895c3f61941f7b8330ebe78f061988309
+size 4295126