Skip to content

Commit

Permalink
add videopoet
Browse files Browse the repository at this point in the history
  • Loading branch information
Lijun-Yu committed Jan 4, 2024
1 parent c86037e commit 92e627e
Show file tree
Hide file tree
Showing 2 changed files with 52 additions and 37 deletions.
Binary file added v2/images/videopoet.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
89 changes: 52 additions & 37 deletions v2/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -55,20 +55,53 @@ <h1><i>Language Model Beats Diffusion</i>:<br>Tokenizer is key to visual generat
</div>

<div class="header_dark_gray">
<h1>Image Tokenization</h1>
<h1>Video Generation</h1>
</div>


<div id="slideshow1" class="slideshow-container">
<div id="slideshow4" class="slideshow-container">
<div class="mySlides">
<img src="./images/reconstruction.png" class="center">
<div class="imagetext">Comparison with prior works.</div>
<img src="./images/videopoet.gif" class="center">
<div class="imagetext">MAGVIT-v2 tokenizer is the core technique that enables<i>VideoPoet: A large language model for zero-shot video generation</i>. <a href="https://sites.research.google/videopoet/">More</a>.</div>
</div>
<a class="prev" onclick="plusSlides(-1, slideshow1)">&#10094;</a>
<a class="next" onclick="plusSlides(1, slideshow1)">&#10095;</a>
<a class="prev" onclick="plusSlides(-1, slideshow4)">&#10094;</a>
<a class="next" onclick="plusSlides(1, slideshow4)">&#10095;</a>

<div style="text-align:center">
<span class="dot" onclick="currentSlide(1, slideshow1)"></span>
<span class="dot" onclick="currentSlide(1, slideshow4)"></span>
</div>
</div>
<br>
<br>

<div class="header_dark_gray">
<h1>Video Compression</h1>
</div>

<div id="slideshow3" class="slideshow-container">
<div class="mySlides">
<center>
<video class="center" style="width: 95%" controls="" loop="" autoplay="" muted="" playsinline="">
<source src="./images/picked_resized_3in1_text.mp4" type="video/mp4">
<img src="./images/picked_resized_3in1_text.gif" class="img-responsive img-centered" alt="img">
</video>
</center>
<div class="imagetext">Comparison with prior best model and standard video codec.</div>
</div>
<div class="mySlides">
<img src="./images/elo.png" class="center" style="width: 40%;">
<div class="imagetext">Human rater study results.</div>
</div>
<div class="mySlides">
<img src="./images/picked_resized_3in1_text.gif" class="center" style="width: 95%">
<div class="imagetext">Comparison with prior best model and standard video codec (GIF format for easier sharing, which takes longer to load).</div>
</div>
<a class="prev" onclick="plusSlides(-1, slideshow3)">&#10094;</a>
<a class="next" onclick="plusSlides(1, slideshow3)">&#10095;</a>

<div style="text-align:center">
<span class="dot" onclick="currentSlide(1, slideshow3)"></span>
<span class="dot" onclick="currentSlide(2, slideshow3)"></span>
<span class="dot" onclick="currentSlide(3, slideshow3)"></span>
</div>
</div>
<br>
Expand Down Expand Up @@ -121,54 +154,36 @@ <h1>Image Generation<br>
<br>

<div class="header_dark_gray">
<h1>Video Compression</h1>
<h1>Image Tokenization</h1>
</div>

<div id="slideshow3" class="slideshow-container">
<div class="mySlides">
<center>
<video class="center" style="width: 95%" controls="" loop="" autoplay="" muted="" playsinline="">
<source src="./images/picked_resized_3in1_text.mp4" type="video/mp4">
<img src="./images/picked_resized_3in1_text.gif" class="img-responsive img-centered" alt="img">
</video>
</center>
<div class="imagetext">Comparison with prior best model and standard video codec.</div>
</div>
<div class="mySlides">
<img src="./images/elo.png" class="center" style="width: 40%;">
<div class="imagetext">Human rater study results.</div>
</div>

<div id="slideshow1" class="slideshow-container">
<div class="mySlides">
<img src="./images/picked_resized_3in1_text.gif" class="center" style="width: 95%">
<div class="imagetext">Comparison with prior best model and standard video codec (GIF format for easier sharing, which takes longer to load).</div>
<img src="./images/reconstruction.png" class="center">
<div class="imagetext">Comparison with prior works.</div>
</div>
<a class="prev" onclick="plusSlides(-1, slideshow3)">&#10094;</a>
<a class="next" onclick="plusSlides(1, slideshow3)">&#10095;</a>
<a class="prev" onclick="plusSlides(-1, slideshow1)">&#10094;</a>
<a class="next" onclick="plusSlides(1, slideshow1)">&#10095;</a>

<div style="text-align:center">
<span class="dot" onclick="currentSlide(1, slideshow3)"></span>
<span class="dot" onclick="currentSlide(2, slideshow3)"></span>
<span class="dot" onclick="currentSlide(3, slideshow3)"></span>
<span class="dot" onclick="currentSlide(1, slideshow1)"></span>
</div>
</div>
<br>
<br>

<div class="header_dark_gray">
<h1>Video Generation (updating)<br>
<!-- <a href="https://paperswithcode.com/sota/video-prediction-on-kinetics-600-12-frames?p=language-model-beats-diffusion-tokenizer-is"><img src="https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/language-model-beats-diffusion-tokenizer-is/video-prediction-on-kinetics-600-12-frames"></a>
<a href="https://paperswithcode.com/sota/video-generation-on-ucf-101?p=language-model-beats-diffusion-tokenizer-is"><img src="https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/language-model-beats-diffusion-tokenizer-is/video-generation-on-ucf-101"></a></h1> -->
</div>


<!-- <div id="slideshow4" class="slideshow-container">
</div>
<br>
<br> -->

<!-- anon-on -->
<div class="header_dark_gray">
<!-- <div class="header_dark_gray">
<h1>While we're still updating this new version, also check out: <a href="https://magvit.cs.cmu.edu">MAGVIT(v1)</a></h1></p>
</div>
</div> -->
<!-- <div class="header_dark_gray">
<h1>Acknowledgment</h1>
<p></p>
Expand Down

0 comments on commit 92e627e

Please sign in to comment.