StoryDiffusion: Long-range image and video generation

{
  "by": "doodlesdev",
  "descendants": 65,
  "id": 40218021,
  "kids": [
    40218669,
    40218440,
    40218566,
    40220916,
    40218883,
    40221247,
    40218417,
    40218539,
    40222699,
    40218829,
    40219857,
    40218574,
    40243792,
    40218952,
    40243985,
    40223735,
    40221510,
    40228368,
    40218861,
    40226881,
    40218467,
    40218781
  ],
  "score": 233,
  "time": 1714522028,
  "title": "StoryDiffusion: Long-range image and video generation",
  "type": "story",
  "url": "https://storydiffusion.github.io/"
}

{
  "author": "Yupeng Zhou1* Daquan Zhou2‡† Mingming Cheng1 Jiashi Feng2 Qibin Hou1‡†",
  "date": null,
  "description": "StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation",
  "image": "https://storydiffusion.github.io/MagicStory_files/comics/1.jpg",
  "logo": null,
  "publisher": null,
  "title": "StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation",
  "url": "https://storydiffusion.github.io/"
}

{
  "url": "https://storydiffusion.github.io/",
  "title": "StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation",
  "description": "Demo Video       StoryDiffusion can create Magic Story, achieving Long-Range Image and Video Generation!           Comics Generation      StoryDiffusion creates comics in various styles through the...",
  "links": [
    "https://storydiffusion.github.io/"
  ],
  "image": "",
  "content": "<div>\n  <p>Demo Video</p>\n  <p>\n    </p><h3> StoryDiffusion can create Magic Story, achieving Long-Range Image and Video Generation!</h3>\n <p></p>\n  <video width=\"100%\" controls>\n    <source src=\"https://storydiffusion.github.io/MagicStory_files/demo.mp4\" type=\"video/mp4\"></source>\n  </video>\n</div><div>\n  <p>Comics Generation</p>\n  <p>\n   </p><h3> StoryDiffusion creates comics in various styles through the proposed consistent self-attention, maintaining consistent character styles and attires for cohesive storytelling. </h3>\n<p></p>\n  <p><img src=\"https://storydiffusion.github.io/MagicStory_files/comics/1.jpg\" /> <br />\n</p></div><div>\n  <p>Cartoon characters generation</p>\n  <p>\n   </p><h3> StoryDiffusion can create amazing consistent cartoon-style characters.</h3>\n<p></p>\n  <p><img src=\"https://storydiffusion.github.io/MagicStory_files/cartoon1.jpg\" /> <br />\n</p></div><div>\n  <p>Multiple Characters Generation</p>\n  <p>\n   </p><h3> StoryDiffusion can maintain the identity of multiple characters at the same time and generate consistent characters in a sequence of images.</h3>\n<p></p>\n  <p><img src=\"https://storydiffusion.github.io/MagicStory_files/MultipleID.jpg\" /> <br />\n</p></div><div>\n  <p>More Comic Generation Example</p>\n  <p>\n    </p><h3> StoryDiffusion can create impressive comics. We will add more comics and put on here.</h3>\n <p></p>  \n <p><img src=\"https://storydiffusion.github.io/MagicStory_files/comic2.jpg\" /> </p> \n <div>  \n  <h3> \"Girl and Squirrel\"</h3>\n  <p><img src=\"https://storydiffusion.github.io/MagicStory_files/comic3.jpg\" /> </p></div> \n</div><div>\n  <p>Methods</p>\n  <p>The structure of the Consistent Self-Attention.</p>\n  <p><img src=\"https://storydiffusion.github.io/MagicStory_files/structure0.jpg\" /></p><p>The structure of the Motion Predictor.</p>\n  <p><img src=\"https://storydiffusion.github.io/MagicStory_files/structure1.jpg\" /> <br />\n</p></div>",
  "author": "",
  "favicon": "https://storydiffusion.github.io/.png",
  "source": "storydiffusion.github.io",
  "published": "",
  "ttr": 21,
  "type": ""
}