Viewing enriched Twitter post
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation abs: https://t.co/MXOldpo8uk website: https://t.co/7LaOqBANZY This paper from Google & CMU introduces MAGVIT-v2, a joint image-video tokenizer which can be used with a masked language model to perform image and video generation. Obtains SOTA on class-conditional ImageNet 512x512 generation and Kinetics600 frame prediction. Also demonstrates use of MAGVIT-v2 for video compression.
{
"data": [
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/F8DxI6PbYAAqzGI.jpg",
"media_url_https": null,
"display_url": null,
"expanded_url": null
},
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/F8DxMHKbkAAxIqX.jpg",
"media_url_https": null,
"display_url": null,
"expanded_url": null
}
],
"score": 0.89,
"scored_at": "2025-08-09T13:46:07.549680",
"import_source": "manual_curation_2023",
"links_checked": true,
"checked_at": "2025-08-10T10:31:50.608729",
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1711633145332920785/media_0.jpg?",
"filename": "media_0.jpg",
"original_url": "https://pbs.twimg.com/media/F8DxI6PbYAAqzGI.jpg"
},
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1711633145332920785/media_1.jpg?",
"filename": "media_1.jpg",
"original_url": "https://pbs.twimg.com/media/F8DxMHKbkAAxIqX.jpg"
}
],
"storage_migrated": true
}{
"user": {
"created_at": "2011-12-20T03:45:50.000Z",
"default_profile_image": false,
"description": "PhD at 19 |\nFounder and CEO at @MedARC_AI |\nResearch Director at @StabilityAI | \n@kaggle Notebooks GM |\nBiomed. engineer @ 14 |\nTEDx talk➡https://t.co/DwMkst4bnG",
"fast_followers_count": 0,
"favourites_count": 60004,
"followers_count": 45439,
"friends_count": 995,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 703,
"location": "",
"media_count": 1203,
"name": "Tanishq Mathew Abraham, PhD",
"normal_followers_count": 45439,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/441465751/1675968078",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1553508977735962624/nnlSwBmu_normal.jpg",
"screen_name": "iScienceLuvr",
"statuses_count": 12087,
"translator_type": "none",
"url": "https://t.co/nNzCz2VVd1",
"verified": false,
"withheld_in_countries": [],
"id_str": "441465751"
},
"id": "1711633145332920785",
"conversation_id": "1711633145332920785",
"full_text": "Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation\n\nabs: https://t.co/MXOldpo8uk\nwebsite: https://t.co/7LaOqBANZY\n\nThis paper from Google & CMU introduces MAGVIT-v2, a joint image-video tokenizer which can be used with a masked language model to perform image and video generation. Obtains SOTA on class-conditional ImageNet 512x512 generation and Kinetics600 frame prediction. Also demonstrates use of MAGVIT-v2 for video compression.",
"reply_count": 7,
"retweet_count": 79,
"favorite_count": 399,
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [
{
"url": "https://t.co/DKWS0MdqwS",
"expanded_url": "https://arxiv.org/abs/2310.05737",
"display_url": "arxiv.org/abs/2310.05737"
},
{
"url": "https://t.co/TcWPD0pWMF",
"expanded_url": "https://magvit.cs.cmu.edu/v2/",
"display_url": "magvit.cs.cmu.edu/v2/"
}
],
"media": [
{
"media_url": "https://pbs.twimg.com/media/F8DxI6PbYAAqzGI.jpg",
"type": "photo"
},
{
"media_url": "https://pbs.twimg.com/media/F8DxMHKbkAAxIqX.jpg",
"type": "photo"
}
],
"url": "https://twitter.com/iScienceLuvr/status/1711633145332920785",
"created_at": "2023-10-10T06:41:57.000Z",
"#sort_index": "1711633145332920785",
"view_count": 77427,
"quote_count": 6,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": true,
"startUrl": "https://twitter.com/iscienceluvr/status/1711633145332920785"
}