Viewing enriched Twitter post
🚀 HART by @MIT : Hybrid Autoregressive Transformer! It directly generates stunning 1024x1024 images with blazing efficiency, this hybrid approach outshines diffusion models in quality & speed. Also uses Qwen2-VL-1.5B-Instruct 🔥 The image generation speed is super fast, try out the demo! https://t.co/d3hJBs7vGa #AI #ML #CV
{
"score": 0.86,
"scored_at": "2025-08-09T13:46:07.549298",
"import_source": "network_archive_import",
"links_checked": true,
"checked_at": "2025-08-10T10:32:41.828816",
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1854377125974876555/media_0.jpg?",
"filename": "media_0.jpg"
},
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/GbwQR_5WwAAkAI2.jpg",
"media_url_https": null,
"display_url": null,
"expanded_url": null
}
],
"reprocessed_at": "2025-08-12T15:25:11.484537",
"reprocessed_reason": "missing_media_array",
"original_structure": "had_both"
}{
"user": {
"created_at": "2015-05-24T10:18:08.000Z",
"default_profile_image": false,
"description": "mle fellow @huggingface 🤗 - @uwaterloo 🇨🇦 - follow me for more models!",
"fast_followers_count": 0,
"favourites_count": 2253,
"followers_count": 2214,
"friends_count": 116,
"has_custom_timelines": false,
"is_translator": false,
"listed_count": 5,
"location": "SF/Waterloo",
"media_count": 32,
"name": "Jade Choghari",
"normal_followers_count": 2214,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/3225119671/1721639541",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1819969966306639872/bXC0euBo_normal.jpg",
"screen_name": "jadechoghari",
"statuses_count": 205,
"translator_type": "none",
"verified": true,
"withheld_in_countries": [],
"id_str": "3225119671"
},
"id": "1854377125974876555",
"conversation_id": "1854377125974876555",
"full_text": "🚀 HART by @MIT : Hybrid Autoregressive Transformer!\nIt directly generates stunning 1024x1024 images with blazing efficiency, this hybrid approach outshines diffusion models in quality & speed. Also uses Qwen2-VL-1.5B-Instruct 🔥\n\nThe image generation speed is super fast, try out the demo! https://t.co/d3hJBs7vGa\n\n#AI #ML #CV",
"reply_count": 5,
"retweet_count": 39,
"favorite_count": 146,
"hashtags": [],
"symbols": [],
"user_mentions": [
{
"id_str": "15460048",
"name": "Massachusetts Institute of Technology (MIT)",
"screen_name": "MIT",
"profile": "https://twitter.com/MIT"
}
],
"urls": [],
"media": [
{
"media_url": "https://pbs.twimg.com/media/GbwQR_5WwAAkAI2.jpg",
"type": "photo"
}
],
"url": "https://twitter.com/jadechoghari/status/1854377125974876555",
"created_at": "2024-11-07T04:15:34.000Z",
"#sort_index": "1854377125974876555",
"view_count": 20559,
"quote_count": 1,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": true,
"startUrl": "https://x.com/jadechoghari/status/1854377125974876555"
}