Viewing enriched Twitter post
Impressive. GigaGAN is a 1B-parameter GAN that can scale 36 times larger than StyleGAN. The model from Adobe/CMU proves that proves that GANs can be scaled to large datasets AND remain stable. Features: ▸ Latent Space Editing: supports latent interpolation, style mixing, and vector arithmetic operations. ▸ Speed: It can produce 512px images in 0.13 seconds and 4K images in 3.66 seconds. ▸ Upsampling: it can be used as upsampler for ultra-high-resolution images.
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1693319173336608927/media_0.jpg",
"type": "video",
"original_url": "https://pbs.twimg.com/ext_tw_video_thumb/1693314358309163008/pu/img/b1JVgGYAsUh80cH9.jpg",
"download_date": "2025-08-13T06:01:59.802615",
"stored_in_supabase": true
}
],
"conversion_date": "2025-08-13T00:40:05.554910",
"format_converted": true,
"original_structure": "had_media_only"
}{
"user": {
"created_at": "2012-11-07T07:19:36.000Z",
"default_profile_image": false,
"description": "Covering the latest breakthroughs in AI. ML Engineer/Researcher now building AlphaSignal → A technical newsletter read by 120,000+ AI developers.",
"fast_followers_count": 0,
"favourites_count": 4230,
"followers_count": 64949,
"friends_count": 702,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 1408,
"location": "Join 120,000+ readers →",
"media_count": 359,
"name": "Lior⚡",
"normal_followers_count": 64949,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/931470139/1681303371",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1599792074336964608/CobSHV8l_normal.jpg",
"screen_name": "AlphaSignalAI",
"statuses_count": 2400,
"translator_type": "none",
"url": "https://t.co/AyubevadmD",
"verified": false,
"withheld_in_countries": [],
"id_str": "931470139"
},
"id": "1693319173336608927",
"conversation_id": "1693319173336608927",
"full_text": "Impressive. GigaGAN is a 1B-parameter GAN that can scale 36 times larger than StyleGAN. \n\nThe model from Adobe/CMU proves that proves that GANs can be scaled to large datasets AND remain stable.\n\nFeatures:\n▸ Latent Space Editing: supports latent interpolation, style mixing, and vector arithmetic operations.\n\n▸ Speed: It can produce 512px images in 0.13 seconds and 4K images in 3.66 seconds.\n\n▸ Upsampling: it can be used as upsampler for ultra-high-resolution images.",
"reply_count": 33,
"retweet_count": 227,
"favorite_count": 1236,
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [],
"media": [
{
"media_url": "https://pbs.twimg.com/ext_tw_video_thumb/1693314358309163008/pu/img/b1JVgGYAsUh80cH9.jpg",
"type": "video",
"video_url": "https://video.twimg.com/ext_tw_video/1693314358309163008/pu/vid/640x640/HPUeZ8JbtFEBTcpQ.mp4?tag=12"
}
],
"url": "https://twitter.com/AlphaSignalAI/status/1693319173336608927",
"created_at": "2023-08-20T17:48:45.000Z",
"#sort_index": "1693319173336608927",
"view_count": 217209,
"quote_count": 15,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": true,
"startUrl": "https://twitter.com/alphasignalai/status/1693319173336608927"
}