๐Ÿฆ Twitter Post Details

Viewing enriched Twitter post

@sainingxie

Representation matters. Representation matters. Representation matters, even for generative models. We might've been training our diffusion models the wrong way this whole time. Meet REPA: Training Diffusion Transformers is easier than you think! https://t.co/lyWwiTYjEt(๐Ÿงต1/n)

Media 1

๐Ÿ“Š Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1845510163152687242/media_0.jpg",
      "type": "photo",
      "original_url": "https://pbs.twimg.com/media/GZyAxoCXMAUgjXM.jpg",
      "download_date": "2025-08-13T05:51:22.095807",
      "stored_in_supabase": true,
      "format_converted_from_list": true
    }
  ],
  "conversion_date": "2025-08-13T00:32:24.827944",
  "format_converted": true,
  "original_structure": "had_media_only"
}

๐Ÿ”ง Raw API Response

{
  "user": {
    "created_at": "2020-07-14T16:51:59.000Z",
    "default_profile_image": false,
    "description": "researcher in #deeplearning #computervision | assistant professor at @NYU_Courant @nyuniversity | previous: research scientist @metaai (FAIR) @UCSanDiego",
    "fast_followers_count": 0,
    "favourites_count": 4091,
    "followers_count": 17825,
    "friends_count": 1202,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 214,
    "location": "",
    "media_count": 47,
    "name": "Saining Xie",
    "normal_followers_count": 17825,
    "possibly_sensitive": false,
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1464323007078285312/dR9-qSsT_normal.jpg",
    "screen_name": "sainingxie",
    "statuses_count": 407,
    "translator_type": "none",
    "url": "https://t.co/z7UjEiSqGu",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "1283081795890626560"
  },
  "id": "1845510163152687242",
  "conversation_id": "1845510163152687242",
  "full_text": "Representation matters. \nRepresentation matters. \nRepresentation matters, even for generative models.\n\nWe might've been training our diffusion models the wrong way this whole time. Meet REPA: Training Diffusion Transformers is easier than you think! https://t.co/lyWwiTYjEt(๐Ÿงต1/n)",
  "reply_count": 29,
  "retweet_count": 273,
  "favorite_count": 1820,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [
    {
      "url": "https://t.co/kzEakbK1SF",
      "expanded_url": "https://sihyun.me/REPA/",
      "display_url": "sihyun.me/REPA/"
    }
  ],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GZyAxoCXMAUgjXM.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/sainingxie/status/1845510163152687242",
  "created_at": "2024-10-13T17:01:25.000Z",
  "#sort_index": "1845510163152687242",
  "view_count": 363610,
  "quote_count": 29,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": false,
  "startUrl": "https://x.com/sainingxie/status/1845510163152687242"
}