🐦 Twitter Post Details

Viewing enriched Twitter post

@__JohnNguyen__

Transfusion combines autoregressive with diffusion to train a single transformer, but what if we combine Flow with Flow? 🤔 🌊OneFlow🌊 the first non-autoregressive model to generate text and images concurrently using a single transformer—unifying Edit Flow (text) with Flow Matching (images). Performance boost while unlocking new capabilities: 🔥 Scales better than Transfusion (AR), 50% fewer FLOPS than Transfusion for similar performance ⚡ Mixed-modal training boosts both generation & understanding 😑 Mask diffusion: fixed-length + extra FLOPS for masked tokens. Transfusion: sequential generation ✅ OneFlow: variable-length via token deletion + concurrent mixed-modal generation with fewer FLOPS 🧵1/n

Media 1

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1975600785074311368/media_0.jpg?",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1975600785074311368/media_0.jpg?",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2025-10-12T13:39:04.121945",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "1975600785074311368",
  "url": "https://x.com/__JohnNguyen__/status/1975600785074311368",
  "twitterUrl": "https://twitter.com/__JohnNguyen__/status/1975600785074311368",
  "text": "Transfusion combines autoregressive with diffusion to train a single transformer, but what if we combine Flow with Flow? 🤔\n\n🌊OneFlow🌊 the first non-autoregressive model to generate text and images concurrently using a single transformer—unifying Edit Flow (text) with Flow Matching (images).\n\nPerformance boost while unlocking new capabilities:\n🔥 Scales better than Transfusion (AR),  50% fewer FLOPS than Transfusion for similar performance\n⚡ Mixed-modal training boosts both generation & understanding\n😑 Mask diffusion: fixed-length + extra FLOPS for masked tokens. Transfusion: sequential generation\n✅ OneFlow: variable-length via token deletion + concurrent mixed-modal generation with fewer FLOPS\n\n 🧵1/n",
  "source": "Twitter for iPhone",
  "retweetCount": 77,
  "replyCount": 7,
  "likeCount": 390,
  "quoteCount": 6,
  "viewCount": 44087,
  "createdAt": "Tue Oct 07 16:35:06 +0000 2025",
  "lang": "en",
  "bookmarkCount": 265,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "1975600785074311368",
  "displayTextRange": [
    0,
    273
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "__JohnNguyen__",
    "url": "https://x.com/__JohnNguyen__",
    "twitterUrl": "https://twitter.com/__JohnNguyen__",
    "id": "1537295545189793793",
    "name": "John Nguyen",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1537296756471263233/4K2NllTR_normal.jpg",
    "coverPicture": "",
    "description": "",
    "location": "New York, USA",
    "followers": 618,
    "following": 186,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Thu Jun 16 04:46:42 +0000 2022",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 738,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 46,
    "statusesCount": 206,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "1975600785074311368"
    ],
    "profile_bio": {
      "description": "Multimodal @ FAIR",
      "entities": {
        "description": {},
        "url": {
          "urls": [
            {
              "display_url": "johnlnguyen.com",
              "expanded_url": "https://johnlnguyen.com",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/82omgBH6vz"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/aTInWr6gtK",
        "expanded_url": "https://twitter.com/__JohnNguyen__/status/1975600785074311368/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "id_str": "1975594251812573184",
        "indices": [
          274,
          297
        ],
        "media_key": "16_1975594251812573184",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAgoAARtquIE/l5AACgACG2q+cmRWUMgAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAACCgABG2q4gT+XkAAKAAIbar5yZFZQyAAA",
            "media_key": "16_1975594251812573184"
          }
        },
        "media_url_https": "https://pbs.twimg.com/tweet_video_thumb/G2q4gT-XkAAgtaX.jpg",
        "original_info": {
          "focus_rects": [],
          "height": 1160,
          "width": 1600
        },
        "sizes": {
          "large": {
            "h": 1160,
            "w": 1600
          }
        },
        "type": "animated_gif",
        "url": "https://t.co/aTInWr6gtK",
        "video_info": {
          "aspect_ratio": [
            40,
            29
          ],
          "variants": [
            {
              "bitrate": 0,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/tweet_video/G2q4gT-XkAAgtaX.mp4"
            }
          ]
        }
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {},
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}