🐦 Twitter Post Details

Viewing enriched Twitter post

@svlevine

We've updated the DDPO website with some new results for training diffusion models with RL! Our aesthetic bunny is now much more... aesthetic. Latest here: https://t.co/5Mui7Wb8pB Includes code, LoRA training for low memory, pretrained models, etc. Some highlights 👇 https://t.co/719kNbN32s

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1708608842454679995/media_0.jpg",
      "type": "video",
      "original_url": "https://pbs.twimg.com/ext_tw_video_thumb/1708607683736272896/pu/img/kU65-Qyuvv4Pbhr6.jpg",
      "download_date": "2025-08-13T06:03:15.220384",
      "stored_in_supabase": true
    }
  ],
  "conversion_date": "2025-08-13T00:42:22.342918",
  "format_converted": true,
  "original_structure": "had_media_only"
}

🔧 Raw API Response

{
  "user": {
    "created_at": "2018-04-29T03:32:53.000Z",
    "default_profile_image": false,
    "description": "Associate Professor at UC Berkeley",
    "fast_followers_count": 0,
    "favourites_count": 682,
    "followers_count": 68232,
    "friends_count": 121,
    "has_custom_timelines": false,
    "is_translator": false,
    "listed_count": 995,
    "location": "Berkeley, CA",
    "media_count": 802,
    "name": "Sergey Levine",
    "normal_followers_count": 68232,
    "possibly_sensitive": false,
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/990434811662680064/BKCbJypl_normal.jpg",
    "screen_name": "svlevine",
    "statuses_count": 1860,
    "translator_type": "none",
    "url": "https://t.co/NbWOUtDUEe",
    "verified": false,
    "withheld_in_countries": [],
    "id_str": "990433714948661250"
  },
  "id": "1708608842454679995",
  "conversation_id": "1708608842454679995",
  "full_text": "We've updated the DDPO website with some new results for training diffusion models with RL! Our aesthetic bunny is now much more... aesthetic.\n\nLatest here: https://t.co/5Mui7Wb8pB\nIncludes code, LoRA training for low memory, pretrained models, etc. Some highlights 👇 https://t.co/719kNbN32s",
  "reply_count": 4,
  "retweet_count": 55,
  "favorite_count": 268,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [
    {
      "url": "https://t.co/5Mui7Wb8pB",
      "expanded_url": "https://rl-diffusion.github.io/",
      "display_url": "rl-diffusion.github.io"
    }
  ],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/ext_tw_video_thumb/1708607683736272896/pu/img/kU65-Qyuvv4Pbhr6.jpg",
      "type": "video",
      "video_url": "https://video.twimg.com/ext_tw_video/1708607683736272896/pu/vid/avc1/764x720/CCa0JwEysF_ksR6a.mp4?tag=12"
    }
  ],
  "url": "https://twitter.com/svlevine/status/1708608842454679995",
  "created_at": "2023-10-01T22:24:27.000Z",
  "#sort_index": "1708608842454679995",
  "view_count": 60959,
  "quote_count": 1,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": false,
  "startUrl": "https://twitter.com/svlevine/status/1708608842454679995"
}