← PicsartCONTENT HISTORY

Update to Picsart

Snapshot Nov 7, 2026 · 00:09 UTC · version 2.4.0

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save Picsart and check future changes in Following.

Up to 3 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Put the user's own characters, people or things into a video of theirs with Recast - each picture replaces one person or thing in the video, and the motion, the place and the sound stay as filmed - on a board that checks the video, offers each video model with its price and makes the video itself. A character swap for an AI influencer, a mascot or a product placed into real footage. Use when the user has a video and wants someone or something in it replaced by their character, a photo or a product (\"put my character in this clip\", \"replace the cup with my product\", \"swap me into this video\"). Not for a new video from a prompt or a picture (generate-media), cutting their footage (edit-footage), or an animated ad rebuilt with new photos and text (recreate-video).",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 161
    }
  ],
  "name": "recast",
  "skill_md_contents": "---\nname: recast\ndescription: Put the user's own characters, people or things into a video of theirs with Recast - each picture replaces one person or thing in the video, and the motion, the place and the sound stay as filmed - on a board that checks the video, offers each video model with its price and makes the video itself. A character swap for an AI influencer, a mascot or a product placed into real footage. Use when the user has a video and wants someone or something in it replaced by their character, a photo or a product (\"put my character in this clip\", \"replace the cup with my product\", \"swap me into this video\"). Not for a new video from a prompt or a picture (generate-media), cutting their footage (edit-footage), or an animated ad rebuilt with new photos and text (recreate-video).\nmetadata:\n  title: Recast\n  short-description: Put your character or product into your own video\n  argument-hint: '[your video, and who or what goes in]'\n  starter-prompt: Put my character into my video.\n---\n\n# Recast\n\nRead picsart-video-rules first. One job: one of the user's own videos, with people or things in it\nreplaced by the user's pictures. The Recast board checks the video, offers the video models with\nthe price, and makes the video itself. You bring it the video, the pictures and who is in the video,\nthen read what it made.\n\n| Stage | Gate | Skills |\n|---|---|---|\n| 1. The video and the pictures | ASK | — |\n| 2. Who is in the video | — | — |\n| 3. The board | ASK, SPEND | — |\n| 4. What it made | DELIVER | — |\n\n## 1. The video and the pictures\n\nEvery file goes in as a Picsart-hosted URL, as picsart-video-rules's Asset URLs says. A video or a\npicture a Picsart tool returned in this conversation is used as it is. Files on the user's disk go\nup with `picsart_upload_local_files` when you have a shell. Otherwise\nASK with `picsart_drive_upload_ask` for all of them in one panel, in the first turn.\n\nWhat goes in, at most 8 pictures, in the order the user named them:\n\n- **A character they name:** find it with `picsart_film_list_assets`, with no `projectFolderUid` for\n  a character made outside a film and with the film's for its cast. Pass its `portraitUrl` as `url`,\n  its `name`, and `character: true`: the sheet's views are one character.\n- **A photo or a product shot:** its URL, with a `name` when the user gave one.\n- **A new place they asked for** in a picture: that picture with `role: \"place\"`.\n\nThe board's own What goes in step adds pictures from the user's images, characters and props, or\nfrom their device, and its Place step adds a place from their images, so never hold the board for a\npicture: open it with what you have. A picture\nthat does not exist yet (a new character, a product shot) is a job of its own: offer make-character\nor generate-media in one sentence, and do it only on a yes.\n\nThe board checks the video's length, size and frame rate against each model and says which ones\ntake it, so read no limits here.\n\n## 2. Who is in the video\n\nRead the video's length with `picsart_media_probe`, then look at 4 to 6 moments spread over it with\n`picsart_media_video_stills` (`times`, `labels: true`). Both are free. Look at the sheet as\npicsart-video-rules's Asset URLs says.\n\nWrite `found` from what you saw: every person, the main one first, then the things that matter to\nthe action, at most 8. Each is a short lowercase label by how it looks, never by where it stands or\nby a name: \"the woman in the long dark coat\", \"the cup in her hand\". The board offers these labels\nas what each picture replaces. When the user said who or what a picture replaces, set its\n`replaces` to the label that matches.\n\n## 3. The board\n\nASK with `picsart_recast_setup`: `videoUrl`, `pictures`, `found`, and only what the user said:\n\n- `sound`: `generated` when they want new sound, `none` for silence; leave it out to keep the\n  video's own sound.\n- `notes`: their own words for the run that the board has no control for (\"keep her hat on, make\n  the cup red\"), and with them `notesSay`: whether those words say what the place should be, and\n  whether they say anything about the sound.\n\nOpening the board is free. It is the whole turn: add one line at most, and end the turn. On the\nboard the user picks what each picture replaces, the place, the model, the resolution, the versions\nand the sound, and sees the price above Generate. Their Generate at that price is this spend's\ngo-ahead: never quote it again in the chat, and never call `picsart_generate` for this video\nyourself. The board runs every job, and a second run charges twice.\n\n## 4. What it made\n\nThe board's answer is `recast_feedback`; read it before the sentence around it.\n\n- **`status: \"done\"`:** the board already shows the video before and after, with Download. Say in\n  one line that it is ready. Give each link in `results` only when the user asks for the file. When\n  `shortfall` is there, say plainly how many versions could not be made (`versions`), or how many\n  kept the model's own sound because the original could not be put back (`sound`).\n- **`status: \"failed\"`:** say in one line where it stopped, from `failedStep`: `words` is the check\n  of what they wrote, `copy` is preparing their video, `make` is making the new video, and `sound` is\n  putting the sound back. The board offers the other models.\n- **`recast_post`:** they pressed Post. Open `picsart_social_post_preview` with that `video` in\n  `media` (`[{ \"type\": \"video\", \"url\": <video> }]`), a caption you wrote for it, and as `platforms`\n  the ones the user named, else `[\"instagram\", \"tiktok\"]`: the preview lets them tick others.\n\nRun nothing again unless the user asks: Change and run again and Try another model are on the\nboard. Then offer one next step in a sentence (another version, another model, posting it), and do\nit only on a yes.\n"
}

SHA-256 of public snapshot: f890dbe38fcdbd25603dc26393672459aee1a6d97bcc99ae446ef68082bc8d71