{
  "id": 18121749,
  "title": "7 Patterns From 204 Muse Video Prompts Shared on X, Plus a Node.js Script to Run Them",
  "url": "https://urgent.news/2026/11/04/7-patterns-from-204-muse-video-prompts-shared-on-x-plus-a-node-js",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-11-04T13:03:53.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/super_lewis/7-patterns-from-204-muse-video-prompts-shared-on-x-plus-a-nodejs-script-to-run-them-3imn"
  },
  "original_language": "en",
  "account": "In recent weeks, Muse Video clips featuring handheld selfies and POV shorts have dominated my X feed. The creative prompts behind these videos were scattered across numerous posts, often truncated or shared in replies. To make sense of this trend, I compiled a collection of 204 Muse Video prompts shared on X, each credited to its creator and linked to the original post. These prompts were divided into 13 categories, ranging from boyfriend POV shots to dance sequences and fashion portraits.\n\nThe collection, hosted on GitHub Pages and hosted by my own platform, apimodels.app, reveals several common patterns among the most successful prompts. First, creators often lock their subjects into a single reference sheet, using a headshot and outfit sheet as visual guides for each shot. This ensures consistency in the character's appearance throughout the video.\n\nNext, many prompts break down the scene into time-stamped steps, detailing the character's movements and camera cuts at specific intervals. This approach prevents stiff, unchanging loops by giving the video a sense of progression and rhythm. For POV prompts, the camera is treated as a person, with the creator appearing only as a hand or forearm, creating an immersive experience for the viewer.\n\nRepetition is also a key pattern, particularly in long-form English prompts that establish a fixed character and costume before diving into the creative process. Additionally, creators often incorporate elements that highlight the limitations of phone cameras, such as handheld shake and noise reduction, to add authenticity to the final product.\n\nSplitting longer prompts into shorter clips also proved effective, allowing creators to maintain character consistency while staying within the API's character limits. Lastly, some prompts are designed specifically for Meta's Muse app, relying on the app's built-in prompt generation capabilities rather than an external API. This highlights the importance of understanding the strengths and limitations of different tools when creating Muse Video content.",
  "summary": "Over the past few weeks my X feed filled up with Muse Video clips: handheld selfies, vlogs and \"boyfriend POV\" shorts that look like they were filmed on a phone. The prompts behind them were scattered across hundreds of posts, many cut off behind \"Show more\", split across replies, or quietly swapped for a translation. So I collected them. muse-video-prompts is an open-source library of 204 Muse…",
  "key_points": [
    "Muse Video prompts compiled from 204 X posts, categorized into 13 types",
    "Consistent character appearance achieved through reference sheet usage",
    "Time-stamped scene breakdown prevents stiff loops and adds rhythm"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}