Popnow Video

---
name: "PopNow Video Generation"
slug: "popnow-video"
description: "Use the existing MIT-licensed PopNow video skill to quote and create AI videos from text or an image through the commercial PopNow API, confirm the quoted cost before generation, poll asynchronous jobs, and download the result."
github_stars: 0
verification: "listed"
source: "https://github.com/popnow-ai/popnow-skills"
author: "popnow-ai"
category: "Image & Creative Automation"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "popnow-ai/popnow-skills"
  github_stars: 0
---

# PopNow Video Generation

This catalog entry points to the existing [official PopNow video skill](https://github.com/popnow-ai/popnow-skills/tree/7116ca7a328943acfe799a0f87084abbc69992c6/skills/popnow-video). The upstream bundle contains a `SKILL.md`, a Python standard-library helper, and model-reference documentation. Use it when a user wants a short video from a written brief, wants to animate a photo, or needs a supported video extension or upscaling operation. It is not a local video-generation model: the helper calls the commercial PopNow API at `https://api.popnow.ai/api/v1`.

The skill and helper source are MIT-licensed. An authenticated PopNow account, an API key, an internet connection, and sufficient paid API balance are needed for generation. Finding and installing the skill does not purchase API usage. Model availability and prices can change; query the current model schema and quote the exact request rather than promising a fixed price or unsupported option.

## Installation

Install or set up from the source-backed instructions:

npx skills add popnow-ai/popnow-skills. Configure POPNOW_API_KEY in the agent environment. For the current API USD billing contract, use the popnow-media skill and the current API documentation at https://popnow.ai/docs/tasks.

- Source: https://github.com/popnow-ai/popnow-skills

## Workflow and boundaries

1. Ask for the intended subject, motion, duration and supplied image when relevant. Keep content suitable for a general audience.
2. Read the selected model's live fields. Use the text-to-video model for a text brief and its image-to-video variant for a supplied photo.
3. Quote the exact request with the upstream helper. Tell the user the quoted cost and wait for a clear confirmation before creating a paid job. Pass the confirmed maximum to `create --confirm-credits`; if the price increases, quote again and ask again.
4. Poll the asynchronous job and report its actual state. Download successful output promptly because signed result links expire. Do not describe a queued or failed task as a finished video.
5. Keep `POPNOW_API_KEY` in the user's environment. Never publish or echo a key, request that the user paste one into chat, or send it to a storage download host.

Commands, error handling and examples for this revision are maintained in the [upstream skill](https://github.com/popnow-ai/popnow-skills/blob/7116ca7a328943acfe799a0f87084abbc69992c6/skills/popnow-video/SKILL.md). Official product and API documentation: [PopNow](https://popnow.ai), [API docs](https://popnow.ai/docs). This submission is a catalog inclusion request, with `verification: listed`; it does not claim an ASE security review or endorsement.