LaunchKit · 2026
Back to Skills

aiml-image-video

Generate images or videos via AIMLAPI from prompts.

0
1.0k downloads
by @aimlapihello

Setup & Installation

openclaw skills install @aimlapihello/aiml-image-video

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install aiml-image-video

Version History

v1.0.2Feb 26, 2026 - Version note by skill developer:

- No file or documentation changes detected in this version. - Functionality and instructions remain unchanged from the previous release.

What This Skill Does

Generates images and videos from text prompts using the AIMLAPI platform. Scripts handle retries, async video polling, and required User-Agent headers without manual setup.

Handles AIMLAPI's async video polling and retry logic automatically, removing boilerplate that would otherwise need to be written for every project.

When to use it

  • Generating product mockup images from text descriptions
  • Creating short video clips from scene prompts
  • Batch-generating image variations with custom sizes
  • Automating media generation in agent pipelines
  • Prototyping visual assets from written briefs

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: generate a time-lapse video of clouds over a mountain range

AGENT
  1. 1Run gen_video.py with the prompt and model flag
  2. 2POST to /v2/video/generations to create the async task
  3. 3Poll /v2/video/generations with the returned generation_id until status is completed
  4. 4Download the video from the returned URL to the output directory
OUTPUT

Video file saved to ./out/videos/

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

AIMLAPI account and API key (set as AIMLAPI_API_KEY environment variable)