A cloud-powered skill that transforms static images into fully edited AI videos with transitions and background music in under 60 seconds.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-to-ai
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install image-to-ai using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Image to AI?
Image to AI is a powerful automation tool designed to bypass the steep learning curve of professional video editing software. By leveraging high-performance cloud GPU nodes, this skill allows users to simply describe their vision to turn photos into dynamic video content. Whether you are a marketer or a creator, you can generate 1080p MP4 files complete with cinematic transitions and audio tracks without needing local rendering power.
Built as part of the Openclaw Skills ecosystem, it handles everything from file uploads to complex timeline compositing. The skill supports a wide range of formats including JPG, PNG, WEBP, and HEIC, ensuring that high-resolution inputs translate into sharp, professional-grade video frames automatically.
Image to AI Use Cases
- Creating product showcase videos from static JPG or PNG photos for e-commerce.
- Generating social media advertisements with text overlays and background music.
- Converting high-resolution photography into animated slideshows or narrated videos.
- Rapidly prototyping video concepts through iterative, text-based editing commands.
- Batch processing multiple image sets into distinct video projects within a single session.
How Image to AI Works
- The user uploads image files (up to 200MB) and provides a descriptive prompt for the desired video output.
- The skill initiates a session with the remote API and establishes a secure connection using a NEMO_TOKEN.
- User instructions are processed via a Server-Sent Events (SSE) stream which translates natural language into timeline edits.
- Cloud GPU nodes composite the video layers, applying transitions, text overlays, and audio as specified.
- An export job is queued to compress the project into a standard format like H.264 MP4 at 1080p resolution.
- The skill polls the rendering status and provides a direct download URL once the video is ready.
Image to AI Setup
To get started with Image to AI, ensure your environment is configured. The skill can automatically generate a trial token if one is not provided.
# Set your API token as an environment variable
export NEMO_TOKEN="your_token_here"
# The skill will automatically manage session state in:
# ~/.config/nemovideo/
If no token is found, the skill will POST to the anonymous-token endpoint using a unique Client-Id to grant you 100 initial credits.
Image to AI Data Schema & Taxonomy
The skill manages a structured draft system using a condensed JSON taxonomy to ensure low-latency communication during the editing process.
| Key | Definition | Details |
|---|---|---|
t |
Tracks | Contains the layers of the project (Video, Audio, Text). |
tt |
Track Type | 0 = Video, 1 = Audio, 7 = Text overlays. |
sg |
Segments | Specific clips or assets within a track. |
d |
Duration | Length of segments measured in milliseconds (ms). |
m |
Metadata | Technical info like resolution and frame rates. |
Image to AI Advanced Features
- Multi-track timeline management for simultaneous control of video, BGM, and titles.
- Automatic session persistence allowing for iterative refinements without re-uploading assets.
- Smart intent classification that routes natural language commands (e.g., "show credits" or "export") to specific API actions.
- Real-time SSE stream monitoring with automated heartbeat checks for long-running GPU render tasks.
- Support for professional export formats including MP4, MOV, and WEBM with high-resolution frame output.
SKILL.md
Loading
Related Openclaw Skills
AMG PostgreSQL Flexible Server Health Check
A sophisticated diagnostic skill for executing fleet-wide health audits and deep-dive telemetry analysis of Azure PostgreSQL Flexible Servers.
A-Stock Holding Monitor
A specialized monitoring script designed to track A-share stock positions with automated alerts for price targets, support levels, and abnormal volatility.
Jupyter Helper
A powerful utility for managing, converting, and debugging Jupyter notebooks through an AI-enhanced interface.
AI Image to Video — Animate Images into Video Clips
A high-performance AI skill for turning product photos and still images into smooth 1080p animated video clips via cloud-based GPU rendering.
Python Cookbook
A comprehensive library of Python code patterns and utility commands for file I/O, async functions, linting, and debugging.
Supabase Tool
A specialized utility for generating Supabase API curl commands and SQL helpers to query, audit, and manage databases efficiently.
Featured*
