A comprehensive media generation skill for creating, upscaling, and animating high-fidelity images and videos via the Runware API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install runware
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 runware 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 Runware?
Runware is a powerful integration designed for Openclaw Skills that provides a unified gateway to the world's most advanced generative AI models. It allows developers and creators to interact with FLUX.1, Stable Diffusion XL, Kling AI, and Runway Gen-3 through a streamlined interface. Whether you need photorealistic images or cinematic video sequences, this skill handles the complexities of API communication and model selection.
By leveraging this tool within the Openclaw Skills ecosystem, users can automate creative workflows that previously required manual intervention across multiple platforms. It is optimized for speed and quality, offering access to both professional-grade models for final outputs and faster models for rapid iteration and prototyping.
Runware Use Cases
- Creating custom marketing assets and social media graphics using text-to-image prompts.
- Animating static images or brand logos into high-quality videos for advertisements.
- Enhancing and upscaling legacy image assets for modern high-resolution displays.
- Implementing style transfers on existing photos using image-to-image transformation.
- Batch generating diverse visual concepts for rapid product design and brainstorming.
How Runware Works
- The user provides a Runware API key to authenticate the Openclaw Skills session.
- A command is issued specifying the generation type, such as text-to-image or image-to-video, along with the desired prompt.
- The skill identifies the target model (defaulting to FLUX.1 Dev for images or Kling AI for videos) and sends the parameters to the Runware API.
- For image tasks, the generated file is received and saved to the designated output folder.
- For video tasks, the skill utilizes an asynchronous polling mechanism to monitor the generation progress until the final video file is ready for download.
Runware Setup
To get started with this skill, first obtain an API key from runware.ai. You can then configure your environment by setting the RUNWARE_API_KEY variable:
export RUNWARE_API_KEY="your_api_key_here"
Alternatively, you can provide the key directly when running generation scripts using the --api-key flag. Ensure you have the Python scripts image.py and video.py available in your local environment to execute commands through Openclaw Skills.
Runware Data Schema & Taxonomy
The skill manages inputs and outputs using a structured approach to ensure consistency across different models:
| Data Type | Attributes | Description |
|---|---|---|
| Images | --format, --width, --height |
Outputs in PNG, JPG, or WEBP; default 1024x1024 resolution. |
| Videos | --duration, --format |
Outputs in MP4, WEBM, or MOV; support for variable durations. |
| Models | model_id |
Uses unique identifiers like runware:101@1 for FLUX.1 Dev or klingai:5@3 for Kling AI. |
| Storage | -o, --output |
Files are saved locally to specified paths or current directory. |
Runware Advanced Features
- Support for LoRA model IDs to apply specific artistic styles or characters to image generations.
- Frame interpolation capabilities by providing both starting and ending images for smooth video transitions.
- Granular control over reproduction using seeds and CFG scales for precise creative direction.
- Integration with the Civitai model ecosystem, allowing access to thousands of community-tuned Stable Diffusion models.
- Built-in upscaling logic to increase image resolution by a specific factor while maintaining detail.
SKILL.md
Loading
Related Openclaw Skills
Token Risk Explainer Skill
An automated utility that translates technical Binance Web3 token audit data into plain-language risk assessments and social media drafts.
Meme Risk Radar Skill
A bilingual meme token risk analysis engine that transforms Binance Web3 discovery data into actionable, risk-scored insights.
Alpha Copilot Skill
A research automation tool that generates a daily top-5 crypto token leaderboard with risk summaries and ready-to-publish social media drafts.
Feishu Message Fallback
A resilient messaging skill that ensures Feishu delivery through automatic retries and format-to-plain-text fallback strategies.
Music Manager
A universal music downloader and manager that extracts audio from YouTube and Bilibili, converts it to MP3, and organizes it into local libraries.
Gaode Map (AMap) Integration
A Python-based skill for integrating Gaode Map (AMap) capabilities like POI search and multi-modal route planning into AI agent workflows.
Featured*
