aimlapi-media-gen
Generate images or videos via AIMLAPI (OpenAI-compatible) from prompts. Use when Codex needs to call AI/ML API media endpoints, batch image/video jobs, or produce media files from text prompts using AIMLAPI credentials.
Why use this skill?
Efficiently generate high-quality images and video assets in OpenClaw using the aimlapi-media-gen skill. Automate media production.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/d1m7asis/aimlapi-media-genWhat This Skill Does
The aimlapi-media-gen skill provides a robust interface for OpenClaw agents to interface with AIMLAPI’s generative media suite. By acting as a standardized wrapper around OpenAI-compatible endpoints, this skill allows users to programmatically generate high-fidelity images and video assets. It automates the complexities of authentication, API payload structuring, and local file storage, ensuring that generated media is saved directly into specified project directories for immediate use in larger workflows. Whether you are generating marketing visuals, abstract concept art, or synthetic video frames, this skill handles the heavy lifting of API communication.
Installation
To install this skill, use the ClawHub CLI tool to fetch the repository components. Ensure you have your AIMLAPI credentials ready, as the scripts require an API key to function. Run the following command in your terminal:
clawhub install openclaw/skills/skills/d1m7asis/aimlapi-media-gen
Once installed, ensure your environment variable AIMLAPI_API_KEY is exported in your shell session. You can verify the installation by running the help command on the provided scripts, such as python3 scripts/gen_image.py --help.
Use Cases
- Automated Content Creation: Generate batch imagery for blog posts or social media campaigns directly from a list of prompts.
- Rapid Prototyping: Quickly create video storyboards or placeholder assets for game development and UI/UX design.
- Workflow Orchestration: Integrate image and video generation into multi-step agent workflows where visual output is required as a downstream input.
- Synthetic Data Generation: Produce large sets of images for training or testing computer vision models via automated API calls.
Example Prompts
- "Generate four high-resolution images of a cyberpunk city at night using the gpt-image-1 model and save them to the folder ./project/assets/night_city."
- "Create a 6-second video showing a time-lapse of a flower blooming in a desert using the aimlapi provider video model."
- "Batch generate 10 variations of a minimalist logo for a tech startup and place the files in the output directory."
Tips & Limitations
- Payload Customization: Always use the
--extra-jsonflag to pass model-specific parameters that are not supported by the default script flags. This ensures you can utilize the full feature set of specialized models. - Endpoint Configuration: Since video generation parameters vary significantly between model providers, consult
references/aimlapi-media.mdbefore initiating high-volume video tasks to ensure your payloads are correctly structured. - Storage Management: The scripts will overwrite files if the naming convention remains identical. We recommend unique file naming or clearing directories before bulk runs to prevent data loss.
- API Limits: Keep in mind that AIMLAPI quotas apply to these requests; heavy batching may exceed your monthly or per-minute token limits.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-d1m7asis-aimlapi-media-gen": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api, code-execution