Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Wraps the ImaginePro API to generate images and videos using Midjourney, Flux, Nano Banana, and Lumi Girl models. Supports post-processing operations including upscaling, background removal, and prompt enhancement. All generation is asynchronous with built-in polling via a Python helper script.
Consolidates five distinct generation models and post-processing tools under a single API key and Python script, avoiding separate integrations for each provider.
When to use it
- Generate product mockups with reference images using Nano Banana
- Create character portraits or anime-style art with Lumi Girl
- Upscale and variant Midjourney outputs for final delivery
- Remove backgrounds from product photos for e-commerce
- Generate short videos from two frame images with MJ Video
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: generate a cinematic portrait of a warrior queen in 2:3 aspect ratio and upscale the best result
- 1Run `python3 imaginepro_api.py wait --prompt 'portrait of a warrior queen, cinematic lighting --ar 2:3' --model midjourney` to submit and poll until done
- 2Receive the messageId and image URL from the completed response
- 3Run `python3 imaginepro_api.py upscale --id <messageId> --button U1` to upscale the first quadrant
- 4Poll status with `python3 imaginepro_api.py status --id <upscaleMessageId>` until DONE
- 5Return the final upscaled image URL to the user
High-resolution upscaled portrait image URL ready for download
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.