plume-image
Plume AI image generation and editing service. Auto-triggers when users send images or describe image needs. Supports: text-to-image, image-to-image, background removal, watermark removal, style transfer, text-to-video, image-to-video. Activate when user mentions: generate image, edit image, remove background, change background, remove watermark, text-to-image, image-to-image, AI art, style transfer, generate poster, photo editing, generate video, AI video, animate this image, make it move, image-to-video, make image into video, seedance2, seedance.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/dake6767/plume-imagePlume AI Image Service
Help users complete AI image generation and editing through natural language.
π¨ Critical Workflow Rules (Must Follow)
All tasks must use: create β poll_cron.py register β reply to user immediately β end
Strictly prohibited:
- β Do NOT use
process_image.py pollcommand - β Do NOT run check after register
- β Do NOT use sleep to wait before polling
- β Do NOT ask users to paste API Key in chat
- β Do NOT auto-create tasks when user sends only an image without text instructions β the user may just be preparing a reference image; wait for explicit text instructions before acting
Correct approach:
- β
Call
poll_cron.py registerimmediately after creating a task - β Reply to user right after register succeeds, informing them that processing has started
- β End the current session; background process polls automatically and delivers result
- β When receiving a pure image (no text), just reply "Got your image. What would you like to do with it?" and wait for the user's next message
β οΈ Mandatory Pre-check (Run Before Every Use)
python3 ${CLAUDE_SKILL_DIR}/scripts/check_config.py
- Output
CONFIGURED: proceed with subsequent operations - Output
NOT_CONFIGURED: stop immediately, prompt user to configure as follows (do NOT ask for the key in chat):
To use the Plume AI image service, you need to configure your API Key first:
- Visit Plume Platform to register and obtain an API Key
- Edit
~/.openclaw/openclaw.json, add toskills.entries:Or add"plume-image": { "env": { "PLUME_API_KEY": "your-key" } }PLUME_API_KEY=your-keyto the~/.openclaw/.envfile- Enter
/restartto apply changes
Background Polling Behavior
This skill starts a background Python process via poll_cron.py register to poll task status. Results are delivered via openclaw message send when the task completes.
- Poll interval: images 3β5s, videos 10β30s
- Default timeout: 30 minutes (adjustable by category)
- Max concurrency: 5 active polling tasks
- Process exits automatically and cleans up metadata after task completes, fails, or times out
- Results delivered via
openclaw message send, no direct channel API calls
Supported categories (fixed enum, do not invent)
| category | Alias | Use case | Default |
|---|---|---|---|
Banana2 | ι¦θ | text-to-image / image-to-image / style transfer | β default for images |
BananaPro | ι¦θPro | text-to-image / image-to-image (user explicitly requested) | |
remove-bg | background removal | ||
remove-watermark | watermark removal | ||
seedream | ε³ζ’¦/θ±ε ε³ζ’¦ | Doubao Seedream image generation | |
veo | text-to-video / image-to-video | β default for videos | |
seedance2 | Seedance2 video (user explicitly requested) |
Metadata
Not sure this is the right skill?
Describe what you want to build β 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-dake6767-plume-image": {
"enabled": true,
"auto_update": true
}
}
}