OpenClaw Skill Guide

Use PixelDojo in OpenClaw for AI images, video, and live model selection.

This page is the OpenClaw-specific companion to PixelDojo AI Agents. It focuses on installing the PixelDojo skill from ClawHub, exporting `PIXELDOJO_API_KEY`, checking the live catalog, and running the exact OpenClaw commands that create images or videos.

Live catalog with 27+ models
Async jobs with status polling
Text-to-image, text-to-video, image-to-video

Workflow

How to use PixelDojo from OpenClaw

The install flow is simple: install the skill, export the key, inspect the live catalog, then generate and poll the async job.

Step 01

Install the skill from ClawHub

Start from the PixelDojo skill listing so OpenClaw gets the packaged scripts, setup instructions, and reference files.

Step 02

Export your API key

Set PIXELDOJO_API_KEY before running helpers so every request is authenticated against the live PixelDojo API.

Step 03

Check the live model catalog

Run models.sh first, choose the best fit for the request, and do not guess model IDs from memory.

Step 04

Generate, poll, and download

Use generate.sh or the Nano Banana helper, poll the async job, and return the saved asset path to the user.

Commands

Exact OpenClaw commands to run

These examples match the current PixelDojo skill workflow on ClawHub: setup, catalog lookup, image generation, video generation, Nano Banana, and direct status polling.

Set up the skill

Export your key and optionally copy the local env template.

export PIXELDOJO_API_KEY=your_api_key_here
cp ~/.openclaw/skills/pixeldojo/.env.example ~/.openclaw/skills/pixeldojo/.env

Check the live model catalog

Always inspect the live catalog first so OpenClaw uses current model IDs and capabilities.

bash ~/.openclaw/skills/pixeldojo/models.sh

Generate an image

Use the shared prompt-based helper for standard text-to-image generation.

bash ~/.openclaw/skills/pixeldojo/generate.sh image "editorial product photo of a silver robot" flux-2-pro --aspect-ratio 16:9

Generate a video

Use the video mode when the request needs motion, duration, or image-to-video input.

bash ~/.openclaw/skills/pixeldojo/generate.sh video "cinematic ocean waves at sunset" seedance-1.5 --duration 5

bash ~/.openclaw/skills/pixeldojo/generate.sh video "slow camera push-in" wan-2.6-flash --image-url https://example.com/input.png --duration 5

Use Nano Banana 2

Reach for the dedicated helper when prompt adherence or typography quality matters most.

python3 ~/.openclaw/skills/pixeldojo/scripts/generate-nano-banana.py "clean ecommerce hero shot of running shoes" --aspect-ratio 16:9 --output ~/Desktop/shoes.png

Check job status

Poll the async job directly when you already have a job ID and want the latest status.

bash ~/.openclaw/skills/pixeldojo/status.sh job_abc123

Model picks

Recommended models for common OpenClaw requests

If the user asks for a default recommendation, these are good starting points. If the request is specialized, check the live catalog before choosing.

Best general image quality

Strong default pick for polished image generation tasks.

flux-2-max

Prompt adherence and typography

Best fit when the user cares about text rendering or exact instructions.

nano-banana-2

Editing-oriented image work

Use for editing flows and context-sensitive image transformations.

flux-kontext-pro

Fast image-to-video motion

A strong OpenClaw option for quick motion from a reference image.

wan-2.6-flash

Text-to-video generation

Good first stop for short cinematic video prompts.

seedance-1.5

Output paths and overrides

~/Pictures/AI Generated/images/
~/Pictures/AI Generated/videos/
Override with `--output /path/to/file.png`

Practical notes for agents

  • Default download folders are `~/Pictures/AI Generated/images/` and `~/Pictures/AI Generated/videos/`.
  • Use `--output /path/to/file.png` or `--output /path/to/file.mp4` when the user needs a custom save path.
  • The shared helper supports `--aspect-ratio`, `--duration`, `--image-url`, `--output`, `--poll-interval`, and `--max-wait`.
  • If a request needs model-specific editing payloads, inspect the live catalog and API behavior before improvising.
  • PixelDojo markets commercial usage rights, but users still need to follow PixelDojo terms and any third-party model restrictions.

FAQ

OpenClaw and PixelDojo FAQ

How do I install the PixelDojo OpenClaw skill?

Open the ClawHub listing, install the PixelDojo skill into OpenClaw, then export PIXELDOJO_API_KEY before running any helper scripts.

What environment variable does the skill need?

The required variable is PIXELDOJO_API_KEY. You can also override the API base with PIXELDOJO_API_BASE if you need a non-default endpoint.

Which command should I run first in OpenClaw?

Run models.sh first so you are selecting from the live PixelDojo catalog instead of guessing model IDs or outdated capabilities.

Can OpenClaw use PixelDojo for both images and videos?

Yes. The PixelDojo skill supports image generation, text-to-video, image-to-video, async job polling, and direct downloads of the completed output.

When should I use the Nano Banana helper?

Use the dedicated Nano Banana helper when the user specifically wants Nano Banana 2 or when prompt adherence and typography quality are especially important.

Ready to run it

Install the PixelDojo OpenClaw skill and start generating.

Start with the ClawHub listing, grab your API key, then use the exact OpenClaw commands above to create image or video assets from the live PixelDojo catalog.