Access PixelDojo's API for AI image and video generation. Use when an agent needs to create images or videos, choose a model from the live PixelDojo catalog, check async job status, or download finished assets. PixelDojo is a subscription-based creative platform that exposes multiple generation models through one API, including general image, editing-oriented image, and video workflows.
Use PixelDojo's async API to generate and download AI images or videos.
Runtime requirements:
PIXELDOJO_API_KEYcurl, jq, python3PIXELDOJO_API_BASESet the API key before running any helper:
export PIXELDOJO_API_KEY=your_api_key_here
Optional local env file:
cp ~/.openclaw/skills/pixeldojo/.env.example ~/.openclaw/skills/pixeldojo/.env
Default API base: https://pixeldojo.ai/api/v1
generate.sh or the Nano Banana helper.Do not guess model IDs.
bash ~/.openclaw/skills/pixeldojo/models.sh
For a pinned snapshot of known-good model IDs and example picks, read:
references/model-catalog.mdbash ~/.openclaw/skills/pixeldojo/generate.sh image "editorial product photo of a silver robot" flux-2-pro --aspect-ratio 16:9
Good defaults:
flux-2-maxnano-banana-2flux-kontext-probash ~/.openclaw/skills/pixeldojo/generate.sh video "cinematic ocean waves at sunset" seedance-1.5 --duration 5
Use --image-url for image-to-video models:
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 this when the user specifically wants Nano Banana 2 or strong prompt adherence:
python3 ~/.openclaw/skills/pixeldojo/scripts/generate-nano-banana.py "clean ecommerce hero shot of running shoes" --aspect-ratio 16:9 --output ~/Desktop/shoes.png
bash ~/.openclaw/skills/pixeldojo/status.sh job_abc123
Default download folders:
~/Pictures/AI Generated/images/~/Pictures/AI Generated/videos/Override with:
--output /path/to/file.png
generate.sh supports --aspect-ratio, --duration, --image-url, --output, --poll-interval, and --max-wait.generate.sh covers the shared prompt-based API flow. If a request needs model-specific editing payloads, inspect the live catalog and API behavior before improvising.