Zenmux Image Gen Skill

Zenmux Image Gen Skill

Generate images using Zenmux's Vertex AI API with Gemini image models.

Features

• Text-to-image generation
• Single image editing
• Multi-image composition (up to 14 images)
• Multiple Gemini model support

Generate

uv run {baseDir}/scripts/generate_image.py --prompt "your image description" --filename "output.png"

Edit (single image)

uv run {baseDir}/scripts/generate_image.py --prompt "edit instructions" --filename "output.png" -i "/path/to/input.png"

Multi-image composition (up to 14 images)

uv run {baseDir}/scripts/generate_image.py --prompt "combine these into one scene" --filename "output.png" -i img1.png -i img2.png -i img3.png

Available Models

Specify model with --model:

uv run {baseDir}/scripts/generate_image.py --prompt "a sunset over mountains" --filename "sunset.png" --model "google/gemini-2.5-flash-image"

API Key Configuration

1. Environment variable (recommended):

   export ZENMUX_API_KEY="your-api-key"
   

2. OpenClaw config:

   openclaw config set skills.zenmux-image-gen-skill.apiKey "your-api-key"
   

3. Command line argument:

   uv run {baseDir}/scripts/generate_image.py --api-key "your-api-key" --prompt "..." --filename "..."
   

Notes

• Use timestamps in filenames: yyyy-mm-dd-hh-mm-ss-name.png.
• The script prints a MEDIA: line with the file path.
• Important: To send the image to chat channels (Telegram, Discord, etc.), use the message tool with filePath parameter. The MEDIA: line alone will NOT auto-attach the image as a real attachment.
• Do not read the image back; report the saved path only.