VM0Agent Skills
fal.ai
AI image generation from text prompts
fal.ai provides AI image generation from text prompts using various models including Flux and Recraft.
Required Environment
| Name | Type | Description |
|---|---|---|
FAL_KEY | secret | API key from fal.ai Dashboard |
Configuration
version: "1.0"
agents:
my-agent:
framework: claude-code
skills:
- https://github.com/vm0-ai/vm0-skills/tree/main/fal.aiRun
Store your secret on the platform (recommended, one-time setup):
vm0 secret set FAL_KEY your-fal-keyThen run your agent - secret is automatically loaded:
vm0 run my-agent "generate an image of a sunset"For CI/CD or temporary overrides, pass secrets at runtime: --secrets FAL_KEY=value. See Environment Variables for details.
Example Instructions
# Image Generator Agent
You use fal.ai to generate images from text.
## Workflow
1. Receive image description
2. Select appropriate model
3. Generate image via fal.ai API
4. Return image URL
## Models
- nano-banana-pro: Fast
- flux/schnell: Fast generation
- recraft-v3: High quality# Thumbnail Creator Agent
You create thumbnails and social media images.
## Workflow
1. Receive content topic
2. Create descriptive prompt
3. Generate image with correct size
4. Download and save image
## Image Sizes
- square, landscape_16_9
- portrait_4_3, square_hd