OpenClaw Skill

fal-ai

Generate and edit images & videos using fal.ai API — Flux, Gemini, Kling.

🦞 View on ClawhHub GitHub 📦 .skill

Supported Models

Text → Image

nano-banana-pro

Google's Gemini 3 Pro for text-to-image generation

Image → Image

nano-banana-pro/edit

Gemini 3 Pro for image editing — slower but handles complex edits

Image → Image

flux/dev/image-to-image

FLUX.1 dev for fast style transfers (~2-3s)

Image → Video

kling-video/o3/pro/image-to-video

Kling O3 Pro for generating video from images — start/end frames, 3-15s duration

Video → Video

kling-video/o3/pro/video-to-video/edit

Kling O3 Pro for video transformations — supports style refs and character elements

Features

🎨 Text-to-image, image-to-image, and video-to-video
⚡ Queue-based async requests with automatic polling
💾 Pending requests survive restarts
🔧 CLI + Python library included
📝 Easy to add new fal.ai models

Installation

Option 1: ClawhHub (recommended)

openclaw skills install clawhub:Sxela/falai

Option 2: Download .skill file

# Download fal-ai.skill from button above, then:
unzip fal-ai.skill -d ~/.openclaw/workspace/skills/

Option 3: One-liner

cd ~/.openclaw/workspace/skills
curl -L https://sxe.la/skills/fal-ai-skill/fal-ai.skill -o fal-ai.skill
unzip fal-ai.skill && rm fal-ai.skill

Option 4: Clone from GitHub

cd ~/.openclaw/workspace/skills
git clone https://github.com/Sxela/openskills.git
mv openskills/fal-ai-skill ./fal-ai
rm -rf openskills

Setup

Add your fal.ai API key to TOOLS.md:

### fal.ai
FAL_KEY: your-key-here

Get a key at fal.ai/dashboard/keys

Usage

# Generate image from text
python3 scripts/fal_client.py submit "fal-ai/nano-banana-pro" \
  '{"prompt": "A cat astronaut on the moon"}'

# Transform an image
python3 scripts/fal_client.py submit "fal-ai/flux/dev/image-to-image" \
  '{"image_url": "...", "prompt": "anime style"}'

# Poll for results
python3 scripts/fal_client.py poll