A high-performance image generation skill supporting fal.ai and BytePlus Seedream for reference-guided, batch, and high-resolution visual creation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install phy-fal-image-gen
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install phy-fal-image-gen using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is FAL Image Generation Skill?
This skill enables AI agents to generate professional-grade visual content by interfacing with fal.ai and BytePlus Seedream APIs. It provides a robust model routing system that automatically selects the best backend—whether it is the cost-effective Seedream for photo realism or Nano Banana Pro for precise text rendering in posters. By integrating this into your Openclaw Skills library, you gain the ability to handle complex image tasks including text-to-image, image-to-image with up to 14 references, and high-resolution outputs suitable for print or social media.
The skill is designed to be highly flexible, offering specialized handling for different visual requirements. It includes specific color control logic for various models, such as Kodak Portra 400 analog film descriptions for fal.ai NBP and lighting-based editorial descriptions for Seedream, ensuring that your Openclaw Skills produce aesthetically superior results every time.
FAL Image Generation Skill Use Cases
- Generating high-quality social media assets for Instagram, Xiaohongshu, or Stories using optimized aspect ratios like 9:16 and 3:4.
- Creating professional posters and infographics with structured JSON prompts for precise text placement and layout control.
- Executing large-scale batch image generation in parallel across multiple models like Flux and Seedream to save time and resources.
- Using multiple reference images to maintain consistent style, character appearance, or layout across generated visual assets.
How FAL Image Generation Skill Works
- The user provides a prompt, optional reference images, and desired aspect ratio via the command line or a batch JSON file.
- The skill routing logic selects the appropriate backend (Seedream, Flux, or NBP) based on the user's flags or task complexity.
- The Python script executes via the uv runner, processing requests asynchronously for parallel batch operations.
- Images are generated and automatically saved to a structured directory organized by the current date for easy retrieval.
- The script outputs a MEDIA path reference, allowing the agent gateway to deliver the final visual asset to the user immediately.
FAL Image Generation Skill Setup
To integrate this into your Openclaw Skills environment, configure your API keys and run the script using the uv package manager.
# Set environment variables
export FAL_API_KEY="your_fal_api_key"
export BYTEPLUS_API_KEY="your_byteplus_api_key"
# Run a single image generation
uv run {baseDir}/skills/fal-image-gen/scripts/generate.py \
--prompt "A mountain temple at golden hour, low angle, 24mm f/8" \
--aspect-ratio 9:16 \
--output {baseDir}/output/
FAL Image Generation Skill Data Schema & Taxonomy
The skill organizes output in a date-based directory structure and supports complex input via JSON for batching.
| Feature | Description |
|---|---|
| Output Path | {baseDir}/output/YYYY-MM-DD/ organized by date |
| Media Trigger | Prints MEDIA: /path/to/image.png for gateway delivery |
| Batch Input | JSON array containing prompt, model, refs, and aspect_ratio |
| Resolution Tiers | standard, high (default), and max (up to 12.8M px for print) |
FAL Image Generation Skill Advanced Features
- Intelligent model routing between fal.ai and BytePlus Seedream to optimize for cost, speed, or quality requirements.
- Support for up to 14 reference images in Seedream, allowing for unprecedented fidelity in style and layout guidance.
- JSON-structured prompt support for Nano Banana Pro (NBP) to ensure accurate text rendering in complex graphic designs.
- Parallel batch generation capabilities allowing diverse model calls (Flux, Seedream, NBP) within a single execution block.
- Automatic image hosting management that transitions BytePlus temporary URLs to fal.ai permanent storage for long-term access.
SKILL.md
Loading
Related Openclaw Skills
Daily Social Media Routine
A structured 15-20 minute engagement routine designed to help indie developers and founders build a consistent social presence across multiple platforms.
Creator Watchlist & Content Analyzer
A powerful tool for tracking and analyzing high-performing Twitter creators to extract viral content patterns and growth insights within Openclaw Skills.
Content Type Router
A sophisticated routing engine that transforms natural language descriptions into structured visual configurations for automated image generation.
Brand DNA Extractor
An advanced brand identity extraction engine that uses computer vision and web scraping to generate structured visual profiles from any website.
Founder Content System
A complete content creation and multiplication system designed for solo founders and indie hackers to scale their presence across social platforms.
Instagram Public Profile Scraper
A lightweight Python tool for scraping public Instagram profile metrics and recent post data without requiring a login or browser automation.
Featured*
