A high-performance AI skill for generating and editing photorealistic images with advanced text rendering and native editing capabilities.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install flux2-flash
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 flux2-flash 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 Flux 2 Flash Image Generation?
Flux 2 Flash is a cutting-edge image generation and editing skill powered by Black Forest Labs' FLUX.2 [dev] model. It excels at producing highly realistic visuals, rendering crisp and legible text within images, and providing seamless native editing features. This Openclaw Skills integration allows developers to automate complex visual tasks through a simple API interface. Whether you need to generate a brand new concept from a text prompt or modify an existing image by adding or removing elements, this skill handles the heavy lifting with extreme speed and precision.
The dual-mode architecture of this tool automatically detects whether you are creating from scratch or editing based on the provided input. By integrating these Openclaw Skills into your workflow, you gain access to one of the fastest and most capable image models available today, optimized for both aesthetic quality and functional utility in developer environments.
Flux 2 Flash Image Generation Use Cases
- Generating photorealistic marketing assets and stock photos from descriptive text prompts.
- Editing existing images to add, remove, or replace specific elements using natural language instructions.
- Creating high-quality social media content with accurate and readable text overlays.
- Prototyping visual concepts for web design and digital media directly within your coding agent.
- Batch processing image variations for creative exploration using different seeds and guidance scales.
How Flux 2 Flash Image Generation Works
- Initialize the task by calling the submit_task tool with your specific prompt and optional image URLs.
- The system automatically selects the Text-to-Image mode if no images are provided, or the Image Editing mode if image_urls are included.
- A unique task_id is returned immediately upon successful submission to the Openclaw Skills infrastructure.
- Use the get_task tool to poll the status of your generation which transitions through pending, processing, and completed.
- Retrieve the final high-resolution image URL or error message from the result field once the status is marked as completed.
Flux 2 Flash Image Generation Setup
To integrate this skill into your environment, ensure you have access to the Openclaw Skills ecosystem. No complex local installation is required as it operates via MCP tools. Configure your API keys and call the tools as follows:
# Example of submitting a text-to-image task
mcp-tool-call submit_task --model_id "fal-ai/flux-2/flash" --parameters '{"prompt": "A futuristic city", "image_size": "landscape_16_9"}'
Flux 2 Flash Image Generation Data Schema & Taxonomy
The skill uses a structured JSON schema for both input parameters and task management, compatible with Openclaw Skills standards.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| prompt | string | Yes | - | Detailed description of the image or edit. |
| image_urls | array | No | - | List of 1-4 URLs for image editing mode. |
| image_size | string | No | landscape_4_3 | Preset sizes like square_hd or landscape_16_9. |
| num_images | integer | No | 1 | Number of images to generate (1-4). |
| guidance_scale | number | No | 2.5 | Control over prompt adherence (0-20). |
| output_format | string | No | png | Format: jpeg, png, or webp. |
Flux 2 Flash Image Generation Advanced Features
- Intelligent Automatic Mode Switching between generation and editing based on input context.
- Advanced Text Rendering optimization for clear typography within AI-generated visuals.
- Prompt Expansion support to automatically enhance simple prompts for better visual results.
- Multi-image input support allowing the combination of up to 4 images for complex editing tasks.
- Fine-grained control over generation using guidance scales and seed values for reproducible outputs.
SKILL.md
Loading
Related Openclaw Skills
Fashion Studio
An automated end-to-end workflow for creating professional e-commerce fashion photography and detail pages using specialized AI agent sub-delegation.
fal-ai Model Documentation Discovery
A specialized automation skill to extract all available model variants and documentation links from any fal.ai model page.
Fal Consumption Audit
A specialized auditing tool for reconciling Fal.ai API consumption with internal user billing records to ensure financial accuracy and detect usage anomalies.
Character Creator
An automated workflow for generating comprehensive AI character assets, including descriptions, portraits, and consistent multi-angle reference images.
Hailuo Video Generation (MiniMax 2.3)
An advanced video generation skill leveraging MiniMax Hailuo 2.3 to create cinematic AI videos from text prompts or static images.
Image Model Evaluation
An automated benchmarking suite for evaluating image generation models across dimensions like prompt adherence, style, and character consistency.
Featured*
