cf ai Image

    4

    Free, high-speed SDXL Lightning text-to-image generation via Cloudflare Workers AI.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    cf-ai-image

    Example session with this skill installed

    Generate a cyberpunk street at night with neon lights using the cf-ai-image skill.

    • Read your context and instructions
    • Compiled the cf-ai-image
    • Generated the image

    Generating image...
    Prompt: cyberpunk street at night, neon lights
    Model: SDXL Lightning (4 steps)

    Saved: /users/home/.cf-ai-image/20231027_143005.png (1240.5 KB)

    20231027_143005.png

    PNG · 1536×1024

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    What it does

    This skill provides a high-performance interface for generating high-resolution images using the Stable Diffusion XL (SDXL) Lightning model. By leveraging Cloudflare Workers AI, it offloads computationally expensive inference from your local machine to Cloudflare's global GPU network.

    Why use this skill

    Generating SDXL images usually requires a high-end GPU or expensive monthly subscriptions. This skill solves that by utilizing Cloudflare's free tier, allowing for professional-grade 1024x1024 image generation with zero infrastructure costs. Unlike standard SDXL, the Lightning variant used here produces high-fidelity results in just four steps, drastically reducing latency for your AI agent's workflows.

    Supported tools

    • Model: SDXL Lightning (4-step inference)
    • Infrastructure: Cloudflare Workers AI
    • Output: Direct PNG byte stream processing
    • Parameters: Supports custom dimensions (width/height), negative prompts, and guidance scales.

    The Output

    The skill yields a high-quality PNG image file saved locally. It handles the raw binary response from the Cloudflare API, manages local directory structures, and provides file path feedback to the calling agent.

    • Requires Cloudflare account & API tokens.
    • Fixed 4-step inference (no step count customization).
    • Standard Cloudflare Workers AI rate limits apply.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 7 months ago

    Permissions

    Terminal / Shell
    Network Access
    Environment Variables
    Listed7 months ago

    What's inside

    Frequently Asked Questions

    This skill generates high-quality 1024x1024 images using the SDXL Lightning model via Cloudflare's global GPU network, eliminating the need for expensive local hardware or monthly image-generation subscriptions.

    Unlike standard SDXL which requires 20-50 steps, the Lightning model used in this skill achieves professional-grade results in just 4 steps, providing significantly faster response times for your AI workflows.

    You will need a Cloudflare account to access their Workers AI API; however, image generation currently falls under their generous free tier, allowing for cost-effective scaling.

    The skill is designed with standard Python integration, making it compatible with most major agent frameworks that support custom tool calls and local file system access.

    Upon acquisition, you receive the full skill implementation, configuration instructions, and any necessary integration scripts to start generating images immediately.

    Yes, the skill allows you to pass custom parameters including negative prompts, specific dimensions (width/height), and guidance scales to ensure the output matches your agent's requirements.

    New in Branding & Design