Flux Image Generation Server

What is Flux Image Generation Server?

A simple HTTP server that calls the Flux Schnell model on Replicate to generate images from text prompts.

How to use Flux Image Generation Server?

Install dependencies via npm install, set the REPLICATE_API_TOKEN environment variable, compile with npm run build, then start with npm start. The server listens on port 3000 and provides a single POST endpoint at /generate that accepts a JSON body with a prompt field.

Key features of Flux Image Generation Server

• Wraps Replicate’s Flux Schnell model in a local HTTP server
• Accepts text prompts and returns generated image data
• Simple JSON API – one endpoint, no extra configuration
• Runs on port 3000 after build and start commands
• Returns success/error responses in a consistent format

Use cases of Flux Image Generation Server

• Generate images from descriptive text prompts for prototyping or creative work
• Integrate image generation into applications that communicate over HTTP
• Quickly test Flux Schnell model outputs without using Replicate’s web interface

FAQ from Flux Image Generation Server

What does Flux Image Generation Server do?

It provides a local HTTP API that forwards a text prompt to Replicate’s Flux Schnell model and returns the generated image result.

How do I set the Replicate API token?

Export the token as an environment variable before starting the server: export REPLICATE_API_TOKEN=your_token_here.

How do I start the server?

Run npm run build then npm start. The server will listen on port 3000.

What is the API endpoint and request format?

Send a POST request to http://localhost:3000/generate with a JSON body containing a prompt field (string). Example: {"prompt": "a cat wearing a hat"}.

How do I stop the server?

Press Ctrl+C in the terminal where the server is running.