AI SDK - Firemoon Provider

The Firemoon provider for the AI SDK contains image and video generation support for the Firemoon Studio API.

Setup

The Firemoon provider is available in the firemoon-ai-sdk-provider module. You can install it with:

npm i firemoon-ai-sdk-provider

Provider Instance

You can import the default provider instance firemoon from firemoon-ai-sdk-provider:

import { firemoon } from 'firemoon-ai-sdk-provider';

Configuration

If you need to configure the provider, you can use the createFiremoon function:

import { createFiremoon } from 'firemoon-ai-sdk-provider';

const firemoon = createFiremoon({
  apiKey: 'your-api-key', // defaults to FIREMOON_API_KEY environment variable
  baseURL: 'https://firemoon.studio/api', // optional, defaults to Firemoon Studio API
});

Usage

Image Generation

Generate images using FLUX models:

import { firemoon } from 'firemoon-ai-sdk-provider';
import { experimental_generateImage as generateImage } from 'ai';

const { image } = await generateImage({
  model: firemoon.image('flux/dev'),
  prompt: 'A serene mountain landscape at sunset',
});

const filename = `image-${Date.now()}.png`;
fs.writeFileSync(filename, image.uint8Array);
console.log(`Image saved to ${filename}`);

Advanced Image Generation

Pass additional options using providerOptions:

const { image } = await generateImage({
  model: firemoon.image('flux/dev'),
  prompt: 'A futuristic city with flying cars',
  size: 'landscape_16_9',
  providerOptions: {
    firemoon: {
      guidance_scale: 7.5,
      num_inference_steps: 35,
      seed: 12345,
    },
  },
});

Multiple Images

Generate multiple images in a single request:

const { images } = await generateImage({
  model: firemoon.image('flux/dev'),
  prompt: 'A beautiful sunset',
  n: 4, // Generate 4 images
});

images.forEach((image, index) => {
  fs.writeFileSync(`image-${index}.png`, image.uint8Array);
});

Video Generation

Generate videos using Kling models:

const result = await generateImage({
  model: firemoon.image('kling/kling-2-1-master'),
  prompt: 'A butterfly emerging from its chrysalis',
  providerOptions: {
    firemoon: {
      duration: '5',
      aspect_ratio: '16:9',
    },
  },
});

Supported Models

Image Models

• FLUX Models

  • flux/dev - Fast, high-quality image generation
  • flux/schnell - Rapid image generation
  • flux/pro - Professional-grade images

• Ideogram Models

  • ideogram/v3 - Advanced image generation
  • ideogram/v3-turbo - Fast ideogram generation
  • ideogram/v3-character-edit - Character editing

Video Models

• Kling Models

  • kling/kling-2-1-master - Professional video generation
  • kling/kling-1-6 - Video generation

• Minimax Models

  • minimax/hailuo-02 - Creative AI content
  • minimax/video-01 - Video generation

• Google Veo Models

  • google/veo-3-fast - Fast video generation

Model Options

Common Options

All models support these options via providerOptions.firemoon:

• seed (number) - Random seed for reproducible results
• num_images (number) - Number of images to generate (1-4)

Image Model Options

FLUX and Ideogram models support:

• image_size (string) - Image dimensions: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
• guidance_scale (number) - How closely to follow the prompt (1-20)
• num_inference_steps (number) - Number of denoising steps (1-50)

Video Model Options

Kling and video models support:

• duration (string) - Video duration in seconds
• aspect_ratio (string) - Video aspect ratio: 16:9, 9:16, 1:1

Authentication

You need a Firemoon Studio API key to use this provider. You can obtain one from:

1. Sign in to Firemoon Studio
2. Navigate to the API Keys page
3. Create a new API key

Set your API key as an environment variable:

export FIREMOON_API_KEY=your_api_key_here

Or pass it directly when creating the provider:

const firemoon = createFiremoon({
  apiKey: 'your_api_key_here',
});

Error Handling

The provider handles various error scenarios:

• 401 Unauthorized - Invalid or missing API key
• 403 Forbidden - Access denied or insufficient credits
• 429 Too Many Requests - Rate limit exceeded
• 500 Internal Server Error - Generation failed

Example error handling:

try {
  const { image } = await generateImage({
    model: firemoon.image('flux/dev'),
    prompt: 'A beautiful landscape',
  });
} catch (error) {
  console.error('Generation failed:', error.message);
}

Documentation

For more information about Firemoon Studio:

• Firemoon Studio
• API Documentation
• Quickstart Guide

For more information about the AI SDK:

• AI SDK Documentation
• AI SDK on GitHub

Support

Need help? Contact Firemoon Studio at [email protected]