What can you do with it?

The /image-generate command enables you to create unique images from text descriptions using the high-performance Flux Schnell model. You can generate artwork, product mockups, marketing visuals, concept designs, illustrations, and professional graphics by simply describing what you want to see, with precise control over style, composition, and quality.

How to use it?

Basic Command Structure

/image-generate [description]

Parameters

Required:

  • prompt - Text description of the image you want to generate

Optional:

  • aspect_ratio - Image dimensions: “1:1”, “16:9”, “21:9”, “3:2”, “2:3”, “4:5”, “5:4”, “3:4”, “4:3”, “9:16”, “9:21” (defaults to “1:1”)
  • num_outputs - Number of variations to generate: 1-4 (defaults to 1)
  • num_inference_steps - Number of denoising steps: 1-4 (defaults to 4). Lower steps = faster but lower quality
  • seed - Random seed for reproducible generation (integer, optional)
  • output_format - Format of output images: “webp”, “jpg”, “png” (defaults to “webp”)
  • output_quality - Quality when saving images: 0-100 (defaults to 80). Not relevant for PNG outputs
  • disable_safety_checker - Disable safety checker for generated images (boolean, defaults to false)
  • go_fast - Run faster predictions with fp8 quantized model (boolean, defaults to true). Note: outputs not deterministic when enabled
  • megapixels - Approximate megapixels for generated image: “1”, “0.25” (defaults to “1”)
  • fileLinksExpireInDays - How long generated files remain accessible: 1-7 days (defaults to 7)
  • fileLinksExpireInMinutes - How long generated files remain accessible in minutes (takes precedence over days)

Response Format

The command returns:

{
  "output": [
    {
      "url": "https://generated-file-url",
      "mimeType": "image/webp"
    }
  ]
}

Note: All generated images are automatically saved to your “Multimedia Artifact” file store and will be accessible for the duration specified by the fileLinksExpireInDays parameter.

Examples

Basic Image Generation

/image-generate
prompt: A modern office space with plants and natural lighting

Generates a single square image of an office space with default settings.

Marketing Visual Creation

/image-generate
prompt: Professional product photography of a sleek wireless headphones on a marble surface with soft studio lighting
aspect_ratio: 16:9
output_format: png
output_quality: 95
num_inference_steps: 4

Creates a high-quality product photo perfect for e-commerce or marketing materials.

Artistic Illustration

/image-generate
prompt: Watercolor painting of a serene mountain landscape with a crystal clear lake reflecting autumn colors
aspect_ratio: 4:3
num_outputs: 3
seed: 12345

Generates three variations of an artistic landscape using a fixed seed for consistency.

Logo and Branding

/image-generate
prompt: Minimalist logo design for a tech startup, clean geometric shapes, blue and white color scheme, modern typography
aspect_ratio: 1:1
output_format: png
disable_safety_checker: false

Creates a logo concept with transparent background support.

Social Media Content

/image-generate
prompt: Instagram-style flat lay of a cozy reading nook with books, coffee cup, and warm lighting, aesthetic composition
aspect_ratio: 9:16
output_format: webp
go_fast: true
megapixels: 1

Generates vertical content optimized for Instagram stories with fast processing.

Character Design

/image-generate
prompt: Character design of a friendly robot mascot for a children's app, colorful, approachable, cartoon style
aspect_ratio: 1:1
num_outputs: 4
num_inference_steps: 4
output_quality: 90

Creates multiple character variations for design iteration.

Architectural Visualization

/image-generate
prompt: Architectural rendering of a sustainable eco-friendly house with solar panels, green roof, large windows, modern design
aspect_ratio: 21:9
output_format: jpg
output_quality: 85
fileLinksExpireInDays: 7

Generates a wide-format architectural visualization that stays accessible for a week.

Notes

Model Capabilities:

  • Fast generation (typically 10-30 seconds)
  • High-quality outputs with professional results
  • Excellent for commercial and creative use cases
  • Supports various artistic styles and photorealistic imagery

Limitations:

  • Cannot generate images of specific real people
  • Avoids creating harmful or inappropriate content
  • Results may vary based on prompt complexity
  • Video generation is not supported

Model Parameters (black-forest-labs/flux-schnell)

Image Generation Parameters

  • prompt (required): Prompt for generated image
  • aspect_ratio: Aspect ratio (“1:1”, “16:9”, “21:9”, “3:2”, “2:3”, “4:5”, “5:4”, “3:4”, “4:3”, “9:16”, “9:21”, default: “1:1”)
  • num_outputs: Number of outputs to generate (1 to 4, default: 1)
  • num_inference_steps: Number of denoising steps (1 to 4, default: 4). Lower steps = faster but lower quality
  • seed: Random seed for reproducible generation (integer, optional)
  • output_format: Format of output images (“webp”, “jpg”, “png”, default: “webp”)
  • output_quality: Quality when saving images (0 to 100, default: 80). Not relevant for PNG outputs
  • disable_safety_checker: Disable safety checker for generated images (boolean, default: false)
  • go_fast: Run faster predictions with fp8 quantized model (boolean, default: true). Note: outputs not deterministic when enabled
  • megapixels: Approximate megapixels for generated image (“1”, “0.25”, default: “1”)