text-to-image

Create image from text - Z-Image

Generate high-quality images from text descriptions using the Z-Image turbo model.

Key Features:

  • Superior speed with turbo architecture
  • High-quality image generation
  • Flexible image size configuration
  • Supports LoRA and ControlNet variants

Best for:

  • Fast prototyping and iteration
  • High-volume image generation
  • Cost-effective production workloads
post/v1/ai/text-to-image/z-image

Request

  • Base URL: https://api.magnific.com
  • URL: https://api.magnific.com/v1/ai/text-to-image/z-image
  • Auth: API key in header x-magnific-api-key

Request body

promptstring required

Text description of the image you want to generate.

Tips:

  • Be specific about visual details, composition, and style
  • Z-Image excels at fast, high-quality image generation
  • Works well with detailed scene descriptions

Examples:

  • Simple: "A suited raccoon smoking a cigar"
  • Detailed: "A cyberpunk city street at night, neon signs reflecting on wet pavement, flying cars in the distance"
webhook_urlstring uri

Optional callback URL that will receive asynchronous notifications whenever the task changes status. The payload sent to this URL is the same as the corresponding GET endpoint response, but without the data field.

image_size'square' | 'square_hd' | 'portrait_3_4' | 'portrait_9_16' | 'landscape_4_3' | 'landscape_16_9'

The aspect ratio and size of the generated image. If not specified, defaults to square_hd (1024x1024).

Available sizes:

  • square: 512x512 pixels
  • square_hd: 1024x1024 pixels (default)
  • portrait_3_4: 768x1024 pixels
  • portrait_9_16: 576x1024 pixels
  • landscape_4_3: 1024x768 pixels
  • landscape_16_9: 1024x576 pixels
num_inference_stepsinteger

The number of inference steps to perform. Higher values may produce more detailed images but take longer. For Z-Image turbo, 8 steps is recommended for optimal speed/quality balance.

seedinteger

Random seed for reproducibility. Using the same seed with identical parameters produces the same image. Useful for iterating on a design or creating variations.

output_format'jpeg' | 'png'

The format of the generated image.

  • png: Lossless format, best for images with text or sharp edges
  • jpeg: Compressed format, smaller file size
enable_safety_checkerboolean

Whether to enable the content safety checker. When enabled, the model filters potentially unsafe content.

Example request

{
  "prompt": "A suited raccoon smoking a cigar",
  "webhook_url": "https://www.example.com/webhook",
  "image_size": "square_hd",
  "num_inference_steps": 8,
  "seed": 42,
  "output_format": "png"
}

Response

OK - The request has succeeded and the Z-Image process has started.

Example response

{
  "data": {
    "generated": [
      "https://openapi-generator.tech",
      "https://openapi-generator.tech"
    ],
    "task_id": "046b6c7f-0b8a-43b9-b35d-6489e6daee91",
    "status": "CREATED"
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.