Minimax Image 01 Text To Image API Documentation

Minimax Image 01 Text To Image API Documentation

Playground

MiniMax Image-01 text-to-image model generates high-quality images from text descriptions. Create diverse visuals across multiple styles and scenarios with natural language prompts. Supports multiple aspect ratios and custom dimensions. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

MiniMax Image-01 Text-to-Image is a powerful AI image generation model that creates high-quality images from text descriptions. Part of the MiniMax image-01 family, this model excels at understanding natural language prompts and generating diverse, creative visuals across multiple styles and scenarios. Perfect for content creators, designers, marketers, and developers building AI-powered applications.

Key Features

• Natural Language Understanding Simply describe what you want to see in plain text (up to 1500 characters), and the model generates corresponding images with impressive accuracy and creativity.

• Flexible Image Dimensions Specify exact pixel dimensions from 512×512 to 2048×2048 pixels (must be divisible by 8) for precise control over output size. Common sizes include 1024×1024, 1280×720, 1152×864, and more.

• Prompt Optimization Built-in prompt optimizer automatically enhances your text descriptions for better generation results, making it easier to achieve professional-quality outputs even with simple prompts.

• Batch Generation Generate up to 9 images in a single request, perfect for exploring creative variations and selecting the best result for your needs.

• Reproducible Results Use seed values to generate consistent results across multiple runs, essential for iterative refinement and maintaining consistency in production workflows.

• Multiple Output Formats Receive generated images as direct URLs (24-hour expiration) or Base64-encoded data for immediate embedding in your applications.

Use Cases

• Content Creation: Generate unique visuals for blogs, articles, social media posts, and marketing materials
• Concept Art: Quickly visualize ideas, characters, scenes, and environments for creative projects
• Product Mockups: Create product visualizations, packaging designs, and promotional imagery
• Marketing & Advertising: Generate eye-catching visuals for campaigns, ads, and promotional content
• Game Development: Create concept art, textures, backgrounds, and character designs
• E-commerce: Generate product lifestyle images, backgrounds, and contextual scenes
• Education: Create custom illustrations for educational materials, presentations, and courses
• Prototyping: Rapidly generate visual concepts for UI/UX design and app development

Supported Formats & Dimensions

Output Dimensions:

• Width/Height range: 512 to 2048 pixels
• Must be divisible by 8
• Common sizes: 1024×1024 (square), 1280×720 (widescreen), 1152×864 (standard), 1248×832 (photo), 832×1248 (portrait photo), 864×1152 (portrait), 720×1280 (mobile/vertical), 1344×576 (ultra-wide)

Output Formats:

• URL (default): Direct links to generated images, valid for 24 hours
• Base64: Encoded image data for direct embedding

How to Use

Basic Text-to-Image Generation

1. Write Your Prompt

• Describe the image you want in the prompt field (max 1500 characters)
• Be specific about subjects, style, composition, lighting, and mood
• Example: “A serene mountain landscape at sunset with purple and orange skies, snow-capped peaks, and a crystal-clear lake reflecting the colors”

2. Select Image Size

• Specify dimensions using the size parameter like “1024 * 1024” or “1280 * 720”
• Choose dimensions that match your use case (square for social media, widescreen for presentations, etc.)

3. Configure Options

• num_images: Set 1-9 to generate multiple variations (default: 1)
• prompt_optimizer: Enable for automatic prompt enhancement (recommended for beginners)
• seed: Use a specific number for reproducible results

4. Generate

• Submit your request and receive generated images as URLs or Base64 strings
• Images are typically ready within seconds

Advanced Tips

Prompt Writing Best Practices:

• Start with the main subject, then add details about style, lighting, composition
• Use descriptive adjectives: “vibrant”, “moody”, “minimalist”, “photorealistic”
• Specify artistic styles: “oil painting”, “digital art”, “watercolor”, “3D render”
• Include lighting details: “golden hour”, “studio lighting”, “dramatic shadows”
• Mention camera angles: “aerial view”, “close-up”, “wide angle”

Using Seeds for Consistency:

• Generate an image you like and note its seed value
• Use the same seed with modified prompts to create variations
• Perfect for maintaining consistent style across multiple images

Batch Generation Strategy:

• Generate 4-9 variations in one request to explore different interpretations
• Compare results and select the best output
• More cost-effective than multiple single-image requests

API Parameters

• prompt (required): Text description of desired image (max 1500 chars)
• size: Image dimensions (e.g., “10241024”, “1280720”)
• num_images: Number of images to generate (1-9, default: 1)
• seed: Random seed for reproducible results (integer)
• prompt_optimizer: Enable automatic prompt enhancement (boolean)
• enable_base64_output: Return Base64 instead of URLs (boolean)
• enable_sync_mode: Wait for generation to complete before returning (boolean)

Pricing

• $0.0035 per image
• Generate multiple images in one request for efficient batch processing
• Total cost = $0.0035 × number of images generated
• Example: Generating 9 variations costs only $0.0315

Output Format

Generations return as:

• URLs (default): Direct links to generated images hosted on WaveSpeedAI (valid for 24 hours)
• Base64 (optional): Encoded image data for direct embedding in applications

Response includes:

• Unique request ID for tracking
• Generation status (created, processing, completed, failed)
• Output array with generated image URLs or Base64 data
• NSFW content detection flags for each image
• Creation timestamp
• Success/failure counts

Best Practices

• Be Descriptive: More detailed prompts generally produce better results
• Use Prompt Optimizer: Enable it if you’re new to AI image generation
• Generate Multiple Variations: Use num_images > 1 to explore different interpretations
• Iterate with Seeds: Find a good result, then use its seed to create variations
• Choose Appropriate Dimensions: Select dimensions that match your use case
• Test Different Styles: Experiment with artistic styles in your prompts
• Save Successful Prompts: Keep a library of prompts that work well for future use

Example Prompts

Photorealistic: “A professional product photo of a luxury watch on a marble surface, studio lighting, shallow depth of field, commercial photography style”

Artistic: “An impressionist oil painting of a Parisian café in autumn, warm colors, loose brushstrokes, golden afternoon light”

Conceptual: “A futuristic cityscape at night with neon lights, flying vehicles, cyberpunk aesthetic, rain-slicked streets, dramatic perspective”

Character: “A friendly robot character with a round body, expressive LED eyes, metallic blue finish, standing in a modern laboratory, 3D render style”

Related Models

Also available on WaveSpeedAI:

• minimax/image-01/image-to-image - Transform existing images with text prompts

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "size": "1024*1024",
  "num_images": 1,
  "prompt_optimizer": false
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/minimax/image-01/text-to-image" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters