Meta Muse Image Text To Image API Documentation

Meta Muse Image Text To Image API Documentation

Playground

Meta Muse Image Text-to-Image generates high-quality images from text prompts for creative visuals, concept art, marketing assets, social content, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Meta Muse Image Text-to-Image generates high-quality images from text prompts. Describe the subject, composition, lighting, style, and visual details, then choose an aspect ratio and output format to create the final image.

Why Choose This?

• Text-to-image generation
  Generate images directly from natural-language prompts.

• Simple creative workflow
  Provide a prompt, select layout settings, and generate an image in one request.

• Flexible aspect ratio
  Choose the output aspect ratio based on your target format.

• Multiple output formats
  Select the image format that fits your workflow.

• Low-cost image generation
  Generate images at a fixed price per image.

Parameters

How to Use

1. Write your prompt — Describe the subject, environment, style, lighting, and composition.
2. Choose aspect ratio — Select the layout that matches your target format.
3. Choose output format — Select the image format for the generated output.
4. Submit — Generate the final image and retrieve the output URL.

Pricing

Pricing is fixed at $0.011 per image.

Best Use Cases

• Creative image generation — Create original images from text prompts.
• Concept art — Explore characters, scenes, objects, and visual styles.
• Marketing visuals — Generate images for campaigns, ads, and social media.
• Product concepts — Create visual ideas for product presentation and creative testing.
• Fast prompt iteration — Test different visual directions at low cost.

Pro Tips

• Use clear prompts with subject, composition, lighting, style, and background details.
• Choose 1:1 for square images and other aspect ratios for platform-specific layouts.
• Keep the prompt focused on one main scene or subject for better results.
• Add camera, lighting, and mood details when you need a more polished visual style.
• Use webp when you want compact web-friendly image output.

Related Models

• Meta Muse Image Text-to-Image — Generate images from natural-language prompts.
• Meta Muse Image Edit — Edit images with text instructions.

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",
  "aspect_ratio": "1:1",
  "output_format": "webp"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/meta/muse-image/text-to-image" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters