Qwen Image Max Text To Image API Documentation

Qwen Image Max Text To Image API Documentation

Playground

Qwen Image Max is a text-to-image model with high-quality image generation supporting Chinese and English prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Qwen-Image-Max Text-to-Image is flagship text-to-image generation model built on the Qwen-Image architecture. It delivers exceptional image quality with strong prompt adherence, supporting multiple aspect ratios and flexible output formats for professional creative workflows.

Why Choose This?

• Premium image quality Generates highly detailed, coherent images with excellent composition and lighting.

• Strong prompt following Accurately interprets complex descriptions including style, mood, and specific details.

• Multiple aspect ratios Preset options for 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3 to fit any platform.

• Flexible sizing Custom width and height from 256 to 1536 pixels for precise control.

• Multiple output formats Export as JPEG, PNG, or WebP based on your needs.

• Prompt Enhancer Built-in tool to automatically improve your prompts for better results.

Parameters

How to Use

1. Write your prompt — describe the image in detail, including style, lighting, and composition.
2. Select size preset — choose an aspect ratio that fits your needs.
3. Adjust dimensions (optional) — fine-tune width and height if needed.
4. Set seed (optional) — use a specific seed for reproducible results, or -1 for random.
5. Run — submit and download your image.

Pricing

Best Use Cases

• Professional Photography — Generate photorealistic images with studio-quality lighting.
• Fashion & Editorial — Create high-contrast, stylized fashion imagery.
• Marketing & Advertising — Produce polished visuals for campaigns and social media.
• Concept Art — Visualize ideas with detailed, coherent compositions.
• Product Visualization — Generate lifestyle and product imagery.

Pro Tips

• Use the Prompt Enhancer to automatically refine your descriptions.
• Include specific style keywords like “monochrome photography”, “high contrast”, “sharp focus” for better results.
• Describe lighting conditions, camera angles, and mood for more precise outputs.
• Use seed -1 for variety, or set a specific seed when iterating on a concept.
• Choose WebP for smaller file sizes with good quality, PNG for transparency support.

Notes

• Resolution range is 256-1536 pixels for both width and height.
• Seed value -1 generates a random seed each time.
• For best results, write detailed prompts with specific visual attributes.

Related Models

• Qwen-Image-Max Edit — Edit existing images with text instructions.
• Qwen-Image Edit-Plus — Advanced image editing with bilingual text support.

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"
}
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/wavespeed-ai/qwen-image-max/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

Response Parameters

Result Request Parameters

Result Response Parameters