Qwen Image Text To Image API Documentation

Qwen Image Text To Image API Documentation

Playground

Qwen-Image is a 20B MMDiT next-gen text-to-image model that generates images from text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Qwen-Image is a 20B MMDiT-based text-to-image generation model, especially strong at native text rendering in both English and Chinese. It is a powerful creative tool for posters, comics, and visual storytelling, while also excelling at general image generation from photorealism to anime.

Why it looks great

• SOTA text rendering: Rivals GPT-4o in English and best-in-class for Chinese.
• In-pixel text generation: Text is fully integrated into the image (no overlays).
• Bilingual typography: Handles diverse fonts, styles, and complex layouts.
• General image capability: Excels across styles—photorealistic, anime, impressionist, minimalist.

Limits and Performance

• Max resolution per job: up to 1536 × 1536 pixels
• Custom size: manually set width & height
• Output formats: JPEG / PNG / WEBP
• Processing speed: ~5–8 seconds per image (depends on size & queue)
• Input prompt: supports detailed, multi-line descriptions

Price

Only $0.02 per image!!!

How to Use

1. Write a prompt describing the image (can include embedded text).
2. Adjust size (width & height, up to 1536×1536).
3. Set a seed for reproducibility.
4. Choose output_format.
5. Run the job and download the generated image.

Pro tips for best quality

• For poster design, explicitly describe font style, placement, and mood.
• For bilingual text, specify both Chinese and English in the prompt.
• Use consistent seeds to regenerate similar layouts with slight variations.
• Keep height:width ratio balanced for best typography results.

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",
  "seed": -1,
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/qwen-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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 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) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters