Qwen Image Text To Image 2512 API Documentation

Qwen Image Text To Image 2512 API Documentation

Playground

Qwen Image 2512 is Qwen’s latest text-to-image model with enhanced prompt understanding, superior text rendering, and versatile aspect ratio support. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Qwen Image 2512 is latest text-to-image generation model from the Qwen AI family. It excels at understanding natural language prompts and producing high-quality images with exceptional text rendering capabilities — perfect for creating posters, signage, logos, and designs requiring readable text.

Why Choose This?

• Superior text rendering Accurately generates legible text within images, including multiple languages, fonts, and layouts. Ideal for designs requiring readable text elements.

• Enhanced prompt understanding Interprets complex, detailed prompts with better comprehension of subject relationships, spatial arrangements, and stylistic nuances.

• Flexible sizing Supports custom width and height configurations for various use cases — social media, presentations, print, and web content.

• Consistent quality across styles Produces high-quality results whether you’re creating photorealistic images, illustrations, concept art, or abstract designs.

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

Parameters

Output Format Options

• jpeg — Smaller file size, good for photos and web use
• png — Lossless quality, supports transparency, best for graphics with text
• webp — Modern format with better compression, good browser support

How to Use

1. Write your prompt — describe the image you want, including style, composition, lighting, and mood.
2. Adjust size — set width and height for your desired dimensions.
3. Set seed — use -1 for random results, or specify a number for reproducibility.
4. Choose output format — select jpeg, png, or webp based on your needs.
5. Run — click Run, preview the result, and iterate if needed.

Pricing

Simple flat-rate pricing regardless of image size.

Best Use Cases

• Marketing and Advertising — Create eye-catching visuals with text for ads, posters, and promotional materials.
• Social Media Content — Generate engaging images optimized for different platform formats.
• Product Design — Visualize concepts, mockups, and packaging designs with integrated text.
• Branding and Identity — Design logos, signage, and branded visuals with readable text elements.
• Editorial and Publishing — Produce illustrations, cover art, and visual content for articles.

Pro Tips

• Be specific in your prompts — include subject, style, lighting, camera angle, and atmosphere for best results.
• For text in images, explicitly specify the exact text, font style, and placement (e.g., “poster with the text SUMMER SALE in bold red letters at the top”).
• Use the same seed with the same prompt to reproduce identical outputs.
• This model is specifically optimized for generating readable text within images.

Notes

• Please ensure your prompts comply with content guidelines. If an error occurs, review your prompt and try again.

Related Models

• Qwen Image Edit 2511 — Image editing model from the Qwen family for precise visual modifications.
• Qwen Image Edit Plus — Enhanced editing model with dual-mode editing and precise bilingual text editing.
• Qwen Image Edit 2511 LoRA — LoRA-enabled version for custom style and character fine-tuning.

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",
  "output_format": "jpeg"
}
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/text-to-image-2512" \
  -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