Z Image Turbo Image To Image API Documentation

Z Image Turbo Image To Image API Documentation

Playground

Z-Image-Turbo Image-to-Image is a 6 billion parameter model that enhances the quality of reference images (similar to upscaling) in sub-second time. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Z-Image Turbo Image-to-Image is a versatile image generation model that offers a spectrum of modifications — from subtle enhancement to dramatic reimagination. The key is the strength parameter: at low values, it preserves your original image while enhancing quality (similar to upscaling); at high values, it uses your image as loose inspiration for entirely new creations.

This is not a simple editing tool — it’s a generation engine that lets you control exactly how much of the original image to preserve.

Why Choose This?

• Flexible transformation spectrum From near-lossless enhancement to complete style overhaul — all controlled by a single strength slider.

• Quality enhancement mode At low strength, improve image quality, add detail, and sharpen without changing content.

• Creative reimagination mode At high strength, use your image as a reference while dramatically changing style, composition, or subject.

• Custom output sizing Set exact width and height for your output, independent of input dimensions.

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

• Fast and affordable Turbo-optimized for quick generation at just $0.005 per image.

Understanding Strength

The strength parameter is the core of this model. It controls how much the output differs from your input image:

Parameters

How to Use

1. Upload your image — drag and drop or paste a public URL.
2. Write your prompt — describe the desired output or transformation.
3. Set strength — low for enhancement, high for reimagination.
4. Adjust output size — set width and height as needed.
5. Run — submit and download the transformed image.

Pricing

Simple flat-rate pricing regardless of image size or strength setting.

Best Use Cases

• Image Enhancement (strength 0-0.3) — Improve quality, add sharpness, enhance details without changing content.
• Style Transfer (strength 0.5-0.8) — Apply new artistic styles while preserving composition.
• Creative Reimagination (strength 0.8-1.0) — Use images as inspiration for entirely new creations.
• Batch Processing — Affordable pricing enables large-scale image transformation.
• Iterative Design — Quickly explore variations with different strength levels.

Pro Tips

• Start with strength 0.5 to understand how the model interprets your image, then adjust.
• For quality enhancement without content change, use strength below 0.3 with a prompt describing the desired quality.
• For dramatic transformations, use strength above 0.8 with a detailed prompt describing the new style.
• The prompt matters more at higher strength values; at low strength, the image dominates.
• Use the same seed to compare different strength levels on the same image.

Notes

• Output dimensions can differ from input — set width and height to your target size.
• At strength 0, output will be nearly identical to input (useful for testing).
• At strength 1, output may differ significantly while retaining some compositional elements.

Related Models

• Z-Image Turbo Text-to-Image — Generate images from text prompts only.
• Qwen Image Edit 2511 — Precise image editing with text instructions.
• Qwen Image Edit Plus — Enhanced editing with dual-mode and 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",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "size": "1024*1024",
  "strength": 0.6,
  "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/z-image-turbo/image-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