Qwen Image 2.0 Pro Edit

Qwen Image 2.0 Pro Edit

Playground

Qwen Image 2.0 Pro Edit is a professional-grade image editing model with superior quality and advanced instruction understanding. Up to 2k. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Qwen Image 2.0 Pro Edit is an image-editing model for transforming existing images with natural-language instructions. Upload 1 to 3 reference images, describe the edit you want, and generate a refined image while preserving the visual context from your inputs.

Why Choose This?

• Instruction-based image editing Modify, restyle, or enhance uploaded images using a simple text prompt.

• Multi-image input Supports up to 3 input images for edits, references, or visual context.

• Strong prompt understanding Follows detailed Chinese or English editing instructions for targeted changes.

• High-resolution workflow Supports images from 384 to 3072 pixels on each dimension, with output up to 2k.

• Reproducible results Set a seed when you need repeatable generations.

Parameters

How to Use

1. Upload your image inputs - add 1 to 3 images to edit or use as references.
2. Write your prompt - describe the change, style, object, background, or composition you want.
3. Set seed (optional) - use a fixed seed for reproducible results.
4. Run - submit the request and download the generated image.

Pricing

Best Use Cases

• Photo retouching - Adjust appearance, lighting, composition, or scene details.
• Creative edits - Transform style, mood, clothing, backgrounds, or objects.
• Product visuals - Refine product shots or create alternate presentation styles.
• Character and portrait edits - Preserve identity while changing details or aesthetics.
• Reference-guided edits - Use multiple images to provide context for the final output.

Pro Tips

• Use clear, specific edit instructions instead of broad prompts.
• Upload only the images needed for the edit; the model supports a maximum of 3 input images.
• Mention what should stay unchanged when preservation matters.
• Use a fixed seed when comparing prompt variations.
• For final production quality, use the Pro model; for lower-cost iteration, use the standard model.

Notes

• prompt and images are required.
• images accepts 1 to 3 images.
• Each input image should be 384-3072px on each dimension.
• Ensure image URLs are publicly accessible when using URL inputs.
• Ensure your prompts and images comply with content guidelines.

Related Models

• Qwen Image 2.0 Text-to-Image - Standard text-to-image generation.
• Qwen Image 2.0 Pro Text-to-Image - Pro text-to-image generation.
• Qwen Image Edit Plus - Image editing 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",
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "seed": -1
}
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-2.0-pro/edit" \
  -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