Available now

Qwen Image 2.1 Turbo: image editing

By Alibaba

Upload a reference and give Qwen Image 2.1 Turbo a focused edit, such as changing the background while keeping the product and its label. Choose an output size or leave it on Auto.

Model ID
Maker
Alibaba
Added
October 12, 2026

Model id

Use this in every request
qwen-image-2.1-turbo/edit

This model has other modes with their own ids: qwen-image-2.1-turbo.

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen-image-2.1-turbo/edit",
  "input": {
    "prompt": "Replace the white backdrop with pale blue. Keep the product, the printed label and the existing shadow.",
    "image_urls": [
      "https://example.com/input.png"
    ]
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "qwen-image-2.1-turbo/edit", "quote_id": "QUOTE_ID", "input": {"prompt":"Replace the white backdrop with pale blue. Keep the product, the printed label and the existing shadow.","image_urls":["https://example.com/input.png"]}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for qwen-image-2.1-turbo/edit
NameTypeDescription
promptrequiredstring
Editing instruction in Chinese or English; recommended maximum 4,500 tokens.
enable_thinkingboolean
Defaults to true when prompt rewriting is enabled, otherwise false. Requires Prompt Extend.
image_urlsrequiredarray of image URLs
1–10 public HTTP(S) reference images in order. JPG, JPEG, PNG, BMP, TIFF, WEBP or GIF; up to 10 MB each, dimensions 1–8000 pixels, long-to-short side ratio at most 10:1.
ninteger
Choose 1 to 6 output images.

Default: 1

prompt_extendboolean
Prompt Extend

Default: true

prompt_extend_modestring (enum)
Only direct prompt enhancement is supported for Image Edit.

Default: direct

One of: direct

seedinteger
Seed
sizestring (enum)
Choose a preset output size. Auto lets the model choose the size.

Default: auto

One of: auto, 1024*1024, 2048*2048, 1280*720, 1920*1080, 720*1280, 1080*1920, 1280*960, 960*1280, 1536*1024, 1024*1536

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt
"outputs": [
  { "type": "image", "url": "https://…", "mime_type": "image/png", "thumbnail_url": "https://…" }
]

Pricing

  • per image$0.03/ image

The exact charge for your input comes from a quote. How charges settle

API docs

About this model

Overview

The generation form gives you preset canvas sizes and a transparent background option. The edit form takes reference images and follows a separate instruction.

What you can build

  • Transparent graphics for a layout
  • Product compositions from written briefs
  • Edits with details carried over from a reference

Prompting tips

  • Describe the framing and light before adding secondary props.
  • For an edit, name the object to change and the details to retain.
  • For a cutout, turn on Transparent background: prompt rewriting is switched off for that request and the price stays the same.

What to check

Inspect the handle, rim, shadow and any requested lettering at full size. For edits, compare the result with each reference: object shape, face details and branding can change. Keep the prompt, selected mode, size and seed with the chosen image.

Questions

Can I use the same settings for generation and editing?
The operations share some controls, but their inputs and size options differ. Text-to-image requires a prompt; editing also requires reference images. Choose the operation before copying its API inputs.

Inputs

  • Prompt (required): Editing instruction in Chinese or English; recommended maximum 4,500 tokens.
  • Enable Thinking (optional): Defaults to true when prompt rewriting is enabled, otherwise false. Requires Prompt Extend.
  • Images (required): 1–10 public HTTP(S) reference images in order. JPG, JPEG, PNG, BMP, TIFF, WEBP or GIF; up to 10 MB each, dimensions 1–8000 pixels, long-to-short side ratio at most 10:1.
  • Number of Images (optional): Choose 1 to 6 output images.
  • Prompt Extend (optional)
  • Prompt Extend Mode (optional): Only direct prompt enhancement is supported for Image Edit. Options: direct.
  • Seed (optional) From 0 to 2147483647.
  • Size (optional): Choose a preset output size. Auto lets the model choose the size. Options: auto, 1024*1024, 2048*2048, 1280*720, 1920*1080, 720*1280, 1080*1920, 1280*960, 960*1280, 1536*1024, 1024*1536.

Output and limits

  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • per image: $0.03 / image