alibaba/qwen-image-edit/image-to-image

Name: Qwen Image Edit
Author: Alibaba

Qwen Image Edit by Alibaba - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.

Input

Prompt(string)

The prompt to generate the image with

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

The URL of the image to edit.

This field is required.

Guidance scale(number)

020

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. Range: 0 to 20.

Num Inference Steps(integer)

250

The number of inference steps to perform. Range: 2 to 50.

Strength(number)

0.011

Strength of the image-to-image transformation. Lower values preserve more of the original image. Range: 0.01 to 1.

Output Format(string)

The format of the generated image. Allowed values: jpeg, png.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Seed(integer)

The same seed and the same prompt given to the same version of the model will output the same image every time.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDalibaba/qwen-image-edit/image-to-image

Input Schema

8 parameters · 2 required · 6 optional

Parameter	Type	Required	Description
`image`	string	Required	The URL of the image to edit.
`prompt`	string	Required	The prompt to generate the image with
`seed`	integer	Optional	The same seed and the same prompt given to the same version of the model will output the same image every time.
`strength`	number	Optional	Strength of the image-to-image transformation. Lower values preserve more of the original image. · Min: 0.01 · Max: 1 · Default: 0.94
`aspect_ratio`	string	Optional	The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16
`output_format`	string	Optional	The format of the generated image. · Options: jpeg, png · Default: "png" jpegpng
`guidance_scale`	number	Optional	The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. · Min: 0 · Max: 20 · Default: 4
`num_inference_steps`	integer	Optional	The number of inference steps to perform. · Min: 2 · Max: 50 · Default: 30

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "alibaba/qwen-image-edit/image-to-image",
  "image": "https://static.sandbase.ai/examples/alibaba/qwen-image-edit/image-to-image/input_image_0.png",
  "prompt": "Change bag to apple macbook",
  "strength": 0.94,
  "output_format": "png",
  "guidance_scale": 4,
  "num_inference_steps": 30
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Qwen Image Edit

API README

Qwen Image Edit

Qwen Image Edit is the Qwen Image route for instruction-driven image revision. It uses Qwen’s combined visual-semantic and appearance modeling to interpret subjects, relationships, typography, spatial structure, and surface detail as a connected composition, giving this exact route a clearer production purpose than a generic image request. The explicit image-to-image path emphasizes broad visual reinterpretation anchored by a source rather than a narrowly masked correction.

Use Qwen Image Edit when the project specifically requires a controlled change to supplied imagery. State the creative goal, then define composition, viewpoint, wording, materials, lighting, and finish; for edits, explicitly separate the intended transformation from identity, layout, or regions that must remain stable.

Highlights

Qwen Image Semantic content editing. Changes object identity, scene meaning, viewpoint, or style through natural language.
Qwen Image Appearance-level revision. Modifies local color, texture, text, or material while preserving surrounding context.
Qwen Image Chinese and English text editing. Adds, removes, or replaces bilingual wording in designed imagery.
Directed image-to-image conversion. Reinterprets a supplied image as a new visual while retaining the source cues named in the brief.

Pricing

Configuration	Billing unit	Price
Base generation	Per request	$0.03

When to Use

✅ Good fit	❌ Consider alternatives
The project needs an existing image needs a controlled revision	The intended task belongs to a different media workflow
The available inputs match every required local field	Required source material or usage permission is unavailable
Creative direction can identify subject, style, and delivery	The output must be deterministic at pixel or waveform level
The supported route controls fit the final placement	Delivery requires unsupported formats or dimensions
An asynchronous generated result fits production	A live or frame-synchronous response is mandatory

Prompt Guide

Write the request as a production brief. Identify the subject or source, state the intended result, describe composition and visual or vocal character, then list exact preservation and delivery constraints. For edits, explicitly separate what must change from what must remain unchanged.

{
  "prompt": "A polished editorial composition with a clear subject, controlled lighting, balanced layout, and precisely preserved details",
  "image": "https://example.com/reference.jpg",
  "seed": 1,
  "strength": 0.94,
  "aspect_ratio": "21:9"
}

Technical Specs

Spec	Value
Model ID	`alibaba/qwen-image-edit/image-to-image`
Input fields	`seed` (integer)<br>`image` (string)<br>`prompt` (string)<br>`strength` (number; 0.01–1)<br>`aspect_ratio` (string; `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`)<br>`output_format` (string; `jpeg`, `png`)<br>`guidance_scale` (number; 0–20)<br>`num_inference_steps` (integer; 2–50)
Required input	`prompt`, `image`
Output fields	`url`, `content_type`
Execution	Asynchronous job

Related Models

alibaba/qwen-image-2
alibaba/qwen-image-2/edit
alibaba/qwen-image-2/pro