Qwen Image Max Edit
Playground
Try it on WavespeedAI!Qwen Image Max Edit is an AI model for image editing with text prompts, supporting both Chinese and English languages. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Qwen-Image-Max Edit
Qwen-Image-Max Edit is Alibaba’s advanced AI-powered image editing model that transforms images based on text prompts. Supporting both Chinese and English inputs, it delivers precise edits while preserving the original style and quality.
Why Choose This?
-
Bilingual support Edit images using Chinese or English text prompts with equal accuracy.
-
Multi-image input Support up to 6 reference images for complex editing scenarios.
-
Flexible output sizing Maintains first image dimensions by default, or set custom size with preset aspect ratios.
-
Multiple output formats Export as JPEG, PNG, or WebP based on your needs.
-
Strong edit accuracy Understands context and object relationships for coherent modifications.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired edit (max 800 chars) |
| images | Yes | Reference images (1-6 images, 384-5000px) |
| size | No | Preset aspect ratio: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 |
| width | No | Output width in pixels (256-1536, default: first image) |
| height | No | Output height in pixels (256-1536, default: first image) |
| seed | No | Random seed for reproducibility (-1 for random) |
| output_format | No | Output format: jpeg, png, webp (default: jpeg) |
How to Use
- Upload your images — add 1-6 reference images for editing.
- Write your prompt — describe the edit in Chinese or English.
- Set size (optional) — choose a preset or custom dimensions, or leave empty to match first image.
- Set seed (optional) — use a specific seed for reproducible results.
- Choose output format — select jpeg, png, or webp.
- Run — submit and download your edited image.
Pricing
| Output | Cost |
|---|---|
| Per image | $0.07 |
Best Use Cases
- Photo Retouching — Remove objects, fix imperfections, enhance details.
- Creative Editing — Transform scenes, modify elements, add artistic effects.
- E-commerce — Edit product images, change backgrounds, adjust compositions.
- Marketing — Adapt visuals for different campaigns and platforms.
- Localization — Edit on-image text between Chinese and English.
Pro Tips
- Use clear, specific edit instructions for best results.
- Leave size empty to preserve original dimensions, or set custom size for specific output needs.
- Multiple reference images help with complex edits requiring more context.
- Use seed -1 for variety, or set a specific seed when iterating.
- Choose WebP for smaller file sizes, PNG for transparency support.
- Works equally well with Chinese and English prompts.
Notes
- If size is not specified, output matches the first input image dimensions.
- Custom size range is 256-1536 pixels for both width and height.
- Input image resolution must be between 384-5000 pixels.
- Maximum 6 images can be uploaded per edit.
- Prompt length is limited to 800 characters.
- Ensure uploaded image URLs are publicly accessible.
Related Models
- Qwen-Image-Max Text-to-Image — Generate images from text prompts.
- Qwen-Image Edit-Plus — Advanced editing with precise bilingual text editing.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/qwen-image-max/edit" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"seed": -1
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Text prompt describing the desired edit, supports Chinese and English (max 800 characters) | |
| images | array | Yes | [] | 1 ~ 6 items | Reference images for editing (1-6 images, 384-3072px each dimension) |
| size | string | No | - | 256 ~ 1536 per dimension | Image dimensions in width*height format (e.g., 1024*1024, 1280*720) |
| seed | integer | No | -1 | -1 ~ 2147483647 | Random seed for reproducibility (-1 for random, 0-2147483647 for specific seed) |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | Array of URLs to the generated content (empty when status is not completed). |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |