Alibaba Cloud: Qwen-Image-Edit-2511
qwen-image-edit-2511- Price
- From $0.0122
- Modalities
- Image
About Qwen-Image-Edit-2511
Qwen-Image-Edit-2511 is Alibaba's Qwen team image editing model: you give it one or more images and a written instruction, and it returns an edited image. The 2511 release is an update to earlier Qwen-Image-Edit versions that targets image drift, character consistency, geometric reasoning, and industrial design output, and it folds in popular community LoRA abilities. The weights are published under Apache 2.0.
Where it works well
- Keeps a person or character recognisable across edits, including photos with several people, which the maker lists as a main improvement over the previous release.
- Reduces image drift, so areas you did not ask to change stay close to the source image.
- Takes more than one input image in a request, which suits combining a subject with a background or a second person.
- Handles geometric and industrial-design edits better than the earlier version, according to the Hugging Face model card.
When to choose another model
- It edits existing images only; to create a picture from a text prompt alone, pick a text-to-image model.
- It does not split an image into editable layers; Qwen-Image-Layered is the model for that workflow.
- Every request needs a source image and a written instruction, and a vague instruction gives less predictable edits.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Image editingTokenLab endpointPOST/v1/images/generationscurl -X POST "https://api.tokenlab.sh/v1/images/generations" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{ "operation": "image-to-image", "model": "qwen-image-edit-2511", "prompt": "A minimalist product photo of matte black headphones on a soft blue background.", "image_url": "https://example.com/source.png" }'
Parameters
Image editing
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
cfg_scale | ≥ 1, ≤ 20 | Not provided | Optional guidance control from 1 to 20 in increments of 0.01. cfg_scale requires a compatible delivery path and targets the same control as guidance_scale on that path. If both are supplied, their values must be equal. No shared omitted-value default is asserted. |
guidance_scale | ≥ 1, ≤ 20 | Not provided | Optional guidance scale from 1 to 20. Use increments of 0.01 for shared delivery-path coverage. If cfg_scale is also supplied, use the same value. The omitted default varies by delivery path; one path documents 4.5 while the other does not declare a fixed default. |
height | ≥ 512, ≤ 2048 | 1024 | height is an integer pixel dimension from 512 to 2048; default 1024. Direct width or height requires a compatible delivery path. Use size=WIDTHxHEIGHT for a size string. |
image | Not provided | Not provided | Multipart image file input. Repeat image or image[] for multiple files. All image aliases are combined into one ordered list. The shared declared input range is 1 to 3 images; see the images note for larger input lists. |
image_url | Not provided | Not provided | One source-image URL. All image aliases are combined into one ordered list. The shared declared input range is 1 to 3 images; see the images note for larger input lists. |
image_urls | Inputs: ≥ 1, ≤ 16 | Not provided | A list of source-image URLs, at most 16 entries in that public array. All image aliases are combined into one ordered list. The shared declared input range is 1 to 3 images; see the images note for larger input lists. |
images | Inputs: ≥ 1 | Not provided | Images are combined into one ordered input list. Both delivery paths declare support for 1 to 3 images. One path has a maximum of 3; the other official schema gives no maximum. The public image_urls array accepts up to 16 entries, an additional image_url adds one more input, and multipart uploads accept up to 16 files. A larger model-wide maximum has not been verified. |
n | 1 | 1 | Use an integer. |
negative_prompt | Not provided | Not provided | Optional negative prompt, at most 5000 characters at the public endpoint. Non-empty values from 1 to 5000 characters are accepted by both declared paths. An explicit empty string requires a compatible path. Omit the field when no negative guidance is needed. |
operation | Not provided | Not provided | Not provided |
output_format | png, jpeg, webp | Not provided | Use png, jpeg, or webp. These explicit encodings are available on all declared delivery paths. The omitted encoding varies between PNG and JPEG; set output_format explicitly when it matters. The public endpoint does not accept jpg. |
prompt | Not provided | Not provided | Required edit instruction, 1 to 32000 characters. The public endpoint limits the prompt to 32000 characters; both registered delivery mappings accept that declared range. |
seed | Not provided | Not provided | Optional safe integer seed. The shared declared range is 0 to 9007199254740991; a compatible path also accepts negative safe integers. Omit seed for a random result. No identical result is promised across different delivery paths. |
size | Not provided | 1024x1024 | Use WIDTHxHEIGHT in pixels. The width and height constraints also apply to size. |
steps | ≥ 1, ≤ 50 | Not provided | Use an integer from 1 to 50. Values 1 to 4 require a compatible delivery path. The omitted default varies between 28 and 30, so set steps explicitly when it matters. |
width | ≥ 512, ≤ 2048 | 1024 | width is an integer pixel dimension from 512 to 2048; default 1024. Direct width or height requires a compatible delivery path. Use size=WIDTHxHEIGHT for a size string. |
Fields outside this contract are rejected.
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Image editing
per image- Official price
- $0.0122
- Verified price
- —
- Discount
- —
| Official priceper image | Verified priceper image | Discount | |
|---|---|---|---|
| Image editing | $0.0122 | — | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open Qwen-Image-Edit-2511 in Console with a prompt ready to edit or send.
Help me create an image with qwen-image-edit-2511 using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.
Use cases
Group photo retouching
Change clothing, background, or lighting in a photo with several people while each face stays recognisable from one frame to the next.
Product and industrial design variants
Recolour a product render, swap materials, or adjust the shape of a part from a written instruction, then compare the variants side by side.
Character consistency sets
Place the same illustrated or photographed character in new poses and scenes so a series of images reads as one cast.
Multi-image compositing
Supply a person image and a scene image together and ask for the person to appear in that scene with matching light.
Prompt examples
Change the jacket in the first image to dark green wool, keep the face, pose, and background exactly as they are.
Put the person from image 1 in the kitchen from image 2, standing at the counter, natural window light from the left.
Turn this sketch of a desk lamp into a matte black metal product render on a white backdrop, same camera angle.
FAQ
What does Qwen-Image-Edit-2511 do?
It applies a written instruction to one or more input images and returns the edited result. Typical instructions change clothing, backgrounds, colours, objects, or style while leaving the rest of the picture alone. It is an editing model, so every request needs at least one source image.
What is new in 2511 compared with earlier Qwen-Image-Edit releases?
Alibaba lists less image drift, better character consistency for single subjects and multi-person photos, built-in abilities that previously needed LoRA add-ons, stronger industrial design generation, and improved geometric reasoning. The same instruction should therefore alter the target area and little else.
Can it edit with several reference images at once?
Yes. The model accepts multiple input images with a text prompt, so you can refer to them as image 1, image 2, and so on in the instruction. This is useful for placing a subject into another scene or combining two people in one frame.
Is Qwen-Image-Edit-2511 open source?
The Qwen team publishes the weights on Hugging Face under the Apache 2.0 licence, which allows commercial use. Running it through an API means you do not need to host the model yourself or provide GPUs.
How is it different from Qwen-Image-Layered?
Edit-2511 changes pixels in place based on an instruction. Qwen-Image-Layered instead breaks an image into separate RGBA layers that you then move, resize, or recolour independently. Use Edit-2511 for one-shot changes and Layered when you need to rearrange parts of a design.
How much does Qwen-Image-Edit-2511 cost?
On TokenLab, Qwen-Image-Edit-2511 costs $0.0122 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
Which endpoint should Qwen-Image-Edit-2511 use?
Use https://api.tokenlab.sh/v1/images/edits for Qwen-Image-Edit-2511. The request example below shows the matching code shape.
Which operations does Qwen-Image-Edit-2511 support?
Qwen-Image-Edit-2511 supports Image editing. Select an operation above to see its endpoint and request example.
Compare Qwen-Image-Edit-2511
Sources
Reviewed Oct 2, 2026