Alibaba: 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" }'
Pricing
Official price is the model maker's public baseline. TokenLab price is what you pay for this model on TokenLab.
Image editing
per image- Official price
- $0.0122
- Official
- $0.0122
- Discount
- —
| Official priceper image | Officialper image | Discount | |
|---|---|---|---|
| Image editing | $0.0122 | $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
