Wan Image API

The Wan Image API is a single integration for both text-to-image creation and image editing. It supports Chinese and English prompts, task-based processing, and configurable output sizes, so teams can move from ideation to production assets without swapping tools. Capabilities, limits, and pricing can vary by model and region, so treat the dashboard and API responses as the source of truth.

Model Type :

Wan 2.5 Text to Image Wan 2.5 Image to Image

Prompt

Transform this image into a watercolor painting

Parameters

Estimated Cost (per image)

2 Credits

Total = Base Price x Count (n)

Sample Result

No sample available

Prompt

0 (suggested: 2,000)

Input Images *

Upload up to 2 images (max 10MB each)

Click to upload or drag and drop

Supported formats: JPEG, JPG, PNG, BMP, WEBP
Maximum file size: 10MB; Maximum files: 2

Count

Click Generate to see preview

History

Max 20 items

0 running · 0 completed

Your generation history will appear here

Wan Image API for scalable text-to-image and editing

Generate fresh visuals from prompts or refine existing images with the Wan Image API. Use it for campaign creatives, product imagery, and fast iteration pipelines where consistent output size, prompt control, and reliable task handling matter.

Hero showcase of image generation API feature 1

What can you build with the Wan Image API?

Localized marketing creatives

Create banners, posters, and social ads using the Wan Image API, then localize quickly with Chinese or English prompts. Because the same prompt structure works across markets, teams can keep brand tone consistent while testing multiple layouts and messages for different regions.

Start creating

Marketing showcase of image generation API feature 2

Product and catalog visuals

Use the Wan Image API to generate product scenes from scratch or refine existing shots with edits. It is a practical choice for catalog teams that need consistent framing, controllable sizes, and a steady flow of alternatives for merchandising reviews.

Explore concepts

Catalog showcase of image generation API feature 3

Creative iteration pipelines

Power iterative workflows with the Wan Image API by running task-based jobs and generating multiple candidate images per request. Teams can compare options quickly, reuse prompts across projects, and scale production without rebuilding the integration for every campaign.

Scale up

Workflow showcase of image generation API feature 4

Why teams choose the Wan Image API

The Wan Image API balances creative flexibility with production control, so teams can build consistent assets at speed without changing tools between text-to-image and editing modes.

Unified integration

One API surface for creation and editing keeps pipelines simple.

Prompt control

Chinese and English prompts keep instructions clear and repeatable.

Production readiness

Task-based jobs and size controls fit real delivery workflows.

How to integrate the Wan Image API

A straightforward flow from prompt to production assets.

Choose mode and inputs

Pick text-to-image or image editing, then supply a prompt and optional reference images depending on the task.

Submit a task

Send the request and receive a task id. Task-based processing is used for Wan Image API generation jobs.

Retrieve results

Poll the task status, then download image URLs and store them in your asset pipeline.

View API Docs

Core capabilities of the Wan Image API

Documented controls that help teams ship consistent creative

Language

Chinese and English prompt support

The Wan Image API accepts prompts in Chinese and English, making it practical for global teams. A clear, structured prompt improves consistency across campaigns and helps teams reuse prompt templates without rewriting everything for each region.

Control

Negative prompt guidance

For supported models, the Wan Image API allows negative prompts to remove unwanted artifacts or styles. Documented limits allow up to 2000 characters for prompts and 500 characters for negative prompts, which helps keep instructions readable and controlled.

Editing

Multi-image fusion

The Wan Image API image-editing mode supports multi-image input for fusion tasks. This helps teams combine product shots and backgrounds while keeping the main subject consistent across variations.

Input

Input image requirements

For image editing, supported formats include JPEG, JPG, PNG, BMP, and WEBP. Input images should be between 384 and 5000 pixels on each side and no larger than 10 MB, which helps maintain quality without excessive latency.

Formats

Output size and aspect ratio

You can set output size with a width x height parameter. For Wan 2.5 image editing, total pixels are documented between 768x768 and 1280x1280, with aspect ratios between 1:4 and 4:1. If size is omitted, the default is 1280x1280.

Workflow

Async task workflow

Wan Image API generation runs as tasks. You submit a request, receive a task id, and poll for completion. Task ids are documented as valid for 24 hours, so production systems should retrieve and store results promptly.

Frequently Asked Questions

Everything you need to know about the product and billing.

The Wan Image API is a unified interface that supports both text-to-image creation and image editing workflows. It is designed for production teams that need repeatable prompts, controllable outputs, and consistent task handling. You can generate new scenes from a prompt or refine existing images using edits, while keeping the same integration surface. Because features can vary by model and region, always confirm capabilities and limits in your EvoLink dashboard and the API responses before you standardize a workflow.

Yes. The Wan Image API includes text-to-image generation and image editing modes. Text-to-image workflows are task-based and support prompt input, while image editing workflows accept reference images and allow fusion or controlled changes. This makes it easy to move from concept generation to refinement without switching tools. For the latest model list and mode availability, check your dashboard and the official API docs, since capabilities can change by region or plan.

The Wan Image API supports prompts in Chinese and English. This is useful for global teams that need to localize creative quickly. For best results, keep prompts structured with subject, style, lighting, and background, and reuse a shared prompt template across regions to maintain consistency. Documented prompt limits include up to 2000 characters for prompts and up to 500 characters for negative prompts when supported, so you have room to be specific without losing clarity.

The Wan Image API image editing mode supports multiple reference images for fusion tasks, which lets you combine elements from different sources. This is useful for merging a product shot with a lifestyle background or blending props into a new scene. The exact count can vary by model, so confirm the current limit in the API docs for your endpoint. Keep one primary image as the anchor and add secondary images only for the elements you want to borrow.

For image editing, supported formats include JPEG, JPG, PNG, BMP, and WEBP. Input images should be between 384 and 5000 pixels on each side and no larger than 10 MB. PNG alpha channels are not supported, so treat PNG inputs as flat images. These constraints help balance output quality with predictable latency. Always verify current limits in your EvoLink dashboard and the API docs because they can evolve with new releases.

The Wan Image API lets you set output resolution using a width x height parameter. For Wan 2.5 image editing, documented total pixels are between 768x768 and 1280x1280, and aspect ratios must be between 1:4 and 4:1. If you do not provide size, the default is 1280x1280. For multi-image input, aspect ratio may follow the last image. Check the API docs for model-specific changes before production deployment.

Yes. Text-to-image generation is task-based in Wan 2.5 and earlier, and image editing also runs as tasks. You submit a request, receive a task id, then poll the task endpoint until it completes. Task ids are documented as valid for 24 hours, so retrieve results promptly and store them in your asset pipeline. In production, use backoff for polling to avoid unnecessary retries while keeping acceptable latency.

The Wan Image API allows multiple outputs per request, which is useful for A/B testing and creative review. For Wan 2.5 image editing, the documented output count parameter n can be between 1 and 4, and the number of images impacts cost directly. A practical workflow is to generate three or four candidates in the first pass, choose the strongest, and then run smaller refinement batches to control spend while keeping quality high.

API Reference

Select endpoint

Authentication

All APIs require Bearer Token authentication.

Header

Authorization: 
Bearer YOUR_API_KEY

Get API Key

POST

/v1/images/generations

Generate Image

Create an image generation task using reference images. Supports image-to-image generation mode.

Asynchronous processing mode, use the returned task ID to .

Generated image links are valid for 24 hours, please save them promptly.

Request Parameters

modelstringRequiredDefault: wan2.5-image-to-image

Image generation model name.

Examplewan2.5-image-to-image

promptstringRequired

Prompt describing how to transform the input image.

Notes

Limited to 2000 tokens

ExampleTransform this image into a watercolor painting

nintegerOptionalDefault: 1

Number of images to generate.

Value	Description
1-4	Batch generation supported

Notes

Pre-charged based on n value, actual charge based on generated count

Example1

image_urlsarrayRequired

Reference image URL list for image-to-image transformation.

Notes

Max 2 images per request
Max size: 10MB per image
Formats: .jpeg, .jpg, .png (no transparent), .bmp, .webp
Resolution: width and height range [384, 5000] pixels
URLs must be directly accessible by the server

Examplehttps://example.com/image1.png

callback_urlstringOptional

HTTPS callback address after task completion.

Notes

Triggered on completion, failure, or cancellation
Sent after billing confirmation
HTTPS only, no internal IPs
Max length: 2048 chars
Timeout: 10s, Max 3 retries

Examplehttps://your-domain.com/webhooks/image-task-completed

Request Example

{
  "model": "wan2.5-image-to-image",
  "prompt": "Transform this image into a watercolor painting",
  "image_urls": [
    "https://example.com/image1.png"
  ]
}

Response Example

{
  "created": 1757165031,
  "id": "task-unified-1757165031-uyujaw3d",
  "model": "wan2.5-image-to-image",
  "object": "image.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 45
  },
  "type": "image",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 1.2,
    "user_group": "default"
  }
}