Wan 2.5 Text to Image API

The next-generation Wan 2.5 text to image API delivers state-of-the-art visuals with enhanced bilingual text support, semantic accuracy, and flexible aspect ratios.

Configure Request

Response

Click "Generate" to see results

Wan 2.5 Text to Image API: Precision meets creativity

Generate stunning 1440x1440 visuals with the Wan 2.5 text to image API. Experience breakthrough layout stability, accurate Chinese/English text rendering, and superior lighting control.

What can you build with the Wan 2.5 text to image API?

Global marketing assets

Create cross-market ad visuals using the Wan 2.5 text to image API, famous for its ability to render accurate text in both English and Chinese without artifacts.

Start creating

Complex conceptual art

Wan 2.5 T2I excels at visual reasoning, ensuring complex prompts with multiple subjects and specific lighting conditions are respected faithfully.

Explore concepts

Scalable content production

Leverage EvoLink's unified access to the Wan 2.5 text to image API for high-concurrency batch generation, perfect for A/B testing creative variations.

Scale up

Why developers choose Wan 2.5 T2I

The Wan 2.5 text to image API outperforms previous iterations by removing resolution rigidity and significantly improving semantic understanding for complex layouts.

Superior Text Rendering

Unlike competitors, Wan 2.5 handles in-image typography for posters and UI designs with exceptional clarity in multiple languages.

Flexible Aspect Ratios

Break free from fixed squares. Generate wide panoramas or tall mobile assets with aspect ratios ranging from 1:4 to 4:1.

Enhanced Visual Reasoning

The model understands physics and spatial relationships better, reducing limb errors and floating objects in realistic generations.

How to integrate Wan 2.5 text to image API

Streamline your creative workflow in three simple steps.

Step 1 — Configure your payload

Set your endpoint to Wan 2.5 text to image API. Define your prompt, negative prompt, and desired aspect ratio (e.g., 16:9 or 9:16).

Step 2 — Optimize parameters

Adjust the seed for reproducibility and select image count (1-4). Wan 2.5 supports resolutions up to roughly 2 Megapixels total area.

Step 3 — Execute and retrieve

Send the request via EvoLink. Receive high-fidelity URLs or Base64 data instantly, ready for your application or post-processing pipeline.

View API Docs

Core capabilities

Unlocking the power of Wan 2.5

Core

Wan 2.5 text to image API

Direct access to the latest architecture for high-fidelity synthesis.

Text

Bilingual Typography

Renders legible Chinese and English text directly on images.

Formats

Unlimited Aspect Ratios

Supports extreme dimensions (e.g., 768x2700) within pixel limits.

Intelligence

Visual Reasoning

Deep understanding of prompt logic, lighting, and physics.

Quality

High Resolution

Native generation up to 1440x1440 equivalent area.

Style

Style Versatility

Seamlessly switches between anime, photorealism, and oil painting.

Wan 2.5 T2I vs other models

Choose the right tool for your generation needs

Model	Duration	Resolution	Price	Strength
Wan 2.5 Text to Image API	N/A	Flex (up to 1440p area)	Token-based / Image	Best-in-class bilingual text, strong prompt adherence, flexible ratios.
Wan 2.1 Image-to-Image	N/A	1024x1024 base	Token-based	Good for reference-based restyling, though less precise with text.
Nano Banana 2	N/A	1024px fixed	Per image	Standard generation, lacks the specific bilingual text capabilities of Wan.

Frequently Asked Questions

Everything you need to know about the product and billing.

Wan 2.5 offers significantly improved prompt adherence, native support for complex English/Chinese text rendering, and removes the strict single-side resolution limits found in earlier versions.

The Wan 2.5 text to image API supports a total pixel area between 768x768 and 1440x1440. You can customize dimensions freely (e.g., 768x2700) as long as they fit the total pixel budget.

Yes, one of the standout features of the Wan 2.5 text to image API is its ability to render legible and stylistically accurate text strings in both Chinese and English.

Absolutely. Its high fidelity, stable anatomy generation, and lighting control make it ideal for commercial advertising, game asset creation, and design mockups.

Simply use your EvoLink API key. Our unified interface routes your requests to the optimal Wan 2.5 endpoint, ensuring high availability and competitive pricing.

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 text prompts. Supports text-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-text-to-image

Image generation model name.

Examplewan2.5-text-to-image

promptstringRequired

Prompt describing the image to be generated.

Notes

Limited to 2000 tokens

ExampleA cat playing in the grass

sizestringOptional

Size of the generated image (pixel format only).

Notes

Pixel range: 768x768 to 1440x1440
Aspect ratio range: [1/4, 4]

Example1280x1280

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

prompt_extendbooleanOptionalDefault: true

Whether to enable intelligent prompt rewriting.

Notes

When enabled, a large language model will optimize the prompt
Effective for prompts that lack detail or are too simple

Exampletrue

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-text-to-image",
  "prompt": "A cat playing on the grass",
  "size": "1280x1280"
}

Response Example

{
  "created": 1757165031,
  "id": "task-unified-1757165031-uyujaw3d",
  "model": "wan2.5-text-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,
    "user_group": "default"
  }
}