Which unusual ratios does Wan 2.7 Image support?

Alongside common ratios, it supports 21:9, 8:1, and 1:8 for extreme wide or tall output.

What does Thinking Mode do?

It adds latency to improve reasoning and composition for complex prompts. Leave it off for fast drafts.

How should I choose 1K, 2K, or 4K?

Validate direction at 1K or 2K, then move to 4K for larger final output. Current page pricing is flat per image.

Does it accept references?

No. This model ID is text-to-image only.

How do I reproduce a result?

Keep seed, prompt, ratio, resolution, and Thinking Mode fixed.

Wan 2.7 Image Text-to-Image API & Playground

About Wan 2.7 Image Text to Image

Try Wan 2.7 Image Text to Image with Chinese prompts, 1K/2K/4K output, extreme wide and tall ratios, optional thinking mode, and API code.

The Playground and API use the same model ID: wan2.7-image/text-to-image. This endpoint accepts text prompts only; reference-image editing uses the separate Image-to-Image route.

Provider: Alibaba
Task: Text-to-Image
References: Not supported
Pricing: 160 Credits / image

Model specifications

These specifications reflect the current Wan 2.7 Image Text to Image request contract.

Reference images: Not supported
Output resolution: 1K2K4K
Aspect ratios: 1:116:94:321:93:49:168:11:8
Enhanced reasoning: Optional thinking mode
Reproducibility: Optional seed
Prompt length: 1-5000 characters
Pricing: Per image: 160 Credits / image

Final cost depends on the output tier and input add-ons. Check the live page price and task record for the final charge.

How to use Wan 2.7 Image Text to Image

Choose the destination and aspect ratio before composing subject, scene, material, light, and text.

Subject

Scene

Camera and light

Describe subject and scene

API Quickstart

Copy a minimal request below. See Docs for parameters, callbacks, task retrieval, and errors.

Endpoint: POST /v1/tasks
Model ID: wan2.7-image/text-to-image

cURL

curl -X POST https://api.hiapi.ai/v1/tasks \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan2.7-image/text-to-image",
  "input": {
    "prompt": "A cinematic product campaign with sharp text",
    "aspect_ratio": "1:1",
    "resolution": "2K",
    "thinking_mode": false
  }
}'

The create request immediately returns a taskId; image generation continues asynchronously.

Read the full API documentation

Wan 2.7 Image Text to Image

Input

More parameters

Generation preferences

Advanced

Output

From product campaigns to detailed scenes

Related image models

Qwen Image 2.0 Pro

Seedream 5.0 Lite

Grok Imagine

About Wan 2.7 Image Text to Image

Model specifications

How to use Wan 2.7 Image Text to Image

Describe subject and scene

API Quickstart

Frequently asked questions

Choose output settings

Validate before integration