Available now

Wan 2.7 Image: text to image

By Alibaba

Alibaba's Wan 2.7 Image creates up to five images from a prompt in English or Chinese and edits images from one to four references.

Model ID
Maker
Alibaba

Input

Fields marked * are required. Review the price before generating.

Text prompt describing the desired output. Supports Chinese and English.

Example prompt. Edit it or write your own.

This model reads prompts in English or Chinese.

Number of images to generate (1-5).

Additional settings

Content to avoid in the generated image. Max 500 characters.

Random seed for reproducibility (0-2147483647).

Estimated total$0.05

You sign up first. Your settings are kept.

About this model

Overview

Wan 2.7 Image takes a prompt of up to 2000 characters and a negative prompt of up to 500, and renders in square, portrait or landscape presets.

The edit mode takes one to four images in order; call them image 1 to image 4 in the prompt to say which part comes from where. Prompt expansion is on by default in this mode.

What you can build

  • Sets of up to five options from one prompt
  • A product placed into a scene from another photo
  • An outfit or object swapped between photos
  • Prompts written in Chinese or English

Prompting tips

  • In the edit mode, refer to inputs by number, such as "put the hat from image 2 on the person in image 1".
  • Keep the negative prompt short and concrete: blur, text, extra people.

What to check

Check object counts, layout and lettering at delivery size; compare preserved details after editing.

Inputs

  • Prompt (required): Text prompt describing the desired output. Supports Chinese and English.
  • Negative Prompt (optional): Content to avoid in the generated image. Max 500 characters.
  • Image Size (optional): Output image size. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Number of Images (optional): Number of images to generate (1-5).
  • Seed (optional): Random seed for reproducibility (0-2147483647).
  • Output Format (optional): The format of the generated images. Options: jpeg, png, webp.

Output and limits

  • Image sizes: Square HD (1024×1024), Square (512×512), Portrait 4:3 (768×1024), Portrait 16:9 (576×1024), Landscape 4:3 (1024×768), Landscape 16:9 (1024×576).
  • File formats: JPEG, PNG, WEBP.
  • Up to 5 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 1 image: $0.05 / image