Available now

Wan 2.6 Image: text to image

By Alibaba

Alibaba's Wan 2.6 Image creates an image from a prompt in English or Chinese, or edits a photo and combines up to three reference images from a written instruction.

Model ID
Maker
Alibaba

Input

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

Text prompt describing the desired image. Supports Chinese and English. Max 2000 characters.

Example prompt. Edit it or write your own.

This model reads prompts in English or Chinese.

Optional reference image (0 or 1). When provided, can be used for style guidance. Resolution: 384-5000px each dimension. Max size: 10MB. Formats: JPEG, JPG, PNG (no alpha), BMP, WEBP.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

If not set: matches input image size (up to 1280*1280).

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 2.6 Image takes a prompt of up to 2000 characters and a negative prompt of up to 500. Add one reference image to steer the look; without a size preset, the result follows the reference's size up to 1280 × 1280.

The edit mode takes one to three images, which you refer to by their order in the prompt, and returns one to four images in six preset sizes. Prompt expansion is on by default and rewrites short prompts into fuller ones.

What you can build

  • New scenes in the look of a photo you like
  • Illustrations from a prompt in Chinese or English
  • Square, portrait or landscape images for posts
  • A product placed into a scene from another photo
  • One photo redrawn in the style of another

Prompting tips

  • Use a reference image with a clear style, such as a painting or a strongly graded photo, and describe the new subject in the prompt.
  • Pick a size preset when you need a fixed shape; otherwise the reference decides it.
  • In the edit mode, refer to each upload by its place in the order, such as "the first image", and say what to take from each.
  • Use JPEG or PNG without transparency; images with an alpha channel are not accepted.

What to check

Inspect the full-size output and compare details and subject appearance with your source.

Inputs

  • Prompt (required): Text prompt describing the desired image. Supports Chinese and English. Max 2000 characters.
  • Image (optional): Optional reference image (0 or 1). When provided, can be used for style guidance. Resolution: 384-5000px each dimension. Max size: 10MB. Formats: JPEG, JPG, PNG (no alpha), BMP, WEBP.
  • Negative Prompt (optional): Content to avoid in the generated image. Max 500 characters.
  • Image Size (optional): Output image size. If not set: matches input image size (up to 1280*1280). Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Seed (optional): Random seed for reproducibility (0-2147483647).

Output and limits

  • Image sizes: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • 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