Available now

Wan 2.5 Image: text to image

By Alibaba

Wan 2.5 Image turns a prompt in English or Chinese into one to four images and edits one image or combines two.

Model ID
Maker
Alibaba

Input

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

Supports Chinese and English, max 2000 characters.

Example prompt. Edit it or write your own.

This model reads prompts in English or Chinese.

Values from 1 to 4.

Additional settings

Negative prompt to describe content to avoid. Max 500 characters.

Whether to enable prompt rewriting using LLM. Improves results for short prompts but increases processing time.

Random seed for reproducibility. If None, a random seed is chosen.

Estimated total$0.08

You sign up first. Your settings are kept.

About this model

Overview

Wan 2.5 Image makes one to four images per run in six preset shapes. Prompts can be in English or Chinese, up to 2000 characters, with a negative prompt of up to 500. Prompt rewriting is on by default and helps short prompts.

The edit mode changes one image from an instruction, or combines two reference images into a new one.

What you can build

  • Images from prompts written in Chinese
  • Your photo with a new background or style
  • A scene that brings together two reference images
  • Square, portrait and landscape images for posts

Prompting tips

  • Leave prompt rewriting on for short ideas; turn it off when you need your exact wording.
  • When combining two images, say what to take from each one.

What to check

Check text, object counts and whether edits unintentionally changed the main subject.

Inputs

  • Prompt (required): The prompt for image generation. Supports Chinese and English, max 2000 characters.
  • Negative Prompt (optional): Negative prompt to describe content to avoid. Max 500 characters.
  • Number of Images (optional): Number of images to generate. Values from 1 to 4.
  • Image Size (optional): The size of the generated image. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Enable Prompt Expansion (optional): Whether to enable prompt rewriting using LLM. Improves results for short prompts but increases processing time.
  • Seed (optional): Random seed for reproducibility. If None, a random seed is chosen.

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).
  • Up to 4 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: $0.08 / image