Input
Text prompts for image generation. Supports both Chinese and English, with a minimum of 1 characters and a maximum of 5,000 characters.433/5000
input_urls
File 1
File uploads require configured image storage. A public HTTPS image URL can be used directly.
Upload an image file to use as input for the API. Image dimensions must be at least 240 pixels in length and width.
bbox_list
Draw edit regions on each image. Coordinates are saved as [x1, y1, x2, y2] using the original image pixel coordinates. Each image supports up to 2 boxes.
Boxes
No boxes selected for this image.
Enable Gallery Mode
Enhances reasoning for higher-quality outputs. Only available when Gallery Mode is off and no images are uploaded. May increase generation time.
When the gallery mode is turned off, n represents the number of generated images (1-4); when it is turned on, n represents the maximum number of images (1-12), and the actual value is determined by the model.
color_palette
0 colors / 0.00%Optional custom theme with 3 to 10 colors. Recommended: 8.
Add 3 to 10 colors. Ratios must sum to 100.00%.
Resolution of the generated image. Higher resolutions take longer to generate.(4K generation is available only for text-to-image in Standard Mode)
Aspect ratio of the generated image
Whether to add a watermark identifier
Using the same seeds and the same prompts for the same version of the model can keep the generated content relatively stable.
A configurable parameter. Defaults to true in the Playground.
Output
Examples
Explore different use cases and parameter configurations
Explore more Text to Image models
More AI models from Wan
Latest and popular AI models
README
Complete guide to using wan/2-7-image-pro