wan-video/wan-2.7-image-pro

OfficialView on Replicate →

Generate and edit high-quality images with Alibaba's Wan 2.7 Pro with 4K output, thinking mode, text-to-image, multi-image editing, and image set generation

Capabilities

Seed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`prompt`*	string	Text prompt for image generation or editing	`—`	—
`image_set_mode`	boolean	Generate a coherent set of related images from a single prompt (e.g. a character across seasons). When enabled, num_outputs can be up to 12.	`false`	—
`images`	array	Input images for editing, style transfer, or multi-reference generation (up to 9 images, jpg/png/bmp/webp). When provided, the model operates in image editing mode.		—
`num_outputs`	integer	Number of images to generate (1-4 for standard mode, 1-12 for image set mode)	`1`	min: 1, max: 4
`seed`	integer	Random seed for reproducible generation. Range: 0-2147483647	`—`	—
`size`	string	Output image resolution. '1K', '2K', and '4K' auto-size based on input images. 4K is only available for text-to-image.	`"2K"`	1K2K4K1024102420482048409640961280720720128020481152115220484096230423044096102476876810242048153615362048409630723072*4096
`thinking_mode`	boolean	Enable enhanced reasoning for improved image quality. Only applies to text-to-image (no input images, no image set mode). Increases generation time.	`true`	—

promptrequiredstring

Text prompt for image generation or editing

image_set_modeboolean

Generate a coherent set of related images from a single prompt (e.g. a character across seasons). When enabled, num_outputs can be up to 12.

Default: false

imagesarray

Input images for editing, style transfer, or multi-reference generation (up to 9 images, jpg/png/bmp/webp). When provided, the model operates in image editing mode.

Default:

num_outputsinteger

Number of images to generate (1-4 for standard mode, 1-12 for image set mode)

Default: 1min: 1, max: 4

seedinteger

Random seed for reproducible generation. Range: 0-2147483647

sizestring

Output image resolution. '1K', '2K', and '4K' auto-size based on input images. 4K is only available for text-to-image.

Default: "2K"

1K2K4K1024*10242048*20484096*40961280*720720*12802048*11521152*20484096*23042304*40961024*768768*10242048*15361536*20484096*30723072*4096

thinking_modeboolean

Enable enhanced reasoning for improved image quality. Only applies to text-to-image (no input images, no image set mode). Increases generation time.

Default: true

Version: d880bad3fb10Updated: 7/25/202688.5K runs