wan-video/wan-2.6-i2v

Alibaba Wan 2.6 image to video generation model

Capabilities

Reference Images Negative Prompt Seed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`image` *	string (uri)	Input image for video generation	`—`	—
`prompt` *	string	Text prompt for video generation	`—`	—
`audio`	string (uri)	Audio file (wav/mp3, 3-30s, ≤15MB) for voice/music synchronization	`—`	—
`duration`	integer	Duration of the generated video in seconds	`5`	5 10 15
`enable_prompt_expansion`	boolean	If set to true, the prompt optimizer will be enabled	`true`	—
`multi_shots`	boolean	Enable intelligent multi-shot segmentation (only active when enable_prompt_expansion is enabled). True enables multi-shot segmentation, false generates single-shot content.	`false`	—
`negative_prompt`	string	Negative prompt to avoid certain elements	`""`	—
`resolution`	string	Video resolution	`"720p"`	720p 1080p
`seed`	integer	Random seed for reproducible generation	`—`	—

image required string

Input image for video generation

prompt required string

Text prompt for video generation

audio string

Audio file (wav/mp3, 3-30s, ≤15MB) for voice/music synchronization

duration integer

Duration of the generated video in seconds

Default: 5

5 10 15

enable_prompt_expansion boolean

If set to true, the prompt optimizer will be enabled

Default: true

multi_shots boolean

Enable intelligent multi-shot segmentation (only active when enable_prompt_expansion is enabled). True enables multi-shot segmentation, false generates single-shot content.

Default: false

negative_prompt string

Negative prompt to avoid certain elements

Default: ""

resolution string

Video resolution

Default: "720p"

720p 1080p

seed integer

Random seed for reproducible generation

Version: 8dee499c1e4c Updated: 6/26/2026 45.3K runs