wan-video/wan-2.7-r2v

Generate videos from reference images or clips while preserving subject identity using Alibaba's Wan 2.7 reference-to-video model

Capabilities

Reference Images Negative Prompt Seed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`prompt` *	string	Text prompt for video generation	`—`	—
`aspect_ratio`	string	Aspect ratio of the generated video	`"16:9"`	16:9 9:16 1:1 4:3 3:4
`duration`	integer	Duration of the generated video in seconds	`5`	min: 2, max: 10
`negative_prompt`	string	Negative prompt — describes content that should not appear in the video	`""`	—
`reference_images`	array	Reference images of the character/object to feature in the video (jpg/png/bmp/webp)		—
`reference_videos`	array	Reference videos of the character/object to feature in the video (mp4/mov)		—
`resolution`	string	Output video resolution	`"1080p"`	720p 1080p
`seed`	integer	Random seed for reproducible generation. Range: 0-2147483647	`—`	—
`shot_type`	string	Shot structure of the generated video	`"single"`	single multi

prompt required string

Text prompt for video generation

aspect_ratio string

Aspect ratio of the generated video

Default: "16:9"

16:9 9:16 1:1 4:3 3:4

duration integer

Duration of the generated video in seconds

Default: 5 min: 2, max: 10

negative_prompt string

Negative prompt — describes content that should not appear in the video

Default: ""

reference_images array

Reference images of the character/object to feature in the video (jpg/png/bmp/webp)

Default:

reference_videos array

Reference videos of the character/object to feature in the video (mp4/mov)

Default:

resolution string

Output video resolution

Default: "1080p"

720p 1080p

seed integer

Random seed for reproducible generation. Range: 0-2147483647

shot_type string

Shot structure of the generated video

Default: "single"

single multi

Version: 00f2bfc4cada Updated: 6/26/2026 2.5K runs