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 ImagesNegative PromptSeed

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"`	16:99:161:14:33:4
`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"`	720p1080p
`seed`	integer	Random seed for reproducible generation. Range: 0-2147483647	`—`	—
`shot_type`	string	Shot structure of the generated video	`"single"`	singlemulti

promptrequiredstring

Text prompt for video generation

aspect_ratiostring

Aspect ratio of the generated video

Default: "16:9"

16:99:161:14:33:4

durationinteger

Duration of the generated video in seconds

Default: 5min: 2, max: 10

negative_promptstring

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

Default: ""

reference_imagesarray

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

Default:

reference_videosarray

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

Default:

resolutionstring

Output video resolution

Default: "1080p"

720p1080p

seedinteger

Random seed for reproducible generation. Range: 0-2147483647

shot_typestring

Shot structure of the generated video

Default: "single"

singlemulti

Version: 00f2bfc4cadaUpdated: 8/1/20264.5K runs