Wan 2.7 Reference to Video: AI Image-to-Video Generator

Alibaba WAN 2.7 Reference-to-Video. Reference characters/props to generate new shots.

📝

Overview

About this model

Alibaba WAN 2.7 Reference-to-Video turns character, prop, or scene references from images or videos into new video shots.

1Character Consistency: Generate storyboards using the same character across different scenes.
💰

Pricing & Value

Cost analysis

muapiapp0.02 - 0.03 credits per second

Dynamic pricing based on resolution and length.

Model Provider$0.05+ per clip

Less flexible than our per-second billing.

* Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Promptstring

Text description of the desired motion and scene.

Default ValueA person walking in the rain...
Reference Imagesarray

Array of reference image URLs (jpg/png). Max 4 items.

Default Valueundefined
Reference Videosarray

Array of reference video URLs (mp4/mov). Max 4 items.

Default Valueundefined
Image Urlstring

URL to a single reference image.

Default Valueundefined
Negative Promptstring

What not to generate

Default Valueblurry, low quality, distorted
Aspect RatioEnum (5 options)

The aspect ratio of the generated video.

Default Value16:9
ResolutionEnum (2 options)

Output resolution

Default Value720p
Durationint

Video duration in seconds (2-10).

Default Value5
📖

Implementation Guide

Developer documentation

Provide up to 4 reference videos and one optional image. Describe the output cleanly in the prompt.

Common Questions

Frequently asked

Maximum references?

Up to 4 videos and 1 image.