SandBase is live — $1 in free credits on signupStart free ›

Alibaba modelsvideo generation api

alibaba/wan/2.6/reference-to-video

Alibaba Wan 2.6 reference-to-video model generating video guided by reference content.

Input
The text prompt to generate a video from.
The URLs of reference videos to guide video generation.
The duration of the generated video in seconds. Valid values are 5 and 10. Allowed values: 5, 10.
The aspect ratio of the generated video. Allowed values: 1:1, 4:3, 3:4, 16:9, 9:16.
The resolution of the video to generate. Allowed values: 720p, 1080p.
Idle

Example output — click Run to generate your own

API README

Wan 2.6 Reference to Video

Wan 2.6 Reference to Video creates new video around referenced people, characters, pets, or objects, using image or video material to retain recognizable appearance and, when present, vocal character. It is built for interactions involving more than one referenced subject rather than simple first-frame animation.

Assign each reference a clear role in the prompt and describe how the characters interact, where the scene occurs, what they say or do, and how the camera follows them. This model is especially useful for recurring casts, branded mascots, dialogue scenes, and narrative content that depends on stable identity across shots.

Highlights

  • Multi-character reference synthesis. Places several referenced protagonists into one generated interaction while keeping them distinguishable.
  • Appearance and voice carryover. Extracts visual identity and available vocal traits from reference media for the new performance.
  • Narrative shot construction. Supports directed scene progression instead of limiting the output to a single static action.
  • Cross-modal character grounding. Uses both image and video references to anchor people, cartoons, animals, or props in the generated world.

Pricing

ConfigurationBilling unitPrice
5 seconds720p$0.500
5 seconds1080p$0.750
10 seconds720p$1.000
10 seconds1080p$1.500

When to Use

✅ Good fit❌ Consider alternatives
The project needs this exact reference-to-video workflowThe intended task belongs to a different media route
Available source media matches every required fieldRequired assets or usage rights are unavailable
The brief can define subject, action, camera, and styleOutput must be deterministic at frame or pixel level
Supported duration, resolution, and framing fit deliveryFinal placement requires unsupported specifications
An asynchronous generation job fits productionA live or frame-synchronous response is mandatory

Prompt Guide

Describe the result as a shot or design brief: identify subjects and references, state the action or transformation, specify environment and composition, then add camera behavior, lighting, pacing, style, sound, and preservation constraints where relevant. Use exact reference identifiers exposed by the local schema.

{
  "duration": 5,
  "prompt": "Video1 holds Image2 and plays a soothing country folk song on the chair from Image3, saying: 'The sunshine is so nice today.' Image1 holds a bouquet of sunflowers, walks past Video1, places the flowers on the table next to Video1, and says: 'That sounds lovely, could you sing it again?'",
  "resolution": "720p",
  "videos": [
    "https://example.com/reference.mp4"
  ]
}

Technical Specs

SpecValue
Model IDalibaba/wan/2.6/reference-to-video
Input fieldsprompt (string)<br>videos (array)<br>duration (integer; 5, 10)<br>resolution (string; 720p, 1080p)<br>aspect_ratio (string; 1:1, 4:3, 3:4, 16:9, 9:16)
Required inputprompt
Output fieldsurl, content_type
ExecutionAsynchronous job

Related Models

Related Models

alibaba/wan/2.6/reference-to-video/flashWan 2.6 Flash by Alibaba - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.alibaba/wan/2.6/image-to-video/flashWan 2.6 Flash by Alibaba - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.alibaba/wan/2.6/image-to-videoAlibaba Wan 2.6 image-to-video model transforming still images into video. Supports first-frame-to-video only.alibaba/wan/2.6/text-to-videoAlibaba Wan 2.6 text-to-video model with cinematic visuals, configurable duration (5 or 10 seconds) and resolution.alibaba/wan/2.1/text-to-video/loraWan 2.1 Lora by Alibaba - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.alibaba/wan/2.1/vaceWan 2.1 Vace by Alibaba - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.alibaba/wan/2.1/vace/depthWan 2.1 Vace by Alibaba - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.alibaba/wan/2.1/vace/inpaintingWan 2.1 Vace is Alibaba's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.