# Wan v2.6 Reference-to-Video

Wan v2.6 Reference-to-Video prioritizes reconstruction fidelity over turnaround time, producing reference-to-video output where appearance details, vocal timbre, and movement patterns are preserved with care, for use cases where the generated video must closely match the reference subject.

- **Model ID:** `alibaba/wan-v2.6-r2v`
- **Type:** video
- **Providers:** alibaba
- **Context window:** Not applicable
- **Maximum output tokens:** 0
- **Pricing:** See the provider details below
- **Canonical page:** https://vercel.com/ai-gateway/models/wan-v2.6-r2v

## Supported parameters

- **Parameters:** `aspectRatio`, `resolution`, `duration`, `fps`
- **Operations:** `reference-to-video`
- **Input modalities:** `text`, `image`, `video`
- **Output modalities:** `video`
- **Aspect ratios:** `16:9`, `9:16`, `1:1`, `4:3`, `3:4`
- **Resolutions:** `1280x720`, `720x1280`, `960x960`, `1088x832`, `832x1088`, `1920x1080`, `1080x1920`, `1440x1440`, `1632x1248`, `1248x1632`
- **Durations:** `2s`, `3s`, `4s`, `5s`, `6s`, `7s`, `8s`, `9s`, `10s`
- **Frame rates:** `30 fps`
- **Maximum outputs per request:** Not reported
- **Maximum input images:** 5
- **Input image formats:** `JPEG`, `JPG`, `PNG`, `BMP`, `WEBP`
- **Maximum input image size:** 20 MB

## Example

```ts
import { experimental_generateVideo as generateVideo } from 'ai';

const result = await generateVideo({
  model: 'alibaba/wan-v2.6-r2v',
  prompt: 'A serene mountain lake at sunrise.'
});
```

## About

Alibaba Cloud positioned Wan v2.6 Reference-to-Video as China's first reference-to-video generation model. The core idea is simple: feed the model a short video clip of a person, and it extracts enough about their face, body, clothing, voice, and movement style to convincingly place them into an entirely new scene described by text.

What sets the standard R2V apart within the Wan lineup is its emphasis on reconstruction depth. The model devotes additional inference time to faithfully reproducing fine-grained identity signals, the specific way light falls across facial features, subtle mannerisms in how a subject moves, the particular resonance of a voice. For final-delivery video where a client or audience will scrutinize whether the generated character truly matches the reference, this level of fidelity matters.

The reference pipeline accepts multiple characters from reference images or videos. On AI Gateway, pass reference URLs in order and name them `character1`, `character2`, and so on in the prompt (see the reference-to-video docs). You can mix images and videos within provider limits (up to five references total). Each video reference can be 2 to 30 seconds. Output duration is 2 to 10 seconds at 720p or 1080p, with five aspect ratio options covering landscape, portrait, square, and intermediate formats.

## What to consider

Because R2V allocates more compute to identity reconstruction than the Flash variant, generation times are longer. Budget wall-clock time accordingly when planning render queues for final-delivery assets.

## When to use

### Best For

- Final-delivery marketing assets where the generated character must pass close visual inspection against the reference subject
- Brand campaigns that demand voice and appearance consistency across a series of scenes rendered over time
- Virtual production pipelines where a director needs confident identity transfer before approving a generated sequence
- Multi-subject compositions where several reference identities should appear together in one generated clip

### Consider Alternatives When

- If speed matters more than peak fidelity during early creative exploration, wan-v2.6-r2v-flash provides faster turnaround for drafting
- If the source material is a photograph rather than a video clip, wan-v2.6-i2v animates from still images
- If no reference subject is involved and the video should be generated from text alone, wan-v2.6-t2v is the appropriate model

## Best for

- **Final-delivery marketing assets:** Generated characters that must pass close visual inspection against the reference subject
- **Brand campaign consistency:** Voice and appearance preservation across a series of scenes rendered over time
- **Virtual production pipelines:** Directors who need confident identity transfer before approving a generated sequence
- **Multi-subject compositions:** Scenes where several reference identities appear together in one generated clip

## Consider alternatives

- **Speed over peak fidelity:** wan-v2.6-r2v-flash provides faster turnaround during early creative exploration
- **Photograph source material:** wan-v2.6-i2v animates from still images when the source is a photograph rather than a video clip
- **Text-only video generation:** wan-v2.6-t2v is the appropriate model when no reference subject is involved

## Frequently asked questions

### Why does R2V take longer to generate than the Flash variant?

The standard R2V model spends additional compute on identity reconstruction, fine-grained facial detail, voice matching, and movement pattern extraction all receive more processing time. This is a deliberate design choice favoring output quality over speed.

### What happens if my reference clip is very short, like 2 seconds?

The model can work with clips as short as 2 seconds, but shorter references provide less identity data. For the highest fidelity, longer clips within the 2-30 second range give the extraction pipeline more material to work with, particularly for voice and movement characteristics.

### How should I tag multiple subjects in a single prompt?

Use `character1`, `character2`, and so on in the prompt text, in the same order as your reference URLs. Each name maps to the corresponding reference image or video.

### Does R2V preserve clothing and accessories from the reference?

Yes. The identity extraction covers visual appearance broadly, including clothing, accessories, hairstyle, and body proportions, not just facial features. The generated output aims to maintain the full visual signature of the reference subject.

### What aspect ratios work best for social media delivery?

For vertical social content, 9:16 is the standard choice. For feed posts, 1:1 provides square framing. The model also supports 16:9, 4:3, and 3:4 for other distribution contexts.

### Can R2V be used for product or object identity transfer, or only people?

The reference extraction is designed broadly enough to capture objects and animals in addition to people, though the pipeline is most heavily optimized for human subjects where facial and vocal identity are the primary signals.

## Links

- [Model page](https://vercel.com/ai-gateway/models/wan-v2.6-r2v)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://wan.video/)
- [Provider pricing](https://modelstudio.console.alibabacloud.com/ap-southeast-1/?tab=doc#/doc/?type=model&url=prices)


If you encounter incorrect information, can’t find what you need, need a capability Vercel doesn’t currently offer, or have any other feedback to report, please do it by following the instructions at https://vercel.com/feedback.md.