# Wan v2.6 Image-to-Video

Wan v2.6 Image-to-Video is an image-to-video generation model from Alibaba Cloud that takes a still image and a text prompt and produces a smoothly animated video clip up to 15 seconds long at resolutions up to 1080p.

- **Model ID:** `alibaba/wan-v2.6-i2v`
- **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-i2v

## Supported parameters

- **Parameters:** `aspectRatio`, `resolution`, `duration`, `fps`, `seed`
- **Operations:** `image-to-video`
- **Input modalities:** `text`, `image`
- **Output modalities:** `video`
- **Aspect ratios:** `16:9`, `9:16`, `1:1`, `4:3`, `3:4`
- **Resolutions:** `720P`, `1080P`
- **Durations:** `2s`, `3s`, `4s`, `5s`, `6s`, `7s`, `8s`, `9s`, `10s`, `11s`, `12s`, `13s`, `14s`, `15s`
- **Frame rates:** `24 fps`
- **Maximum outputs per request:** Not reported
- **Maximum input images:** 1
- **Input image formats:** `jpeg`, `jpg`, `png`
- **Maximum input image size:** 20 MB

## Example

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

const result = await generateVideo({
  model: 'alibaba/wan-v2.6-i2v',
  prompt: 'A serene mountain lake at sunrise.'
});
```

## About

Wan v2.6 Image-to-Video belongs to Alibaba Cloud's 2.6-generation video lineup, the quality-focused image-animation model in the series. The model accepts a source image, between 360px and 2000px on either dimension, up to 100MB, paired with a descriptive text prompt that guides the motion, timing, and scene direction. From those inputs it produces video at 480p, 720p, or 1080p in five aspect ratios.

The 2.6 generation introduced substantial upgrades over its predecessors, including improved temporal consistency (less flicker between frames), sharper fine detail retention from the source image, and better instruction-following when the text prompt specifies particular motions or environmental conditions. Audio integration is optionally available, allowing ambient sound or scene audio to accompany the animated output.

Unlike the R2V models, I2V doesn't attempt to extract a character identity for reuse across multiple shots; it animates the submitted image as a single continuous visual source. Multi-shot mode is disabled by default, which keeps the output as a single unbroken clip, appropriate for product showcases, still-life animations, and short narrative scenes anchored to one visual composition.

## What to consider

For rapid iteration and draft-quality previews, consider wan-v2.6-i2v-flash, which trades some visual fidelity for significantly faster generation times.

## When to use

### Best For

- Animating product photography into short video ads without a source video reference
- Bringing concept art, illustrations, or architectural renders to life with guided motion
- Creating portrait or landscape social clips from a single hero image and a motion-direction prompt
- High-quality 1080p animation where generation speed is less critical than visual fidelity

### Consider Alternatives When

- If speed and iteration cadence matter more than peak quality, use wan-v2.6-i2v-flash for faster turnaround at 720p or 1080p
- If you want to generate video from a text description alone without a source image, use wan-v2.6-t2v
- If you need to preserve a character's identity across multiple generated scenes, use wan-v2.6-r2v

## Best for

- **Animated product advertising:** Turning product photography into short video ads without a source video reference
- **Bringing static art to life:** Animating concept art, illustrations, or architectural renders with guided motion
- **Single-hero-image social clips:** Portrait or landscape outputs driven by a motion-direction prompt
- **High-fidelity 1080p animation:** Workflows where visual quality outweighs generation speed

## Consider alternatives

- **Speed over peak quality:** Use wan-v2.6-i2v-flash for faster turnaround at 720p or 1080p during iteration
- **Text-only video generation:** wan-v2.6-t2v generates video from a text description without a source image
- **Cross-scene character consistency:** wan-v2.6-r2v preserves a character's identity across multiple generated scenes

## Frequently asked questions

### What image formats and sizes are accepted?

The model accepts images between 360px and 2000px on each dimension, with a maximum file size of 100MB.

### Can I control the direction of motion with a text prompt?

Yes. A text prompt accompanying the image guides the generated motion, camera direction, and scene atmosphere.

### Does Wan v2.6 Image-to-Video support audio output?

Audio integration is optionally available, ambient sounds can accompany the generated video when enabled.

### How long can generated clips be?

Clips can be 5, 10, or 15 seconds long, making this the longest-output option in the I2V variants.

### What aspect ratios are supported?

The model supports 16:9, 9:16, 1:1, 4:3, and 3:4, the widest aspect ratio selection in the Wan 2.6 I2V lineup.

### When should I choose I2V Flash instead?

If you are prototyping or need fast feedback on motion ideas, the flash variant offers faster generation. For final-quality deliverables at 1080p, the standard I2V model is recommended.

## Links

- [Model page](https://vercel.com/ai-gateway/models/wan-v2.6-i2v)
- [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.