Skip to content
Dashboard

Wan v2.6 Image-to-Video Flash

Wan v2.6 Image-to-Video Flash is Alibaba Cloud's speed-optimized image-to-video model that animates still images into video clips at up to 1080p, designed for fast iteration and high-throughput animation pipelines.

View API reference
Price
$0.05, Per second
Lowest available configuration
import { experimental_generateVideo as generateVideo } from 'ai';
const result = await generateVideo({
model: 'alibaba/wan-v2.6-i2v-flash',
prompt: 'A serene mountain lake at sunrise.'
});
Read docs

Copy link to headingPlayground

Try out Wan v2.6 Image-to-Video Flash by Alibaba Cloud. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

alibaba logo
Start frame (required)
Prompt(optional)

Duration8s
2s15s
Resolution
Videos to generate
alibaba logo

Your generated video will appear here.

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider
Input
Output
Capabilities
ZDR
No Training
Free Tier
Release Date
$0.05/sec+1 more
12/16/2025

Getting started

Generate videos with Wan v2.6 Image-to-Video Flash using the experimental_generateVideo function from AI SDK 6 or later. AI Gateway handles routing and polls until the video is ready.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the video generation quickstart.

index.ts
import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';
async function main() {
const result = await generateVideo({
model: 'alibaba/wan-v2.6-i2v-flash',
prompt: {
image: 'https://example.com/cat.png',
text: 'The cat waves hello and smiles',
},
});
// Save the generated video
fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');
}
main().catch(console.error);

Top-level parameters

Control the output with the top-level resolution and duration parameters. Wan uses resolution, not aspectRatio.

wan-image-to-video-top-level.ts
import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';
async function main() {
const result = await generateVideo({
model: 'alibaba/wan-v2.6-i2v-flash',
prompt: {
image: 'https://example.com/cat.png',
text: 'The cat waves hello and smiles',
},
resolution: '1280x720',
duration: 5,
});
// Save the generated video
fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');
}
main().catch(console.error);
ParameterTypeRequiredDescription
prompt.imagestringYesURL of the image to animate.
prompt.textstringNoDescription of the motion or animation. Max 1500 characters.
durationnumberNoVideo length in seconds. 2-15 seconds.
resolutionstringNoResolution ('1280x720', '1920x1080').
aspectRatiostringNoAspect ratio ('16:9', '9:16', '1:1', '4:3', '3:4').
generateAudiobooleanNoGenerate synchronized audio with the video.
frameImagesArray<{ image: string; frameType: 'first_frame' }>NoOpening frame of the clip, as a single first_frame entry. Replaces prompt.image and wins when both are set. URLs only. Wan does not interpolate to an ending image, so a last_frame entry is ignored with a warning.

Input limits

InputFormatsSourcesMax countMax sizeLimits
TextUp to 1500 characters
Imagejpeg, jpg, png, bmp, webpurl120 MB≥240px · ≤8000px
Audiowav, mp3url15 MB3-30s

Provider options

Load the Wan options under providerOptions.alibaba. audioUrl (an external audio track for lip-sync) is a separate workflow and is documented in the table below.

wan-image-to-video-provider-options.ts
import { experimental_generateVideo as generateVideo } from 'ai';
import fs from 'node:fs';
import 'dotenv/config';
async function main() {
const result = await generateVideo({
model: 'alibaba/wan-v2.6-i2v-flash',
prompt: {
image: 'https://example.com/cat.png',
text: 'The cat waves hello and smiles',
},
duration: 5,
generateAudio: true,
providerOptions: {
alibaba: {
negativePrompt: 'blurry, low quality',
watermark: false,
pollIntervalMs: 5000,
pollTimeoutMs: 600000,
},
},
});
// Save the generated video
fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');
}
main().catch(console.error);

Pass Wan-specific options under providerOptions.alibaba in your generateVideo call.

ParameterTypeRequiredDescription
negativePromptstringNoWhat to avoid in the video. Max 500 characters.
audioUrlstringNoURL to audio file for audio-video sync — see the Input limits table for supported formats, duration, and size.
audiobooleanNoGenerate audio with the video. Provider-side alias for the top-level generateAudio, which wins when both are set. v2.6 only — v2.7 always generates audio and ignores it with a warning.
watermarkbooleanNoAdd watermark to the video. Defaults to false.
pollIntervalMsnumberNoHow often to check task status. Defaults to 5000.
pollTimeoutMsnumberNoMaximum wait time. Defaults to 600000 (10 minutes).

Reference-to-video vs image-to-video

Reference-to-video uses the top-level inputReferences to show the model what your characters look like, then generates a brand-new scene from your prompt. The reference media never becomes the video content; reference each one in the prompt with character1, character2, and so on (first entry maps to character1).

Image-to-video instead animates the actual image you pass in frameImages or prompt.image. The image you provide becomes the video content, and you add motion to that exact scene.

Copy link to headingMore models by Alibaba Cloud

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Free Tier
Release Date
991K3.9 s50 tps
$2/M
$6/M
Read$0.25/M
Write$2.50/M
+2
alibaba logo
09/01/2026
991K1.1 s96 tps
$0.16/M
$0.47/M
Read$0.02/M
Write$0.20/M
+2
alibaba logo
08/26/2026
1M0.6 s133 tps
$0.10/M
$0.40/M
Read$0.01/M
Write$0.63/M
+1
alibaba logo
deepinfra logo
morph logo
+3
08/14/2026
1M2.5 s154 tps
$2/M
$6/M
Read$0.25/M
Write$2.50/M
+1
alibaba logo
fireworks logo
08/02/2026
991K2.5 s140 tps
$0.03/M+2 more
$0.13/M+2 more
Read$0.006/M
Write$0.04/M
+2
alibaba logo
07/28/2026
1M2.0 s58 tps
$0.40/M+1 more
$1.60/M+1 more
Read$0.08/M
Write$0.50/M
+2
alibaba logo
06/02/2026

Copy link to headingAbout Wan v2.6 Image-to-Video Flash

Wan v2.6 Image-to-Video Flash occupies the speed-optimized position within the Wan 2.6 image-to-video family. It accepts the same inputs as the standard I2V model, a source image plus a motion-guiding text prompt, but prioritizes low generation latency, making it well-suited for creative iteration, draft reviews, and high-throughput pipelines where many animation variants need to be evaluated quickly.

Despite the speed focus, the Flash model retains the core visual improvements introduced in the 2.6 generation: better temporal consistency between frames, improved instruction-following for motion prompts, and support for the full resolution range from 480p through 1080p. Teams commonly use the Flash variant during the exploration phase of a production workflow and then route finalized prompts to the standard I2V model for polished output.

The Flash architecture also makes it practical to run animation at scale, for example, generating animated thumbnails or preview loops for a large image library, without the queue times that full-quality generation incurs. Optional audio accompaniment is available on the same pass.

Copy link to headingWhat To Consider When Choosing a Provider

  • Configuration: When peak visual fidelity for a final deliverable takes priority over turnaround time, evaluate the standard wan-v2.6-i2v model alongside this Flash variant before choosing.
  • Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
  • Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use Wan v2.6 Image-to-Video Flash

Best for

  • Rapid prompt iteration: Exploring motion ideas before committing to full-quality I2V rendering
  • High-throughput animation workflows: Processing many images in parallel with short turnaround times
  • Draft previews for review: Generating quick outputs for client review or storyboard approval loops
  • Cost-sensitive animation pipelines: Delivering acceptable quality at lower computational expense

Consider alternatives when

  • Maximum visual fidelity: Use wan-v2.6-i2v for the highest-quality image animation in final deliverables
  • Text-only source: Use wan-v2.6-t2v when generating from a text description rather than an image
  • Consistent character identity: Use wan-v2.6-r2v or wan-v2.6-r2v-flash when the same subject must appear across multiple generated shots

Wan v2.6 Image-to-Video Flash makes image animation practical at production scale by dramatically reducing generation time relative to the standard I2V model, without sacrificing the resolution range or core motion quality of the Wan 2.6 series. It is the recommended starting point for any iterative or high-volume image-to-video workflow.

Copy link to headingFrequently Asked Questions

  • How much faster is I2V Flash compared to the standard I2V model?

    The Flash variant is engineered specifically for faster generation times. Exact speed differences vary by resolution and provider, but Flash is designed for quick-iteration use cases where the standard model's generation time is prohibitive.

  • Does the Flash model support 1080p output?

    Yes. Despite the speed optimization, I2V Flash supports 480p, 720p, and 1080p resolutions.

  • Can I include audio in the generated video?

    Optional audio accompaniment is available on the same generation pass.

  • What is the maximum clip duration?

    Generated clips can be up to 15 seconds long.

  • When should I use Flash versus the standard I2V model?

    Use Flash for drafts, iteration, and high-volume tasks. Use the standard I2V model when final visual quality matters more than turnaround time.

  • Does the Flash model require a different input format than the standard I2V?

    No. Both models accept the same inputs: a source image and a text prompt describing the desired motion.

Your use is subject to Alibaba Cloud's Terms & Privacy Policies.