Browse ModelsAlibabaAlibaba Wan 2.6 Image To Video Pro

Alibaba Wan 2.6 Image To Video Pro

Alibaba Wan 2.6 Image To Video Pro

Playground

Try it on WavespeedAI!

Alibaba WAN 2.6 Image-to-Video Pro converts images into premium-quality videos with superior motion dynamics, enhanced visual fidelity, and professional cinematic output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Wan 2.6 Image-to-Video Pro

Wan 2.6 Image-to-Video Pro is Alibaba’s premium image-to-video model, transforming still images into cinematic video with superior motion quality and detail. Upload a reference image, describe the scene and motion — the model generates smooth, high-resolution video with optional audio input and flexible duration options.


Why Choose This?

  • Pro-tier quality Superior visual fidelity and motion realism from Alibaba’s latest Wan 2.6 architecture.

  • Multiple resolutions Output in 1080p, 2K, or 4K to match your production needs.

  • Audio support Optional audio input for synchronized video generation.

  • Shot type control Choose between single or multi-shot compositions.

  • Prompt Enhancer Built-in prompt optimizer for improved generation results.

  • Negative prompt support Specify elements to exclude for more precise control.


Parameters

ParameterRequiredDescription
promptYesText description of the desired scene and motion
imageYesReference image to animate (URL or upload)
audioNoAudio file for synchronized video (URL or upload)
negative_promptNoElements to exclude from the video
resolutionNoOutput resolution: 1080p (default), 2k, 4k
durationNoVideo length in seconds (default: 5)
shot_typeNoShot composition: single (default) or multi
enable_prompt_expansionNoEnable prompt optimizer (default: disabled)
seedNoRandom seed for reproducibility (-1 for random)

How to Use

  1. Upload your image — provide the reference image to animate.
  2. Write your prompt — describe the scene, motion, camera movement, and mood in detail.
  3. Add audio (optional) — upload audio for synchronized video generation.
  4. Add negative prompt (optional) — specify elements you want to avoid.
  5. Choose resolution — select 1080p, 2K, or 4K based on your needs.
  6. Set duration — choose the desired video length.
  7. Select shot type — single for focused shots, multi for complex compositions.
  8. Enable prompt expansion (optional) — let the optimizer enhance your prompt.
  9. Run — submit and download your video.

Pricing

Duration1080p2k4k
5 s$0.60$0.70$0.80
10 s$1.20$1.40$1.60
15 s$1.80$2.10$2.40

Billing Rules

  • Base rate (1080p): $0.60 per 5 seconds
  • 2K rate: $0.70 per 5 seconds
  • 4K rate: $0.80 per 5 seconds

Best Use Cases

  • Premium Production — High-resolution video requiring superior visual quality.
  • Marketing & Ads — Cinematic promotional videos with professional polish.
  • Music Videos — Synchronized video generation with audio input.
  • E-commerce — Bring product images to life in stunning detail.
  • Content Creation — Create engaging short-form videos for social media.

Pro Tips

  • Use detailed, cinematic prompts for best results — include lighting, camera angles, and motion descriptions.
  • Try the Prompt Enhancer (enable_prompt_expansion) to automatically refine your descriptions.
  • Use negative_prompt to avoid common issues like blurry faces or unwanted elements.
  • Add audio for music videos or content requiring synchronized sound.
  • Use single shot_type for focused character or product animations, multi for complex scene compositions.
  • Set a specific seed for reproducible results across multiple generations.

Notes

  • Both prompt and image are required fields.
  • Ensure uploaded image and audio URLs are publicly accessible.
  • Higher resolutions (2K, 4K) produce better detail but cost more.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.6/image-to-video-pro" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "resolution": "1080p",
    "duration": 5,
    "shot_type": "single",
    "enable_prompt_expansion": false,
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
imagestringYes-The image for generating the output.
audiostringNo--Audio URL to guide generation (optional).
promptstringYes-The positive prompt for the generation.
negative_promptstringNo-The negative prompt for the generation.
resolutionstringNo1080p1080p, 2k, 4kThe resolution of the generated media.
durationintegerNo55, 10, 15The duration of the generated media in seconds.
shot_typestringNosinglesingle, multiThe type of shots to generate.
enable_prompt_expansionbooleanNofalse-If set to true, the prompt optimizer will be enabled.
seedintegerNo-1-1 ~ 2147483647The random seed to use for the generation. -1 means a random seed will be used.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsobjectArray of URLs to the generated content (empty when status is not completed).
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.