Wan 2.6 Image to Video API

alibaba/wan-2.6/image-to-video

Wan 2.6 Image to Video animates single still images into 5–15 second 1080p high-definition videos, featuring first-frame animation, multi-shot camera progression, and precise trajectory control. It faithfully preserves the source image's facial identity, apparel textures, and lighting ambiance while adding expressive motion dynamics guided by your prompt.

Input

Prompt

480/5000

Image Urls

1/1

Required: 1 image. Playground supports JPG, PNG, WebP up to 10 MiB.

Resolution

Duration

Multi Shots

OutputReady

Examples

Animate the exact handmade paper theater. The little green paper dragon slowly unfolds both accordion-paper wings, holds them open and tilts its rounded head with curiosity. Keep all four feet planted, the silhouette intact and every surface visibly matte cut paper. Tiny natural paper-flex movement, subtle paper rustling, fixed front camera, playful stop-motion timing. Preserve the layered ochre and teal arches. No flying, new characters, text, music or cuts.

Continue from this exact first frame. The steam locomotive steadily moves left, forward in the direction its chimney faces across the viaduct, pulling the same three passenger cars. Wheels turn coherently on the fixed rails, white steam curls backward and disperses in the dry air. Slow lateral camera movement preserves the wide canyon composition and scale. Rhythmic wheel clatter and a brief soft steam hiss. Keep the arches, train geometry and landscape stable. One continuous shot, no titles, branding or music.

REST API Spec

Quick Start

Submit an endpoint request and poll for status. Replace example URLs with your accessible files.

Step 1: Configure API authentication

Obtain an API key from the dashboard and include Authorization: Bearer <API_KEY> in every request header.

Submission Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Auth Header: Authorization: Bearer VIDGO_API_KEY

Step 2: Submit a generation task

POST /api/generate/submit. Pass model and optional callback_url at the root level, with generation parameters inside input.

Request Payload

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "alibaba/wan-2.6/image-to-video",
  "input": {
    "prompt": "Continue naturally from this exact first frame. The astronaut gently pushes away from the fixed handrail with her right hand, then drifts slowly sideways in zero gravity, her body and clothing retaining their original shape. A subtle camera track follows her at the same distance; equipment remains fixed. Keep her face, blue flight suit, handrail and window consistent. A quiet ventilation hum and soft fabric movement. One uninterrupted shot, no speech, cuts, logos or captions.",
    "duration": 5,
    "resolution": "720p",
    "multi_shots": false,
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/alibaba/wan-2.6/image-to-video/v1/01/input.jpg"
    ]
  }
}
JSON
)

RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

CODE=$(printf '%s' "$RESPONSE" | jq -r '.code // empty')
if [ "$CODE" != "0" ] && [ "$CODE" != "200" ]; then
  printf 'API error: %s
' "$RESPONSE" >&2
  exit 1
fi
printf '%s
' "$RESPONSE"

Step 3: Poll for task completion

Poll status with task_id; continue while not_started or running, and stop on finished or failed. Read video URLs from data.files[].file_url on success, or data.error_message on failure.

Status Endpoint

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll status using task_id; continue while not_started or running, stop when finished or failed. On success, read data.files[].file_url; on failure, read data.error_message.

not_startedrunningfinishedfailed

Submission Response

{
  "code": 200,
  "data": {
    "task_id": "1QG7XQN3IDI7XD43",
    "status": "running",
    "created_time": "2026-09-21T17:29:36"
  }
}

Completed Response Data

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "finished",
    "files": [
      {
        "file_url": "https://storage.vidgo.ai/generated/video.mp4",
        "file_type": "video"
      }
    ],
    "created_time": "2026-08-22T10:00:00Z",
    "progress": 100,
    "error_message": null
  }
}

Complete end-to-end script example

Expand to view a production-ready script with retry logic, error handling, and timeout safeguards.

Complete end-to-end script example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "alibaba/wan-2.6/image-to-video",
  "input": {
    "prompt": "Continue naturally from this exact first frame. The astronaut gently pushes away from the fixed handrail with her right hand, then drifts slowly sideways in zero gravity, her body and clothing retaining their original shape. A subtle camera track follows her at the same distance; equipment remains fixed. Keep her face, blue flight suit, handrail and window consistent. A quiet ventilation hum and soft fabric movement. One uninterrupted shot, no speech, cuts, logos or captions.",
    "duration": 5,
    "resolution": "720p",
    "multi_shots": false,
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/alibaba/wan-2.6/image-to-video/v1/01/input.jpg"
    ]
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
BUSINESS_CODE=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
  printf 'Submit failed:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

START_TIME=$(date +%s)
POLL_DELAY=2
while true; do
  if [ $(( $(date +%s) - START_TIME )) -ge 600 ]; then
    printf 'Timed out after 600 seconds
' >&2
    exit 1
  fi
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
  BUSINESS_CODE=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.code // empty')
  if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
    printf 'Status request failed:
%s
' "$STATUS_RESPONSE" >&2
    exit 1
  fi

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep "$POLL_DELAY"
      if [ "$POLL_DELAY" -lt 10 ]; then POLL_DELAY=$((POLL_DELAY + 1)); fi
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Request Parameters (input object)

Supported image-to-video parameters inside the input object when submitting a POST request to /api/generate/submit:

Field	Type	Required	Default	Description
prompt	string	Yes	—	String. Trimmed before validation; 1–5,000 Unicode characters.
image_urls	array<string>	Yes	—	Array containing exactly one HTTP(S) image URL. For local uploads in the playground: JPG, PNG, or WebP, up to 10 MiB.
duration	integer	No	5	Integer. Output duration: 5, 10, 15 seconds.
resolution	string	No	720p	Output resolution: 720p or 1080p.
multi_shots	boolean	No	—	Optional boolean. Omit to leave the upstream setting unspecified. The playground starts with false. No additional charge.

Response Fields (query result)

Task details returned when polling GET /api/generate/status/{task_id}:

Field	Type	Description
code	integer	Business response code, 200 on success.
data.task_id	string	Globally unique asynchronous task identifier.
data.status	string	Execution status: not_started, running, finished, or failed.
data.files	array	Generated video files upon completion, each with file_url and file_type.
data.error_message	string \| null	Error description if task fails.

Task Lifecycle

Clients should inspect the status field and stop polling when reaching finished or failed:

not_started
Task received and queued for execution.
running
Generation is in progress.
finished
Generation complete; retrieve video URL from data.files.
failed
Generation failed; inspect data.error_message; deducted credits are refunded per standard policy.

Polling & Error Handling

Recommended Polling IntervalStart polling every 2–3 seconds, increasing to 5 seconds as the task continues, to avoid excessive requests.
Network Fluctuations & RetriesIf status polling encounters 5xx or timeouts, the task is still running; retry querying after a brief pause.
Asynchronous Webhook CallbackProvide callback_url at the root of the request payload to receive the completed task result automatically via POST.

Specifications

Specification	Value	Description
Model ID	alibaba/wan-2.6/image-to-video	Send this value in the root-level model field.
Duration	5, 10, 15s	Default is 5 seconds.
Resolution	720p / 1080p	Default is 720p.

View the Wan 2.6 Image to Video API docs

Wan 2.6 Image to Video

Wan 2.6 Image to Video is developed by Alibaba Tongyi Lab to animate still photos into coherent cinematic videos. By providing a single reference image as the starting visual frame along with a prompt describing desired movements, creators can generate 5, 10, or 15-second takes in up to 1080p resolution, with optional multi_shots camera transitions.

Why Choose This?

High-fidelity first-frame identity preservationAnchors directly onto the source image to preserve exact facial features, hairstyle, and intricate clothing patterns throughout the sequence.
Multi-shot scene evolutionEnable multi_shots to develop a single still image into dynamic multi-angle cinematography without losing character consistency.
Up to 1080p native full HD outputSupports 720p and 1080p resolution tiers to capture delicate skin tones, material reflections, and environmental depth.
Versatile 5–15 second durationsChoose 5, 10, or 15-second outputs to suit everything from quick looping micro-motions to sustained narrative sequences.
Clean API contract and playground testingRequires just one image URL and prompt; easily integrated into creative pipelines via standard asynchronous REST endpoints.

Parameters

Parameter	Requirement	Description
prompt	Required	String. Trimmed before validation; 1–5,000 Unicode characters.
image_urls	Required	Array containing exactly one HTTP(S) image URL. For local uploads in the playground: JPG, PNG, or WebP, up to 10 MiB.
duration	Optional	Integer. Output duration: 5, 10, 15 seconds. Default`51015`
resolution	Optional	Output resolution: 720p or 1080p. Default`720p1080p`
multi_shots	Optional	Optional boolean. Omit to leave the upstream setting unspecified. The playground starts with false. No additional charge. `truefalse`

How to Use

Upload reference imageProvide 1 clear image asset; playground supports JPG, PNG, or WebP up to 10 MiB, while API accepts the image_urls array.
Describe desired motionIn the prompt, detail how subjects move, how lighting evolves, and how the camera should track across the scene.
Select output durationChoose 5, 10, or 15 seconds based on narrative requirements, with 5 seconds as default.
Choose resolutionSelect 720p for rapid iteration or 1080p for full-definition delivery, with 720p as default.
Configure multi-shot modeSet multi_shots to true if you want the single image to evolve into multi-angle cinematic sequences.
Review credits and submitCheck estimated credit cost and click Run, or send an authenticated POST request to /api/generate/submit.
Poll status and save videoMonitor progress with task_id and download the final MP4 file once status reaches finished.

Pricing

Billed per generated video by output resolution and duration. Multiple shots do not add a surcharge. 1 credit = $0.005.

Usage	Rate	Details
720p · 5 seconds	80 credits / $0.40	Per video
720p · 10 seconds	160 credits / $0.80	Per video
720p · 15 seconds	240 credits / $1.20	Per video
1080p · 5 seconds	120 credits / $0.60	Per video
1080p · 10 seconds	240 credits / $1.20	Per video
1080p · 15 seconds	360 credits / $1.80	Per video

Best Use Cases

E-commerce product and model showcasesTransform studio catalog shots into dynamic fashion walks and product demonstration videos.
Digital avatars and character concept riggingBreathe life into illustrations, concept art, and game characters with natural breathing, blinks, and gestures.
Portrait and archival photo animationAnimate historical portraits and personal keepsakes with expressive facial subtleties and realistic lighting.
Photography motion cinemagraphsConvert architectural and landscape stills into vibrant timelapses with drifting clouds and flowing water.
Brand social campaign reelsTurn hero visual assets into high-resolution 1080p social teasers and promotional video ads.

Pro Tips

Use high-clarity source imagery: Clear subject separation, balanced contrast, and well-lit compositions yield the smoothest motion without distortion.
Reference initial image state in prompt: Starting your prompt with reference context (e.g. 'The woman in red turns smoothly...') helps align initial trajectory.
Match duration to motion magnitude: Use 5 seconds for subtle expressions or gentle panning; reserve 10 or 15 seconds for complex bodily actions.
Pair multi_shots with full-body stills: When providing medium or full shots, setting multi_shots=true produces cinematic shot-reverse-shot sequences.
Focus on active positive verbs: Guide movement using definitive action verbs like 'gracefully strides forward' or 'gentle breeze flutters jacket hem'.

Notes

Image input requirements: This endpoint strictly accepts exactly 1 image; image_urls array must contain one accessible HTTP(S) URL.
Playground upload limits: Web playground supports JPG, PNG, and WebP uploads up to 10 MiB per file.
Duration and pricing tiers: Supports 5, 10, and 15 seconds at 720p or 1080p; multi_shots mode adds no extra charge.
Asynchronous execution: POST submission returns task_id immediately; poll the status endpoint or supply callback_url for webhooks.

Wan 2.6 Image to Video API Frequently Asked Questions

What is the Wan 2.6 Image to Video API?

Wan 2.6 Image to Video is an Alibaba model for image-to-video generation. It animates a single static reference image and text prompt into 5–15 second, up to 1080p high-definition dynamic video with support for camera control and multi-shot transitions. Built on a Diffusion Transformer spatio-temporal architecture, it faithfully preserves the input image's subject identity, composition, and lighting while adding coherent physical motion. You can call it programmatically or try it from the playground above.

How many reference images does Wan 2.6 Image to Video accept?

This endpoint strictly accepts exactly 1 static image as the starting frame. When calling the API, provide 1 accessible HTTP(S) image URL in the image_urls array; the playground accepts JPG, PNG, or WebP files up to 10 MiB.

How does Wan 2.6 Image to Video maintain facial consistency?

The model leverages the initial image as a structural latent anchor to preserve facial proportions and expressions. Reinforcing clothing details in your prompt and directing gradual movement helps maintain strict character fidelity throughout the video.

Can Wan 2.6 Image to Video create multi-shot scenes from one photo?

Yes. Enabling the multi_shots parameter allows the model to transition between multiple camera perspectives while keeping the primary subject consistent, with no extra billing surcharge.

What durations does Wan 2.6 Image to Video support?

It supports durations of 5, 10, and 15 seconds, with 5 seconds as default. Use 5 seconds for subtle loops and character micro-gestures, and 10 or 15 seconds for continuous spatial moves.

Does generating 1080p in Wan 2.6 Image to Video alter the image aspect ratio?

No, it maintains your composition. Selecting 1080p enhances fine texture and edge definition while respecting the original framing, delivering production-grade clarity.

Should I use Wan 2.6 Image to Video to transfer motion from an existing clip?

If you want to transfer motion dynamics or aesthetic style from existing video footage, use the Wan 2.6 Reference to Video endpoint instead. Wan 2.6 Image to Video is tailored specifically for animating still images.