SandBaseSandBase
API reference · Alibaba

alibaba/wan/2.6/image-to-video/flash

Integrate this model through SandBase's unified API, with production-ready schemas and examples.

VIDEOAsyncOpen model
Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run
Model IDalibaba/wan/2.6/image-to-video/flash
01

Input Schema

7 parameters · 2 required · 5 optional

ParameterTypeRequiredDescription
imagestringRequiredURL of the image to use as the first frame. Must be publicly accessible or base64 data URI. Image dimensions must be between 240 and 7680.
promptstringRequiredThe text prompt describing the desired video motion. Max 800 characters. · Min length: 1
seedintegerOptionalRandom seed for reproducibility. If None, a random seed is chosen.
audiostringOptional URL of the audio to use as the background music. Must be publicly accessible. Limit handling: If the audio duration exceeds the duration value (5, 10, or 15 seconds), the audio is truncated to the first N seconds, and the rest is discarded. If the audio is shorter than the video, the remaining part of the video will be silent. For example, if the audio is 3 seconds long and the video duration is 5 seconds, the first 3 seconds of the output video will have sound, and the last 2 seconds will be silent. - Format: WAV, MP3. - Duration: 3 to 30 s. - File size: Up to 15 MB.
durationintegerOptionalDuration of the generated video in seconds. Choose between 5, 10 or 15 seconds. · Options: 5, 10, 15 · Default: 5
51015
resolutionstringOptionalVideo resolution. Valid values: 720p, 1080p · Options: 720p, 1080p · Default: "1080p"
720p1080p
multi_shotsbooleanOptionalWhen true, enables intelligent multi-shot segmentation. Only active when enable_prompt_expansion is True. Set to false for single-shot generation. · Default: false
02

Output Schema

FieldTypeDescription
idstringUnique identifier for the generation task
statusstringTask status: pending, running, completed, failed, timeout
modelstringModel used for the generation
outputsarrayArray of output items
outputs[].urlstringURL of the generated artifact
outputs[].content_typestringMIME type (e.g. image/png, video/mp4)
errorobject | nullError details if failed, null on success
error.typestringMachine-readable error type code
error.messagestringHuman-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

  1. Submit — POST to /v1/run, receive an id
  2. Poll — GET /v1/run/{id} until status is completed, failed, or timeout
  3. Retrieve — Read outputs from the completed response
03

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "alibaba/wan/2.6/image-to-video/flash",
  "image": "https://static.sandbase.ai/examples/bfl/flux-2/dev/edit/input_images_0.png",
  "prompt": "A comedic cinematic demo where typed prompts physically transform reality. Photoreal, strong match cuts, coherent main character, no subtitles.\n\nShot 1 [0-4s] Continue from first frame. The creator presses \"PRINT\". The machine clunks like a spaceship. Creator whispers: \"Okay… I'm pressing enter.\"\nShot 2 [4-8s] Smash cut: the printed paper flies into the air and unfolds into a full desert canyon scene around the desk, like reality is being unrolled. Creator says: \"Wait—my prompt has physics?\"\nShot 3 [8-12s] Hard cut: the paper tears and reveals a tropical jungle behind it, perfectly lit, cinematic sun. Creator laughs: \"This is exactly why we do AI.\"\nShot 4 [12-15s] Hard cut back to studio. The printer prints a final line (not shown clearly). Creator looks to camera: \"Multi-scene. Single prompt.\"",
  "duration": 5,
  "resolution": "1080p",
  "multi_shots": false
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"
← Back to Wan 2.6 Image to Video Flash