Image to video

imageVideoSimplify submits an asynchronous generation and returns Content!. Use API key authentication, a ready image model, and an accessible source image. The example uses an existing media ID; uploaded and remix source inputs are alternatives for integrations that already provide those file references.

Animate an image

ImageToVideo

mutation ImageToVideo($metadata: SimpleImage2VideoContentMetadata!) {
  imageVideoSimplify(metadata: $metadata) {
    id
    task {
      id
      status
      progress { finishCode }
    }
  }
}

Variables

{
  "metadata": {
    "modelId": "<IMAGE_MODEL_ID>",
    "srcMediaId": "<IMAGE_MEDIA_ID>",
    "inputPrompt": "The subject turns toward the camera and smiles. Gentle camera push-in.",
    "durationInMilliseconds": 5000,
    "outputQuality": "ultra",
    "resolution": "FHD"
  }
}

Metadata

Field	Type / default	Meaning
`modelId`	`String!`	Required image model ID.
`srcMediaId`	`ID`	Existing source image media. Provide a source through this or an accepted uploaded/remix input.
`inputImage`	`UploadedImageFileInput`	Uploaded source image alternative.
`remixImage`	`RemixUploadedImageFileInput`	Remix source image alternative.
`inputPrompt`	`String`	Movement, camera, scene, and dialogue instructions.
`durationInMilliseconds`	`Long`, `5000` when omitted	Requested output duration in milliseconds. Supported values depend on the workflow.
`outputQuality`	`OutputQuality!`, `high`	`high`, `best`, `ultra`, or `ultraS`.
`resolution`	`VideoResolution`	Optional target resolution where supported.
`endImageMediaId`	`ID`	Existing end-frame image.
`inputEndImage`	`UploadedImageFileInput`	Uploaded end-frame alternative.
`remixEndImage`	`RemixUploadedImageFileInput`	Remix end-frame alternative.
`isFirstAndEndImageSame`	`Boolean!`, `false`	Use the same image for first and end frames.
`promptModifierIds`	`[ID!]`	Predefined prompt modifiers.
`promptBundleId`	`ID`	Selected prompt bundle.
`multiShotPrompt`	`[SingleShotPrompt!]`	Structured shot prompts where supported.
`elementIds`	`[ID!]`	Additional permitted visual or audio references.
`enableBgm`	`Boolean!`, `false`	Request background audio where supported.
`voiceModelId`	`ID`	Selected reference voice.
`voiceModelIds`	`[ID!]`	Additional ordered reference voices.

SD requires high; UHD requires ultra or ultraS. Reference and end-frame support depends on the selected settings. Choose one source representation appropriate to the integration rather than supplying conflicting alternatives.

Dialogue and voice references

Put spoken words in the prompt using the existing voice-section notation:

Voice section in a prompt

<voice-section|<voice|VOICE_MODEL_ID><mood|calm><script|Welcome to the studio.>>

Replace VOICE_MODEL_ID with an accessible selected voice model ID and include that same ID in voiceModelId or voiceModelIds. Selecting a voice supplies a reference; the prompt supplies the dialogue. The scalar voice is combined with the ordered list and duplicate IDs are removed. Multiple voices require a workflow that supports them, and voice references share audio-reference limits with elementIds. For shots, each SingleShotPrompt contains optional prompt, promptModifierIds, and duration. Use the shot format and timing supported by the selected workflow; do not assume every video quality accepts multi-shot input. Retain the returned IDs and follow tasks and results.

Get started

Core concepts

Workflows

GraphQL API

Usage and troubleshooting

Animate an image

Metadata

Dialogue and voice references

​Animate an image

​Metadata

​Dialogue and voice references

Animate an image

Metadata

Dialogue and voice references