v1

latestOpenAPI 3.1.02026-08-04143345.6 KB

videoGeneration

Generate video from image

Animate a still image with realistic motion, depth, and audio. Provide a reference image plus a prompt describing the desired motion. The output preserves the visual identity of the source image.

Returns the generated video directly in the response. For an asynchronous version that returns a job to poll, see v2/image-to-video.

Billed per second of generated video. See Pricing.

post/v1/image-to-video

Headers

Authorizationstring required

API key authentication

Request body

image_uristring required

Image to be used as the first frame of the video. See Input Formats for supported formats and size limits.

promptstring required

Text description of how the image should be animated, can relate to the details in the image

model'ltx-2-fast' | 'ltx-2-pro' | 'ltx-2-3-fast' | 'ltx-2-3-pro' required

Model to use for generation. See Supported Models for details.

Deprecated: ltx-2-fast and ltx-2-pro are deprecated. See the LTX-2 Deprecation Notice.

durationinteger required

Video duration in seconds. See Supported Models for available durations per model.

fpsinteger

Frame rate in frames per second. See Supported Models for available FPS per model and resolution.

resolutionstring required

Output video resolution. See Supported Models for available resolutions per model.

generate_audioboolean

Generate audio for the video. When true, the generated video will include AI-generated audio matching the scene. When false, only silent video is generated.

last_frame_uristring

Image to be used as the last frame of the video. When provided, the video will interpolate between the first frame (image_uri) and this last frame. See Input Formats for supported formats and size limits.

Note: Only supported by ltx-2-3 models (ltx-2-3-fast, ltx-2-3-pro).

Apply camera motion effects to the generated video.

Response

Video generated successfully