API reference · Lightricks

lightricks/ltx-2.3-quality/extend-video

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 IDlightricks/ltx-2.3-quality/extend-video

Input Schema

17 parameters · 1 required · 16 optional

Parameter	Type	Required	Description
`prompt`	string	Required	The prompt describing how the video should continue.
`seed`	integer	Optional	Random seed for reproducibility. If None, a random seed is chosen.
`video`	string	Optional	The URL of the video to extend.
`end_image`	string	Optional	Optional keyframe image for the far end of the extension: the final frame for forward extension, or the new first frame for backward extension.
`num_frames`	integer	Optional	The number of frames to generate for the extension segment, including num_context_frames of overlap with the source video. The new content adds approximately (num_frames - num_context_frames) / frames_per_second seconds. The stable generation budget caps the resolution x frames volume: at 24 fps roughly 20s at 480p-class, 11s at 720p-class and 5s at 1080p-class; a request above the budget returns a 422 (lower num_frames or use a smaller resolution). · Min: 9 · Max: 481 · Default: 121
`resolution`	string	Optional	The size of the generated video. 'auto' follows the source video size/aspect up to the LTX limits; the source is scaled to the final size in the stitched output. Sizes are 32px-aligned (e.g. 1920x1080 is delivered as 1888x1056). Higher resolutions reduce the maximum stable extension length; lower resolutions can run longer. · Options: auto, square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9 · Default: "auto" autosquare_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9
`video_quality`	string	Optional	The quality preset of the generated video. · Options: low, medium, high, maximum · Default: "high" lowmediumhighmaximum
`generate_audio`	boolean	Optional	Whether to generate new audio for the extension segment (crossfaded with the source audio at the seam). When disabled, the source video's own audio track is preserved and the extension stays silent. · Default: true
`guidance_scale`	number	Optional	Classifier-free guidance scale. The default is tuned for fast, high-quality generation. · Min: 1 · Max: 20 · Default: 1
`video_strength`	number	Optional	Conditioning strength of the source context frames. 1.0 keeps the overlap locked to the source for a seamless transition; lower values give the model more freedom. · Min: 0 · Max: 1 · Default: 1
`match_input_fps`	boolean	Optional	When enabled, the output FPS matches the source video's FPS (rounded to an integer and clamped to the supported range) instead of frames_per_second. · Default: true
`extend_direction`	string	Optional	Direction to extend the video. 'forward' continues from the end of the video, 'backward' generates a new beginning. · Options: forward, backward · Default: "forward" forwardbackward
`video_write_mode`	string	Optional	The write mode of the generated video. · Options: fast, balanced, small · Default: "balanced" fastbalancedsmall
`frames_per_second`	number	Optional	Frames per second of the generated video. · Min: 1 · Max: 60 · Default: 24
`end_image_strength`	number	Optional	Conditioning strength of the optional end keyframe. 1.0 = exact match, lower = more freedom for the model. · Min: 0 · Max: 1 · Default: 1
`num_context_frames`	integer	Optional	The number of source frames used as context/overlap for the extension. Snapped down to the LTX temporal grid (8k+1) and clamped to the frames available in the source video. · Min: 9 · Max: 121 · Default: 25
`num_inference_steps`	integer	Optional	Number of inference steps. Defaults to 15 and can be increased up to 30. · Min: 8 · Max: 30 · Default: 15

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

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

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

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": "lightricks/ltx-2.3-quality/extend-video",
  "video": "https://v3b.fal.media/files/b/0a8824b1/sdm0KfmenrlywesfzY1Y1_if6euPp1.mp4",
  "prompt": "Continue the scene naturally, maintaining the same style and motion.",
  "num_frames": 121,
  "resolution": "auto",
  "video_quality": "high",
  "generate_audio": true,
  "guidance_scale": 1,
  "video_strength": 1,
  "match_input_fps": true,
  "extend_direction": "forward",
  "video_write_mode": "balanced",
  "frames_per_second": 24,
  "end_image_strength": 1,
  "num_context_frames": 25,
  "num_inference_steps": 15
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Ltx 2.3 Quality