LTX-2 19B Distilled API Reference

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to lightricks/ltx-2-19b/distilled/video-to-video/lora.

Default: lightricks/ltx-2-19b/distilled/video-to-video/lora

stringpromptrequired

The prompt to generate the video from.

stringimagerequired

An optional URL of an image to use as the first frame of the video.

Optional<string>end_image

The URL of the image to use as the end of the video.

Optional<string>video

The URL of the video to generate the video from.

Optional<string>audio

An optional URL of an audio to use as the audio for the video. If not provided, any audio present in the input video will be used.

Optional<boolean>generate_audio

Whether to generate audio for the video.

Default: true

Optional<number>video_strength

Video conditioning strength. Lower values represent more freedom given to the model to change the video content.

Range: 0 to 1

Default: 1

Optional<string>preprocessor

The preprocessor to use for the video. When a preprocessor is used and `ic_lora_type` is set to `match_preprocessor`, the IC-LoRA will be loaded based on the preprocessor type.

Allowed values: depth, canny, pose, none

Default: none

Optional<number>audio_strength

Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content.

Range: 0 to 1

Default: 1

Optional<number>image_strength

The strength of the image to use for the video generation.

Range: 0 to 1

Default: 1

Optional<string>ic_lora

The type of IC-LoRA to load. In-Context LoRA weights are used to condition the video based on edge, depth, or pose videos. Only change this from `match_preprocessor` if your videos are already preprocessed (or you are using the detailer.)

Allowed values: match_preprocessor, canny, depth, pose, detailer, none

Default: match_preprocessor

Optional<number>ic_lora_scale

The scale of the IC-LoRA to use. This allows you to control the strength of the IC-LoRA.

Range: 0 to 1

Default: 1

Optional<number>end_image_strength

The strength of the end image to use for the video generation.

Range: 0 to 1

Default: 1

Optional<integer>seed

The seed for the random number generator.

Optional<array>loras

Request parameter supported by this model.

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: video-to-video

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request curl -X POST https://api.sandbase.ai/v1/run \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "lightricks/ltx-2-19b/distilled/video-to-video/lora", "prompt": "black-and-white video, a cowboy walks through a dusty town, film grain", "image": "https://static.sandbase.ai/examples/input.png", "video": "https://static.sandbase.ai/examples/lightricks/ltx-2-19b/distilled/video-to-video/lora/input_video_0.mp4", "audio": "https://static.sandbase.ai/examples/input.mp3" }' # 2. If the response is still running, poll the returned id curl https://api.sandbase.ai/v1/run/run_abc123 \ -H "Authorization: Bearer $SANDBASE_API_KEY"