lightricks/ltx-2.3-22b/distilled/video-to-video/lora

Name: LTX-2.3 22B Distilled
Author: Lightricks

Ltx 2.3 22b Distilled Video To Video is Lightricks's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.

Input

Prompt(string)

The prompt to generate the video from.

Video URL(string)

The URL of the video to generate the video from.

Generate Audio(boolean)

Whether to generate audio for the video.

Seed(integer)

The seed for the random number generator.

Video Strength(number)

Video conditioning strength. Lower values represent more freedom given to the model to change the video content. Range: 0 to 1.

Audio Strength(number)

Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content. Range: 0 to 1.

Loras(array)

Enter a JSON array.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDlightricks/ltx-2.3-22b/distilled/video-to-video/lora

Input Schema

7 parameters · 1 required · 6 optional

Parameter	Type	Required	Description
`prompt`	string	Required	The prompt to generate the video from.
`seed`	integer	Optional	The seed for the random number generator.
`loras`	array	Optional	—
`video`	string	Optional	The URL of the video to generate the video from.
`audio_strength`	number	Optional	Audio conditioning strength. Lower values represent more freedom given to the model to change the audio content. · Min: 0 · Max: 1 · Default: 0.01
`generate_audio`	boolean	Optional	Whether to generate audio for the video. · Default: true
`video_strength`	number	Optional	Video conditioning strength. Lower values represent more freedom given to the model to change the video content. · Min: 0 · Max: 1 · Default: 0.01

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-2.3-22b/distilled/video-to-video/lora",
  "video": "https://static.sandbase.ai/examples/lightricks/ltx-2.3-22b/distilled/video-to-video/lora/input_video_0.mp4",
  "prompt": "style: cinematic/realistic. A man wearing a baseball cap walks through a modern town. He holds a coffee cup.",
  "audio_strength": 0.01,
  "generate_audio": true,
  "video_strength": 0.01
}'

# 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 22B Distilled

API README

LTX-2.3 22B Distilled

LTX-2.3 22B Distilled is a video transformation with custom LoRA adapters endpoint in the LTX 2.3 family. It is built for creators who need to turn a concrete creative brief into a controlled visual sequence: the request establishes the source material, the intended subject behavior, the camera language, and the atmosphere of the finished shot. The distilled, LoRA-enabled route keeps that workflow explicit instead of hiding its input assumptions behind a generic video-generation label.

In practice, this route accepts video, loras as creative context and exposes generate audio, video strength for delivery planning. That makes it suitable for shot-based pipelines where teams must preserve a source, direct a transformation, or control the final format without losing sight of the model's central task. Write prompts as a compact shot plan—subject, action, setting, camera, light, and timing—then use the structured fields for constraints that should remain deterministic across iterations.

Highlights

Whole-clip transformation. The video input is the visual timeline to reinterpret; the prompt specifies the desired treatment and motion outcome.
Adjustable source fidelity. video_strength balances preservation of the input clip against freedom to transform it.
Soundtrack-aware processing. Existing or supplied audio can condition the result, with audio_strength controlling its influence.
Route-specific LoRA conditioning. The loras array adds learned styling or concepts to this video to video workflow without replacing its required source inputs. For lightricks/ltx-2.3-22b/distilled/video-to-video/lora, this task-specific control is documented alongside the route’s own required inputs.

Pricing

Billing unit	Price
Base request	`$0.001405`

When to Use

Scenario	Recommendation
Choose this route	Use it when the deliverable specifically calls for video transformation with custom LoRA adapters, rather than a neighboring generation mode.
Prepare the source	Provide video in the format described by the request schema.
Direct the shot	Describe the subject, action, environment, camera movement, lighting, and temporal progression in that order.
Control continuity	Use endpoint frames, reference media, strength, or audio controls when those fields are available instead of burying hard constraints in prose.
Plan delivery	Set duration, frame count, resolution, and aspect ratio explicitly when the schema exposes them, then compare iterations with a stable seed where supported.

Prompt Guide

For video transformation with custom LoRA adapters, describe one coherent shot rather than a list of visual keywords. Put the main subject and action first, follow with location and staging, then add camera movement, lens or framing, lighting, mood, and any timed change. Keep URLs and hard delivery choices in their dedicated fields.

{
  "prompt": "style: cinematic/realistic. A man wearing a baseball cap walks through a modern town. He holds a coffee cup.",
  "generate_audio": true,
  "video": "https://static.sandbase.ai/examples/lightricks/ltx-2.3-22b/distilled/video-to-video/lora/input_video_0.mp4"
}

Technical Specs

Specification	Value
Model ID	`lightricks/ltx-2.3-22b/distilled/video-to-video/lora`
Required inputs	`prompt`
Execution	Asynchronous generation job
Request controls	7 documented fields
Output	`url`, `content_type`

Request fields

Field	Type and constraints
`seed`	integer; Optional
`loras`	array; Optional
`video`	string; Optional
`prompt`	string; Required
`audio_strength`	number; Optional; Range: 0–1; Default: 0.01
`generate_audio`	boolean; Optional; Default: true
`video_strength`	number; Optional; Range: 0–1; Default: 0.01