LTX-2.3 22B Video Trainer

Name: Lightricks LTX-2.3 22B Video Trainer
Price: 9.6 USD
Availability: InStock
Author: Lightricks

lightricks/ltx23-video-trainer

Ltx23 Video Trainer by Lightricks - advanced AI model for training. Delivers high-quality results with fast inference, suitable for both creative and production workflows.

Use in agent Get API key

Base price: $9.60USD / run
Execution: async
Model type: image
Input fields: 25

Try the model

Playground

Open playground

Input

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Resolution(string)

Resolution to use for training. Higher resolutions require more memory. Allowed values: low, medium, high.

Learning Rate(number)

0.0000011

Learning rate for optimization. Higher values can lead to faster training but may cause overfitting. Range: 0.000001 to 1.

Frame Rate(integer)

860

Target frames per second for the video. Range: 8 to 60.

Validation(array)

A list of validation prompts to use during training. When providing an image, _all_ validation inputs must have an image.

Rank(integer)

The rank of the LoRA adaptation. Higher values increase capacity but use more memory. Allowed values: 8, 16, 32, 64, 128.

Audio Preserve Pitch(boolean)

When audio duration doesn't match video duration, stretch/compress audio without changing pitch. If disabled, audio is trimmed or padded with silence.

Number Of Frames(integer)

9121

Number of frames per training sample. Must satisfy frames % 8 == 1 (e.g., 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97). Range: 9 to 121.

Number Of Steps(integer)

10020000

The number of training steps. Range: 100 to 20000.

Validation Aspect Ratio(string)

The aspect ratio to use for validation. Allowed values: 16:9, 1:1, 9:16.

With Audio(boolean)

Enable joint audio-video training. If None (default), automatically detects whether input videos have audio. Set to True to force audio training, or False to disable.

Stg Scale(number)

STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0. Range: 0 to 3.

Split Input Duration Threshold(number)

160

The duration threshold in seconds. If a video is longer than this, it will be split into scenes. Range: 1 to 60.

Split Input Into Scenes(boolean)

If true, videos above a certain duration threshold will be split into scenes.

Validation Number Of Frames(integer)

9121

The number of frames in validation videos. Range: 9 to 121.

Validation Negative Prompt(string)

A negative prompt to use for validation.

Validation Frame Rate(integer)

860

Target frames per second for validation videos. Range: 8 to 60.

Generate Audio In Validation(boolean)

Whether to generate audio in validation samples.

Training Data Url(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL to zip archive with videos or images. Try to use at least 10 files, although more is better. **Supported video formats:** .mp4, .mov, .avi, .mkv **Supported image formats:** .png, .jpg, .jpeg Note: The dataset must contain ONLY videos OR ONLY images - mixed datasets are not supported. The archive can also contain text files with captions. Each text file should have the same name as the media file it corresponds to.

First Frame Conditioning P(number)

Probability of conditioning on the first frame during training. Higher values improve image-to-video performance. Range: 0 to 1.

Audio Normalize(boolean)

Normalize audio peak amplitude to a consistent level. Recommended for consistent audio levels across the dataset.

Trigger Phrase(string)

A phrase that will trigger the LoRA style. Will be prepended to captions during training.

Debug Dataset(boolean)

When enabled, the trainer returns a downloadable archive of your preprocessed training data for manual inspection. Use this to verify that your videos, images, and captions were processed correctly before committing to a full training run.

Auto Scale Input(boolean)

If true, videos will be automatically scaled to the target frame count and fps. This option has no effect on image datasets.

Validation Resolution(string)

The resolution to use for validation. Allowed values: low, medium, high.

OutputReady

Your output will appear here

Complete the inputs, then click Run.

Model card

Specifications

Pricing

Base price: $9.60 / run

Context & modalities

Input: Schema-defined
Output: image

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: Lightricks
Model ID: lightricks/ltx23-video-trainer
Execution: async
Base URL: https://api.sandbase.ai
API: Unified Run API
Endpoint: /v1/run

API README

LTX-2.3 22B Video Trainer

LTX-2.3 22B Video Trainer is a LTX route built for custom video-model training. It turns a curated training set and training controls into a reusable personalized video model, giving creators a focused endpoint instead of forcing one generic workflow across materially different production tasks. The route belongs to a family known for audio-visual timing, cinematic motion, and shot-level controllability, so it is best evaluated as a creative system for intentional shots and assets rather than as a one-click novelty generator.

Use this endpoint when the input contract and deliverable match that job exactly. Its documented controls include rank choices (8, 16, 32, 64, 128); stg_scale (STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0); frame_rate (Target frames per second for the video); resolution choices (low, medium, high). Together, these controls help teams plan predictable iterations, compare outputs under stable settings, and connect generation to iterative film, advertising, and social-video workflows without hiding the operational choices that shape the result.

Highlights

LTX-2.3 22B Video Trainer: dedicated custom model training. This exact route centers on custom model training; it uses the schema-defined source fields to separate its job from neighboring endpoints in the same family.
rank control. options 8, 16, 32, 64, 128; this setting provides a concrete lever for route-specific output planning.
stg_scale control. range 0 to 3; use it to build controlled comparisons without changing the rest of the request.
frame_rate control. range 8 to 60; together with the other documented fields, it supports repeatable review of this model path.

Pricing

Configuration	Price
Standard request	`$9.600000`

When to Use

Scenario	Why this model fits
Create the exact route output	Choose it when you need custom video-model training and already have a curated training set and training controls.
Develop controlled variations	Keep the main brief fixed while changing one documented setting at a time to compare motion, framing, quality, or asset behavior.
Build repeatable batches	Use a consistent request shape for catalog, campaign, storyboard, game-asset, or social-content production.
Preserve source intent	Prefer this route when the supplied reference material must remain the foundation of a reusable personalized video model.
Connect a media pipeline	Use asynchronous results in an automated review, approval, post-production, or asset-management workflow.

Prompt Guide

Start with the desired result, then describe the source relationship, subject action, composition or camera behavior, lighting, style, and timing. For custom video-model training, state what must remain stable as clearly as what should change. Use only fields exposed by the schema; the example below is structurally valid for this route.

{
  "rank": 32,
  "stg_scale": 1,
  "frame_rate": 25,
  "resolution": "medium",
  "validation": []
}

Technical Specs

Specification	Value
Model ID	`lightricks/ltx23-video-trainer`
Workflow	Custom video-model training
Required inputs	No fields marked required by schema
`rank`	`integer`; options: `8`, `16`, `32`, `64`, `128`
`stg_scale`	`number`; minimum: `0`; maximum: `3`
`frame_rate`	`integer`; minimum: `8`; maximum: `60`
`resolution`	`string`; options: `low`, `medium`, `high`
`validation`	`array`
`with_audio`	`boolean`
`aspect_ratio`	`string`; options: `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`
`debug_dataset`	`boolean`
`learning_rate`	`number`; minimum: `1e-06`; maximum: `1`
`trigger_phrase`	`string`

Related Models

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Unified Run API endpoint

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

Model ID

lightricks/ltx23-video-trainer

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "lightricks/ltx23-video-trainer",
  "rank": 32,
  "stg_scale": 1,
  "frame_rate": 25,
  "resolution": "medium",
  "validation": [],
  "debug_dataset": false,
  "learning_rate": 0.0002,
  "audio_normalize": true,
  "number_of_steps": 2000,
  "auto_scale_input": false,
  "number_of_frames": 89,
  "audio_preserve_pitch": true,
  "validation_frame_rate": 25,
  "validation_resolution": "high",
  "split_input_into_scenes": true,
  "validation_aspect_ratio": "1:1",
  "first_frame_conditioning_p": 0.5,
  "validation_negative_prompt": "worst quality, inconsistent motion, blurry, jittery, distorted",
  "validation_number_of_frames": 89,
  "generate_audio_in_validation": true,
  "split_input_duration_threshold": 30
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All image & video models

Model	Type	Default price	Released
LTX-2.3 22B Video TrainerThis model `Lightricks`	Image	$9.60 / run	Apr 14, 2026
LTX 2.3 Fast Image to Video `Lightricks`	Video	$0.36 / run	Mar 5, 2026
LTX 2.3 Fast Text to Video `Lightricks`	Video	$0.36 / run	Mar 5, 2026
LTX 2.3 Pro Image to Video `Lightricks`	Video	$0.48 / run	Mar 5, 2026
LTX 2.3 Pro Text to Video `Lightricks`	Video	$0.48 / run	Mar 5, 2026
LTX 2.3 Pro Retake `Lightricks`	Video	$0.50 / run	Mar 5, 2026

Questions

FAQ

How do I call Lightricks LTX-2.3 22B Video Trainer through SandBase?

Create a SandBase API key, then send requests with the model ID "lightricks/ltx23-video-trainer" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

Do I need a separate Lightricks account?

No. One SandBase API key and balance gives you access to Lightricks LTX-2.3 22B Video Trainer and the other models in the catalog; you do not need to sign up with Lightricks separately.