LTX-2 Video Trainer | Training

fal-ai/ltx2-video-trainer

Train LTX-2 for custom styles and effects.

Training

Commercial use

Schema

LLMs

Playground API

About

Run LTX-2 training.

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Please check the migration guide for more information.

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/ltx2-video-trainer", {
  input: {
    training_data_url: ""
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("fal-ai/ltx2-video-trainer", {
  input: {
    training_data_url: ""
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("fal-ai/ltx2-video-trainer", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("fal-ai/ltx2-video-trainer", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

training_data_url string* required

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.

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.

rank RankEnum

The rank of the LoRA adaptation. Higher values increase capacity but use more memory. Default value: "32"

Possible enum values: 8, 16, 32, 64, 128

number_of_steps integer

The number of training steps. Default value: 2000

learning_rate float

Learning rate for optimization. Higher values can lead to faster training but may cause overfitting. Default value: 0.0002

number_of_frames integer

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). Default value: 89

frame_rate integer

Target frames per second for the video. Default value: 25

resolution ResolutionEnum

Resolution to use for training. Higher resolutions require more memory. Default value: "medium"

Possible enum values: low, medium, high

aspect_ratio AspectRatioEnum

Aspect ratio to use for training. Default value: "1:1"

Possible enum values: 16:9, 1:1, 9:16

first_frame_conditioning_p float

Probability of conditioning on the first frame during training. Higher values improve image-to-video performance. Default value: 0.5

trigger_phrase string

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

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.

split_input_into_scenes boolean

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

split_input_duration_threshold float

The duration threshold in seconds. If a video is longer than this, it will be split into scenes. Default value: 30

validation list<Validation>

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

validation_negative_prompt string

A negative prompt to use for validation. Default value: "worst quality, inconsistent motion, blurry, jittery, distorted"

validation_number_of_frames integer

The number of frames in validation videos. Default value: 89

validation_resolution ValidationResolutionEnum

The resolution to use for validation. Default value: "high"

Possible enum values: low, medium, high

validation_aspect_ratio ValidationAspectRatioEnum

The aspect ratio to use for validation. Default value: "1:1"

Possible enum values: 16:9, 1:1, 9:16

stg_scale float

STG (Spatio-Temporal Guidance) scale. 0.0 disables STG. Recommended value is 1.0. Default value: 1

generate_audio_in_validation boolean

Whether to generate audio in validation samples. Default value: true

{
  "training_data_url": "",
  "rank": 32,
  "number_of_steps": 2000,
  "learning_rate": 0.0002,
  "number_of_frames": 89,
  "frame_rate": 25,
  "resolution": "medium",
  "aspect_ratio": "1:1",
  "first_frame_conditioning_p": 0.5,
  "trigger_phrase": "",
  "auto_scale_input": false,
  "split_input_into_scenes": true,
  "split_input_duration_threshold": 30,
  "validation": [],
  "validation_negative_prompt": "worst quality, inconsistent motion, blurry, jittery, distorted",
  "validation_number_of_frames": 89,
  "validation_resolution": "high",
  "validation_aspect_ratio": "1:1",
  "stg_scale": 1,
  "generate_audio_in_validation": true
}

Output#

video File* required

The URL to the validation videos, if any.

lora_file File* required

URL to the trained LoRA weights (.safetensors).

config_file File* required

Configuration used for setting up inference endpoints.

{
  "video": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  },
  "lora_file": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  },
  "config_file": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  }
}

Other types#

Validation#

prompt string* required

The prompt to use for validation.

image_url string

An image to use for image-to-video validation. If provided for one validation, all validation inputs must have an image.

File#

url string* required

The URL where the file can be downloaded from.

content_type string

The mime type of the file.

file_name string

The name of the file. It will be auto-generated if not provided.

file_size integer

The size of the file in bytes.

LTX-2 Video Trainer Training

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

Validation#

File#