LTX Video Trainer Training

fal-ai/ltx-video-trainer
Train LTX Video 0.9.7 for custom styles and effects.
Training
Commercial use

About

Runs 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

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/ltx-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"
});

3. Queue#

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/ltx-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/ltx-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/ltx-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);

Read more about file handling in our file upload guide.

5. Schema#

Input#

training_data_url string* required

URL to zip archive with images of a consistent style. Try to use at least 10 images and/or videos, although more is better.

In addition to images the archive can contain text files with captions. Each text file should have the same name as the image/video file it corresponds to.

rank RankEnum

The rank of the LoRA. Default value: "128"

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

number_of_steps integer

The number of steps to train for. Default value: 1000

number_of_frames integer

The number of frames to use for training. This is the number of frames per second multiplied by the number of seconds. Default value: 81

frame_rate integer

The target frames per second for the video. Default value: 25

resolution ResolutionEnum

The resolution to use for training. This is the resolution of the video. Default value: "medium"

Possible enum values: low, medium, high

aspect_ratio AspectRatioEnum

The aspect ratio to use for training. This is the aspect ratio of the video. Default value: "1:1"

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

learning_rate float

The rate at which the model learns. Higher values can lead to faster training, but over-fitting. Default value: 0.0002

trigger_phrase string

The phrase that will trigger the model to generate an image. Default value: ""

auto_scale_input boolean

If true, the input will be automatically scale the video to DEFAULT_NUM_FRAMES frames at 16fps.

split_input_into_scenes boolean

If true, input above a certain duration threshold will be split into scenes. If you provide captions for a split video, the caption will be applied to each scene. If you do not provide captions, scenes will be auto-captioned. 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. If you provide captions for a split video, the caption will be applied to each scene. If you do not provide captions, scenes will be auto-captioned. 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. Default value: ``

validation_negative_prompt string

A negative prompt to use for validation. Default value: "blurry, low quality, bad quality, out of focus"

validation_number_of_frames integer

The number of frames to use for validation. Default value: 81

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

validation_reverse boolean

If true, the validation videos will be reversed. This is useful for effects that are learned in reverse and then applied in reverse.

{
  "training_data_url": "",
  "rank": 128,
  "number_of_steps": 1000,
  "number_of_frames": 81,
  "frame_rate": 25,
  "resolution": "medium",
  "aspect_ratio": "1:1",
  "learning_rate": 0.0002,
  "trigger_phrase": "",
  "auto_scale_input": false,
  "split_input_into_scenes": true,
  "split_input_duration_threshold": 30,
  "validation": [],
  "validation_negative_prompt": "blurry, low quality, bad quality, out of focus",
  "validation_number_of_frames": 81,
  "validation_resolution": "high",
  "validation_aspect_ratio": "1:1"
}

Output#

video File* required

The URL to the validations video.

lora_file File* required

URL to the trained LoRA weights.

config_file File* required

Configuration used for setting up the 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.