LTX Video-0.9.7 13B Distilled | Video to Video

fal-ai/ltx-video-13b-distilled/multiconditioning

Generate videos from prompts, images, and videos using LTX Video-0.9.7 13B Distilled and custom LoRA

Inference

Commercial use

Schema

Playground API

About

Generate a video from a prompt and any number of images and video.

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/ltx-video-13b-distilled/multiconditioning", {
  input: {
    prompt: "A vibrant, abstract composition featuring a person with outstretched arms, rendered in a kaleidoscope of colors against a deep, dark background. The figure is composed of intricate, swirling patterns reminiscent of a mosaic, with hues of orange, yellow, blue, and green that evoke the style of artists such as Wassily Kandinsky or Bridget Riley. The camera zooms into the face striking portrait of a man, reimagined through the lens of old-school video-game graphics. The subject's face is rendered in a kaleidoscope of colors, with bold blues and reds set against a vibrant yellow backdrop. His dark hair is pulled back, framing his profile in a dramatic pose."
  },
  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/ltx-video-13b-distilled/multiconditioning", {
  input: {
    prompt: "A vibrant, abstract composition featuring a person with outstretched arms, rendered in a kaleidoscope of colors against a deep, dark background. The figure is composed of intricate, swirling patterns reminiscent of a mosaic, with hues of orange, yellow, blue, and green that evoke the style of artists such as Wassily Kandinsky or Bridget Riley. The camera zooms into the face striking portrait of a man, reimagined through the lens of old-school video-game graphics. The subject's face is rendered in a kaleidoscope of colors, with bold blues and reds set against a vibrant yellow backdrop. His dark hair is pulled back, framing his profile in a dramatic pose."
  },
  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-13b-distilled/multiconditioning", {
  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-13b-distilled/multiconditioning", {
  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#

prompt string* required

Text prompt to guide generation

negative_prompt string

Negative prompt for generation Default value: "worst quality, inconsistent motion, blurry, jittery, distorted"

loras list<LoRAWeight>

LoRA weights to use for generation Default value: ``

resolution ResolutionEnum

Resolution of the generated video (480p or 720p). Default value: "720p"

Possible enum values: 480p, 720p

aspect_ratio AspectRatioEnum

The aspect ratio of the video. Default value: "auto"

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

seed integer

Random seed for generation

number_of_frames integer

The number of frames in the video. Default value: 121

first_pass_number_of_steps integer

Number of inference steps during the first pass Default value: 8

first_pass_skip_final_steps integer

Number of inference steps to skip in the final steps of the first pass. By skipping some steps at the end, the first pass can focus on larger changes instead of smaller details. Default value: 1

second_pass_number_of_steps integer

Number of inference steps during the second pass Default value: 8

second_pass_skip_initial_steps integer

The number of inference steps to skip in the initial steps of the second pass. By skipping some steps at the beginning, the second pass can focus on smaller details instead of larger changes. Default value: 5

frame_rate integer

The frame rate of the video. Default value: 30

expand_prompt boolean

Whether to expand the prompt using a language model.

reverse_video boolean

Whether to reverse the video.

enable_safety_checker boolean

Whether to enable the safety checker. Default value: true

constant_rate_factor integer

The constant rate factor (CRF) to compress input media with. Compressed input media more closely matches the model's training data, which can improve motion quality. Default value: 35

images list<ImageConditioningInput>

URL of images to use as conditioning Default value: ``

videos list<VideoConditioningInput>

Videos to use as conditioning Default value: ``

{
  "prompt": "A vibrant, abstract composition featuring a person with outstretched arms, rendered in a kaleidoscope of colors against a deep, dark background. The figure is composed of intricate, swirling patterns reminiscent of a mosaic, with hues of orange, yellow, blue, and green that evoke the style of artists such as Wassily Kandinsky or Bridget Riley. The camera zooms into the face striking portrait of a man, reimagined through the lens of old-school video-game graphics. The subject's face is rendered in a kaleidoscope of colors, with bold blues and reds set against a vibrant yellow backdrop. His dark hair is pulled back, framing his profile in a dramatic pose.",
  "negative_prompt": "worst quality, inconsistent motion, blurry, jittery, distorted",
  "loras": [],
  "resolution": "720p",
  "aspect_ratio": "auto",
  "number_of_frames": 121,
  "first_pass_number_of_steps": 8,
  "first_pass_skip_final_steps": 1,
  "second_pass_number_of_steps": 8,
  "second_pass_skip_initial_steps": 5,
  "frame_rate": 30,
  "expand_prompt": false,
  "reverse_video": false,
  "enable_safety_checker": true,
  "constant_rate_factor": 35,
  "images": [
    {
      "strength": 1,
      "start_frame_num": 0,
      "image_url": "https://storage.googleapis.com/falserverless/model_tests/ltx/NswO1P8sCLzrh1WefqQFK_9a6bdbfa54b944c9a770338159a113fd.jpg"
    },
    {
      "strength": 1,
      "start_frame_num": 120,
      "image_url": "https://storage.googleapis.com/falserverless/model_tests/ltx/YAPOGvmS2tM_Krdp7q6-d_267c97e017c34f679844a4477dfcec38.jpg"
    }
  ],
  "videos": []
}

Output#

video File* required

The generated video file.

prompt string* required

The prompt used for generation.

seed integer* required

The seed used for generation.

{
  "video": {
    "url": "https://storage.googleapis.com/falserverless/example_outputs/ltxv-multiconditioning-output.mp4"
  },
  "prompt": "A vibrant, abstract composition featuring a person with outstretched arms, rendered in a kaleidoscope of colors against a deep, dark background. The figure is composed of intricate, swirling patterns reminiscent of a mosaic, with hues of orange, yellow, blue, and green that evoke the style of artists such as Wassily Kandinsky or Bridget Riley. The camera zooms into the face striking portrait of a man, reimagined through the lens of old-school video-game graphics. The subject's face is rendered in a kaleidoscope of colors, with bold blues and reds set against a vibrant yellow backdrop. His dark hair is pulled back, framing his profile in a dramatic pose."
}

Other types#

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.

file_data string

File data

LoRAWeight#

path string* required

URL or path to the LoRA weights.

weight_name string

Name of the LoRA weight. Only used if path is a HuggingFace repository, and is only required when the repository contains multiple LoRA weights.

scale float

Scale of the LoRA weight. This is a multiplier applied to the LoRA weight when loading it. Default value: 1

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#

File#

LoRAWeight#

Related Models

LTX Video-0.9.7 13B Distilled Video to Video

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#

File#

LoRAWeight#

Related Models