fal Assets is now live!
Docs
Log-inSign-up

fal-ai/ltx-2.3-quality/reference-video-to-video/lora

Generate high-quality video with audio from reference video, text and images using LTX-2.3 and custom LoRA
Inference
Commercial use
Schema
LLMs
PlaygroundAPIExamples

Table of contents

About

Reference Video To Video Lora

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-2.3-quality/reference-video-to-video/lora", {
  input: {
    prompt: "A dancer in a flowing red dress against a black backdrop, studio lighting, cinematic.",
    video_url: "https://v3b.fal.media/files/b/0a8824b1/sdm0KfmenrlywesfzY1Y1_if6euPp1.mp4",
    loras: [{
      path: "https://example.com/path/to/lora.safetensors",
      scale: 1,
      transformer: "both"
    }]
  },
  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-2.3-quality/reference-video-to-video/lora", {
  input: {
    prompt: "A dancer in a flowing red dress against a black backdrop, studio lighting, cinematic.",
    video_url: "https://v3b.fal.media/files/b/0a8824b1/sdm0KfmenrlywesfzY1Y1_if6euPp1.mp4",
    loras: [{
      path: "https://example.com/path/to/lora.safetensors",
      scale: 1,
      transformer: "both"
    }]
  },
  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-2.3-quality/reference-video-to-video/lora", {
  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-2.3-quality/reference-video-to-video/lora", {
  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#

prompt string* required

The prompt to guide generation.

video_url string* required

The URL of the reference video that supplies motion/structure.

control_video_url string

Optional pre-computed control video (e.g. an already-rendered depth / edge / pose composite). When provided together with skip_control_preprocess, the built-in control estimation is skipped and this video is used directly as the control signal, resampled to the output resolution and frame count.

skip_control_preprocess boolean

Skip the built-in control estimation (depth / edge / pose) and use control_video_url directly as the control signal. Requires control_video_url; ignored if it is not set. With resolution='auto', the output follows the source video size/aspect up to the LTX limits. Explicit resolutions are honored and 64-aligned so the RGB video and control video stay matched.

preserve_original_video boolean

True video-to-video: the base video_url is used as the generation's starting point, while control_video_url still drives the structure. The amount of the original preserved is controlled by strength (denoise): lower strength keeps more of the original video's pixels. Requires skip_control_preprocess, video_url and control_video_url. Default off leaves the standard control path unchanged.

image_url string

Optional reference image for style/character anchoring. This is the FIRST-frame keyframe.

mid_image_url string

Optional middle-frame keyframe image. When set, the look/appearance is anchored to this image around the middle of the clip (in addition to image_url at the start), so the appearance follows a moving camera instead of drifting. Requires image_url.

end_image_url string

Optional last-frame keyframe image. When set, the look/appearance is anchored to this image at the end of the clip. Useful for shots where the camera travels to a different place than the start image. Requires image_url.

video_strength float

Video conditioning strength. Lower values give the model more freedom to change the reference video motion/structure. Default value: 0.6

strength float

Sampler denoise strength for reference-video-to-video. With preserve_original_video on, this is the video-to-video amount: lower values keep more of the original video's pixels (e.g. 0.5 = keep ~50%), 1.0 fully regenerates. Without preserve_original_video it only trims the denoise schedule. Default value: 1

num_frames integer

The number of output frames to generate. For this IC-LoRA endpoint, very long requests are automatically capped by a resolution-dependent stability budget: 720p-class outputs are capped at 150 frames, while smaller outputs can run longer. Default value: 121

resolution ImageSize | Enum

The size of the generated video. In direct-control mode (skip_control_preprocess with control_video_url), 'auto' follows the source video size/aspect up to the LTX limits and explicit sizes are honored with 64px alignment. In the built-in control estimation mode, the output stays near the official control workflow size. Higher resolutions reduce the maximum stable frame count; lower resolutions can run longer. Default value: auto

Possible enum values: auto, square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

Note: For custom image sizes, you can pass the width and height as an object:

"image_size": {
  "width": 1280,
  "height": 720
}
frames_per_second float

Frames per second of the generated video. Default value: 24

num_inference_steps integer

Number of inference steps. Defaults to 15 and can be increased up to 30. Default value: 15

guidance_scale float

Classifier-free guidance scale. The default is tuned for fast, high-quality generation. Default value: 1

generate_audio boolean

Whether to include audio in the returned video. When disabled, the final MP4 is returned without an audio track. Default value: true

negative_prompt string

The negative prompt to steer generation away from. Default value: "color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards"

seed integer

Random seed for reproducibility. If None, a random seed is chosen.

enable_prompt_expansion boolean

Whether to enable prompt expansion. Default value: true

enable_safety_checker boolean

Whether to enable the safety checker. Default value: true

video_quality VideoQualityEnum

The quality preset of the generated video. Default value: "high"

Possible enum values: low, medium, high, maximum

video_write_mode VideoWriteModeEnum

The write mode of the generated video. Default value: "balanced"

Possible enum values: fast, balanced, small

sync_mode boolean

If True, the media is returned as a data URI inline in the response. Useful for short-lived requests and tests.

loras list<LoRAInput>* required

Up to 3 LoRAs to apply on top of LTX-2.3. Each path is downloaded through the registry SSRF-safe downloader before it is loaded. Max size: 3 GB per LoRA.

{
  "prompt": "A dancer in a flowing red dress against a black backdrop, studio lighting, cinematic.",
  "video_url": "https://v3b.fal.media/files/b/0a8824b1/sdm0KfmenrlywesfzY1Y1_if6euPp1.mp4",
  "video_strength": 0.6,
  "strength": 1,
  "num_frames": 121,
  "resolution": "auto",
  "frames_per_second": 24,
  "num_inference_steps": 15,
  "guidance_scale": 1,
  "generate_audio": true,
  "negative_prompt": "color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards",
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "video_quality": "high",
  "video_write_mode": "balanced",
  "loras": [
    {
      "path": "https://example.com/path/to/lora.safetensors",
      "scale": 1,
      "transformer": "both"
    }
  ]
}

Output#

video File* required

The generated video.

seed integer* required

The seed actually used for generation.

prompt string* required

The prompt used for generation (after any expansion).

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

Other types#

ImageSize#

width integer

The width of the generated image. Default value: 512

height integer

The height of the generated image. Default value: 512

VideoFile#

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.

width integer

The width of the video

height integer

The height of the video

fps float

The FPS of the video

duration float

The duration of the video

num_frames integer

The number of frames in the video

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.

Related Models