luma/agent/ray/v3.2/reframe

Luma Ray 3.2 reframes an existing video into a new aspect ratio guided by a text prompt, preserving the original footage frame-for-frame while controlling resolution and outpainting the surrounding canvas.

Inference

Commercial use

Partner

Schema

LLMs

Playground API

1. Calling the API

2. Authentication

API Key

3. Queue

4. Files

5. Schema

About

ray-3.2 aspect-ratio reframe via the Luma Agents API.

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("luma/agent/ray/v3.2/reframe", {
  input: {
    prompt: "Extend the scene into cinematic widescreen with matching lighting and background detail.",
    video_url: "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
    aspect_ratio: "21:9"
  },
  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("luma/agent/ray/v3.2/reframe", {
  input: {
    prompt: "Extend the scene into cinematic widescreen with matching lighting and background detail.",
    video_url: "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
    aspect_ratio: "21:9"
  },
  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("luma/agent/ray/v3.2/reframe", {
  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("luma/agent/ray/v3.2/reframe", {
  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 describing the content to paint into the newly exposed canvas area when reframing to the target aspect ratio.

video_url string* required

URL of the source video to reframe (must be 30 seconds or less).

aspect_ratio AspectRatioEnum* required

Target aspect ratio for the reframed video.

Possible enum values: 3:4, 4:3, 1:1, 9:16, 16:9, 21:9

resolution ResolutionEnum

Resolution of the reframed video. Higher resolutions cost more. Default value: "540p"

Possible enum values: 540p, 720p, 1080p

source_position RayReframeSourcePosition

Optional normalized source rectangle controlling where the source video sits in the output canvas.

{
  "prompt": "Extend the scene into cinematic widescreen with matching lighting and background detail.",
  "video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4",
  "aspect_ratio": "21:9",
  "resolution": "540p"
}

Output#

video File* required

The generated video.

exr_file File

The generated EXR sidecar when exr_export is true. This may be a single EXR file or a ZIP package depending on Luma's export shape.

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

Other types#

RayReframeSourcePosition#

x_norm float* required

Left edge of the source rectangle as a fraction of output width.

y_norm float* required

Top edge of the source rectangle as a fraction of output height.

w_norm float* required

Width of the source rectangle as a fraction of output width.

h_norm float* required

Height of the source rectangle as a fraction of output height.

TextToImageRequest#

prompt string* required

Text prompt describing the image to generate.

aspect_ratio Enum

Aspect ratio of the generated image.

Possible enum values: 3:1, 2:1, 16:9, 3:2, 1:1, 2:3, 9:16, 1:2, 1:3

style StyleEnum

Visual style of the generated image. Default value: "auto"

Possible enum values: auto, manga

output_format Enum

Encoding format of the generated image.

Possible enum values: png, jpeg

enable_web_search boolean

When true, the model may consult the web for references.

reference_image_urls list<string>

Optional list of reference image URLs used to guide the generation.

RayTextToVideoRequest#

prompt string* required

Text prompt describing the video to generate.

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video. Default value: "16:9"

Possible enum values: 3:4, 4:3, 1:1, 9:16, 16:9, 21:9

resolution ResolutionEnum

Resolution of the generated video. Higher resolutions cost more. Default value: "540p"

Possible enum values: 540p, 720p, 1080p

duration DurationEnum

Duration of the generated video. Default value: "5s"

Possible enum values: 5s, 10s

loop boolean

Generate a seamless loop. Only valid for 5s, standard-dynamic-range generations without an end frame.

hdr boolean

Generate an HDR-encoded MP4. Requires HDR access on the account and a resolution of 720p or 1080p; not supported with 10s or loop.

exr_export boolean

Also export an EXR file alongside the MP4. Requires hdr=true and HDR access.

reference_image_urls list<string>

Optional list of reference image URLs used to guide the generation.

RayImageToVideoRequest#

prompt string* required

Text prompt describing the motion/scene to generate.

image_url string* required

URL of the image used as the first frame of the video.

end_image_url string

Optional URL of an image used as the last frame. When set, the model interpolates between image_url and end_image_url.

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video. Default value: "16:9"

Possible enum values: 3:4, 4:3, 1:1, 9:16, 16:9, 21:9

resolution ResolutionEnum

Resolution of the generated video. Higher resolutions cost more. Default value: "540p"

Possible enum values: 540p, 720p, 1080p

duration string

Duration of the generated video. Image-to-video supports 5s. Default value: "5s"

loop boolean

Generate a seamless loop. Only valid for standard-dynamic-range generations without an end frame.

hdr boolean

Generate an HDR-encoded MP4. Requires HDR access on the account and a resolution of 720p or 1080p; not supported with loop.

exr_export boolean

Also export an EXR file alongside the MP4. Requires hdr=true and HDR access.

reference_image_urls list<string>

Optional list of reference image URLs used to guide the generation.

RayVideoToVideoRequest#

prompt string* required

Text prompt describing how to edit the source video.

video_url string* required

URL of the source video to edit.

start_image_url string

Optional URL of an image to use as the edited video's first frame — e.g. a restyled version of the source's opening frame to steer the look of the edit. Leave unset to let the model derive the first frame from the source video.

resolution ResolutionEnum

Resolution of the edited video. Higher resolutions cost more. Default value: "540p"

Possible enum values: 540p, 720p, 1080p

duration DurationEnum

Duration of the edited video. Default value: "5s"

Possible enum values: 5s, 10s

edit_strength Enum

How closely the edit preserves the source video. 'adhere_' stays closest to the source, 'flex_' is balanced, and 'reimagine_*' diverges most. Leave unset to use Luma's default. Cannot be combined with auto_controls.

Possible enum values: adhere_1, adhere_2, adhere_3, flex_1, flex_2, flex_3, reimagine_1, reimagine_2, reimagine_3

auto_controls boolean

Let the model derive the edit conditioning schedule from the source video. Cannot be combined with edit_strength.

hdr boolean

Generate an HDR-encoded MP4. Requires HDR access on the account and a resolution of 720p or 1080p.

exr_export boolean

Also export an EXR file alongside the MP4. Requires hdr=true and HDR access.

ImageEditRequest#

prompt string* required

Text prompt describing the edit to apply.

image_url string* required

URL of the source image to edit.

style StyleEnum

Visual style of the edited image. Default value: "auto"

Possible enum values: auto, manga

output_format Enum

Encoding format of the edited image.

Possible enum values: png, jpeg

reference_image_urls list<string>

Optional list of reference image URLs used to guide the edit.

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.

luma/agent/ray/v3.2/reframe

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#

RayReframeSourcePosition#

TextToImageRequest#

RayTextToVideoRequest#

RayImageToVideoRequest#

RayVideoToVideoRequest#

ImageEditRequest#

File#

Related Models