✨ NEW: Seedream 4.0 Edit - Best Model for Image Editing

Marey Realism V1.5 Video to Video

moonvalley/marey/motion-transfer
Pull motion from a reference video and apply it to new subjects or scenes.
Inference
Commercial use

About

Motion Transfer Endpoint

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("moonvalley/marey/motion-transfer", {
  input: {
    prompt: "Detailed Description: A fast, smooth dolly shot glides forward at water level through a monumental, minimalist colonnade. The imposing, symmetrical rows of brutalist marble columns rush past on either side, their strong vertical lines creating a sense of powerful, constant motion. The dark, glassy water of a central pool perfectly reflects the towering structures, with gentle ripples disturbing the mirror image as the camera advances. The scene is cinematic and moody, with the light-colored stone contrasting against the dark water and the pale sky visible at the far end of the architectural tunnel. shot on 35mm, film, organic, analog, motion blur

  Background: A pale, overcast sky and a distant treeline are framed by the opening at the end of the colonnade, growing larger as the camera moves forward.

  Middleground: The two rows of massive, geometric columns recede into the distance, their uniform shapes creating a hypnotic, rhythmic pattern that rushes past the lens.

  Foreground: The camera skims just above the surface of the dark, rippling water, which reflects the blurred motion of the columns passing on the left and right.",
    video_url: "https://d1kaxrqq3vfrw5.cloudfront.net/fal-launch-assets/guide-assets/fal-motion-transfer-input-5s.mp4"
  },
  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("moonvalley/marey/motion-transfer", {
  input: {
    prompt: "Detailed Description: A fast, smooth dolly shot glides forward at water level through a monumental, minimalist colonnade. The imposing, symmetrical rows of brutalist marble columns rush past on either side, their strong vertical lines creating a sense of powerful, constant motion. The dark, glassy water of a central pool perfectly reflects the towering structures, with gentle ripples disturbing the mirror image as the camera advances. The scene is cinematic and moody, with the light-colored stone contrasting against the dark water and the pale sky visible at the far end of the architectural tunnel. shot on 35mm, film, organic, analog, motion blur

  Background: A pale, overcast sky and a distant treeline are framed by the opening at the end of the colonnade, growing larger as the camera moves forward.

  Middleground: The two rows of massive, geometric columns recede into the distance, their uniform shapes creating a hypnotic, rhythmic pattern that rushes past the lens.

  Foreground: The camera skims just above the surface of the dark, rippling water, which reflects the blurred motion of the columns passing on the left and right.",
    video_url: "https://d1kaxrqq3vfrw5.cloudfront.net/fal-launch-assets/guide-assets/fal-motion-transfer-input-5s.mp4"
  },
  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("moonvalley/marey/motion-transfer", {
  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("moonvalley/marey/motion-transfer", {
  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 generate a video from

video_url string* required

The URL of the video to use as the control video.

first_frame_image_url string

Optional first frame image URL to use as the first frame of the generated video Default value: "https://video-editor-files-prod.s3.us-east-2.amazonaws.com/users/1e4d46df-0702-4491-95ce-763592f33f34/uploaded-images/9b9dce1c-abd0-46c0-bac9-9454f8893b06/original"

reference_image_url string

Optional reference image URL to use for pose control or as a starting frame

negative_prompt string

Negative prompt used to guide the model away from undesirable features. Default value: "gopro, bright, contrast, static, overexposed, bright, vignette, artifacts, still, noise, texture, scanlines, videogame, 360 camera, VR, transition, flare, saturation, distorted, warped, wide angle, contrast, saturated, vibrant, glowing, cross dissolve, texture, videogame, saturation, cheesy, ugly hands, mutated hands, mutant, disfigured, extra fingers, blown out, horrible, blurry, worst quality, bad, transition, dissolve, cross-dissolve, melt, fade in, fade out, wobbly, weird, low quality, plastic, stock footage, video camera, boring, static"

seed integer

Seed for random number generation. Use -1 for random seed each run. Default value: 9

{
  "prompt": "Detailed Description: A fast, smooth dolly shot glides forward at water level through a monumental, minimalist colonnade. The imposing, symmetrical rows of brutalist marble columns rush past on either side, their strong vertical lines creating a sense of powerful, constant motion. The dark, glassy water of a central pool perfectly reflects the towering structures, with gentle ripples disturbing the mirror image as the camera advances. The scene is cinematic and moody, with the light-colored stone contrasting against the dark water and the pale sky visible at the far end of the architectural tunnel. shot on 35mm, film, organic, analog, motion blur\n\nBackground: A pale, overcast sky and a distant treeline are framed by the opening at the end of the colonnade, growing larger as the camera moves forward.\n\nMiddleground: The two rows of massive, geometric columns recede into the distance, their uniform shapes creating a hypnotic, rhythmic pattern that rushes past the lens.\n\nForeground: The camera skims just above the surface of the dark, rippling water, which reflects the blurred motion of the columns passing on the left and right.",
  "video_url": "https://d1kaxrqq3vfrw5.cloudfront.net/fal-launch-assets/guide-assets/fal-motion-transfer-input-5s.mp4",
  "first_frame_image_url": "https://video-editor-files-prod.s3.us-east-2.amazonaws.com/users/1e4d46df-0702-4491-95ce-763592f33f34/uploaded-images/9b9dce1c-abd0-46c0-bac9-9454f8893b06/original",
  "negative_prompt": "gopro, bright, contrast, static, overexposed, bright, vignette, artifacts, still, noise, texture, scanlines, videogame, 360 camera, VR, transition, flare, saturation, distorted, warped, wide angle, contrast, saturated, vibrant, glowing, cross dissolve, texture, videogame, saturation, cheesy, ugly hands, mutated hands, mutant, disfigured, extra fingers, blown out, horrible, blurry, worst quality, bad, transition, dissolve, cross-dissolve, melt, fade in, fade out, wobbly, weird, low quality, plastic, stock footage, video camera, boring, static",
  "seed": 9
}

Output#

video File* required

The generated video.

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

Other types#

MareyInputPoseTransfer#

prompt string* required

The prompt to generate a video from

video_url string* required

The URL of the video to use as the control video.

first_frame_image_url string

Optional first frame image URL to use as the first frame of the generated video

reference_image_url string

Optional reference image URL to use for pose control or as a starting frame

negative_prompt string

Negative prompt used to guide the model away from undesirable features. Default value: "gopro, bright, contrast, static, overexposed, bright, vignette, artifacts, still, noise, texture, scanlines, videogame, 360 camera, VR, transition, flare, saturation, distorted, warped, wide angle, contrast, saturated, vibrant, glowing, cross dissolve, texture, videogame, saturation, cheesy, ugly hands, mutated hands, mutant, disfigured, extra fingers, blown out, horrible, blurry, worst quality, bad, transition, dissolve, cross-dissolve, melt, fade in, fade out, wobbly, weird, low quality, plastic, stock footage, video camera, boring, static"

seed integer

Seed for random number generation. Use -1 for random seed each run. Default value: 9

MareyInputShotExtension#

prompt string* required

The prompt to generate a video from

video_url string* required

The URL of the video to use as the control video.

first_frame_image_url string

Optional first frame image URL to use as the first frame of the generated video

reference_image_url string
negative_prompt string

Negative prompt used to guide the model away from undesirable features. Default value: "gopro, bright, contrast, static, overexposed, bright, vignette, artifacts, still, noise, texture, scanlines, videogame, 360 camera, VR, transition, flare, saturation, distorted, warped, wide angle, contrast, saturated, vibrant, glowing, cross dissolve, texture, videogame, saturation, cheesy, ugly hands, mutated hands, mutant, disfigured, extra fingers, blown out, horrible, blurry, worst quality, bad, transition, dissolve, cross-dissolve, melt, fade in, fade out, wobbly, weird, low quality, plastic, stock footage, video camera, boring, static"

seed integer

Seed for random number generation. Use -1 for random seed each run. Default value: 9

duration DurationEnum

The duration of the generated video. Default value: "5s"

Possible enum values: 5s, 10s

MareyInputI2V#

prompt string* required

The prompt to generate a video from

dimensions DimensionsEnum

The dimensions of the generated video in width x height format. Default value: "1920x1080"

Possible enum values: 1920x1080, 1080x1920, 1152x1152, 1536x1152, 1152x1536

duration DurationEnum

The duration of the generated video. Default value: "5s"

Possible enum values: 5s, 10s

negative_prompt string

Negative prompt used to guide the model away from undesirable features. Default value: "<synthetic> <scene cut> low-poly, flat shader, bad rigging, stiff animation, uncanny eyes, low-quality textures, looping glitch, cheap effect, overbloom, bloom spam, default lighting, game asset, stiff face, ugly specular, AI artifacts"

seed integer

Seed for random number generation. Use -1 for random seed each run. Default value: 9

image_url string* required

The URL of the image to use as the first frame of 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.

MareyInputT2V#

prompt string* required

The prompt to generate a video from

dimensions DimensionsEnum

The dimensions of the generated video in width x height format. Default value: "1920x1080"

Possible enum values: 1920x1080, 1152x1152, 1536x1152, 1152x1536

duration DurationEnum

The duration of the generated video. Default value: "5s"

Possible enum values: 5s, 10s

negative_prompt string

Negative prompt used to guide the model away from undesirable features. Default value: "<synthetic> <scene cut> low-poly, flat shader, bad rigging, stiff animation, uncanny eyes, low-quality textures, looping glitch, cheap effect, overbloom, bloom spam, default lighting, game asset, stiff face, ugly specular, AI artifacts"

seed integer

Seed for random number generation. Use -1 for random seed each run. Default value: 9

Related Models