Wan 2.1 VACE Long Reframe | Video to Video

fal-ai/wan-vace-apps/long-reframe

Reframe entire videos scene-by-scene using Wan VACE 2.1

Inference

Commercial use

Schema

LLMs

Playground API

About

Reframes a long video scene-by-scene.

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/wan-vace-apps/long-reframe", {
  input: {
    video_url: "https://storage.googleapis.com/falserverless/web-examples/wan/t2v.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"
});

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/wan-vace-apps/long-reframe", {
  input: {
    video_url: "https://storage.googleapis.com/falserverless/web-examples/wan/t2v.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("fal-ai/wan-vace-apps/long-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("fal-ai/wan-vace-apps/long-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

The text prompt to guide video generation. Optional for reframing. Default value: ""

negative_prompt string

Negative prompt for video generation. Default value: "letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards"

seed integer

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

resolution ResolutionEnum

Resolution of the generated video. Default value: "auto"

Possible enum values: auto, 240p, 360p, 480p, 580p, 720p

aspect_ratio AspectRatioEnum

Aspect ratio of the generated video. Default value: "auto"

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

num_inference_steps integer

Number of inference steps for sampling. Higher values give better quality but take longer. Default value: 30

guidance_scale float

Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt. Default value: 5

sampler SamplerEnum

Sampler to use for video generation. Default value: "unipc"

Possible enum values: unipc, dpm++, euler

shift float

Shift parameter for video generation. Default value: 5

video_url string* required

URL to the source video file. This video will be used as a reference for the reframe task.

first_frame_url string

URL to the first frame of the video. If provided, the model will use this frame as a reference.

last_frame_url string

URL to the last frame of the video. If provided, the model will use this frame as a reference.

enable_safety_checker boolean

If set to true, the safety checker will be enabled.

acceleration Enum

Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster. Default value: regular

Possible enum values: none, regular

video_quality VideoQualityEnum

The quality 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

num_interpolated_frames integer

Number of frames to interpolate between the original frames. A value of 0 means no interpolation.

enable_auto_downsample boolean

If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length.

auto_downsample_min_fps float

The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences. Default value: 15

interpolator_model InterpolatorModelEnum

The model to use for frame interpolation. Options are 'rife' or 'film'. Default value: "film"

Possible enum values: rife, film

sync_mode boolean

If True, the media will be returned as a data URI and the output data won't be available in the request history.

zoom_factor float

Zoom factor for the video. When this value is greater than 0, the video will be zoomed in by this factor (in relation to the canvas size,) cutting off the edges of the video. A value of 0 means no zoom.

trim_borders boolean

Whether to trim borders from the video. Default value: true

scene_threshold float

Threshold for scene detection sensitivity (0-100). Lower values detect more scenes. Default value: 30

paste_back boolean

Whether to paste back the reframed scene to the original video. Default value: true

{
  "prompt": "",
  "negative_prompt": "letterboxing, borders, black bars, bright colors, overexposed, static, blurred details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, malformed limbs, fused fingers, still picture, cluttered background, three legs, many people in the background, walking backwards",
  "resolution": "auto",
  "aspect_ratio": "auto",
  "num_inference_steps": 30,
  "guidance_scale": 5,
  "sampler": "unipc",
  "shift": 5,
  "video_url": "https://storage.googleapis.com/falserverless/web-examples/wan/t2v.mp4",
  "enable_safety_checker": true,
  "acceleration": "regular",
  "video_quality": "high",
  "video_write_mode": "balanced",
  "num_interpolated_frames": 0,
  "enable_auto_downsample": false,
  "auto_downsample_min_fps": 15,
  "interpolator_model": "film",
  "sync_mode": false,
  "zoom_factor": 0,
  "trim_borders": true,
  "scene_threshold": 30,
  "paste_back": true
}

Output#

video VideoFile* required

The output video file.

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

Other types#

WanVACEVideoEditResponse#

video VideoFile* required

The edited video.

WanVACEVideoEditRequest#

prompt string* required

Prompt to edit the video.

video_url string* required

URL of the input video.

video_type VideoTypeEnum

The type of video you're editing. Use 'general' for most videos, and 'human' for videos emphasizing human subjects and motions. The default value 'auto' means the model will guess based on the first frame of the video. Default value: "auto"

Possible enum values: auto, general, human

image_urls list<string>

URLs of the input images to use as a reference for the generation.

resolution ResolutionEnum

Resolution of the edited video. Default value: "auto"

Possible enum values: auto, 240p, 360p, 480p, 580p, 720p

enable_auto_downsample boolean

Whether to enable automatic downsampling. If your video has a high frame rate or is long, enabling longer sequences to be generated. The video will be interpolated back to the original frame rate after generation. Default value: true

aspect_ratio AspectRatioEnum

Aspect ratio of the edited video. Default value: "auto"

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

auto_downsample_min_fps float

The minimum frames per second to downsample the video to. Default value: 15

enable_safety_checker boolean

Whether to enable the safety checker. Default value: true

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

Wan 2.1 VACE Long Reframe 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#

WanVACEVideoEditResponse#

WanVACEVideoEditRequest#

VideoFile#