tmappdev/change_video_bg – Run with an API on Replicate

tmappdev / change_video_bg

Change or Replace Video Background with any Image

Cold

Public
82 runs
A100 (80GB)

Run with an API

Playground API Examples README Versions

Input

Run this model in Node.js with one line of code:

npx create-replicate --model=tmappdev/change_video_bg

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run tmappdev/change_video_bg using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "tmappdev/change_video_bg:b150accd38553d3332c96efdf3aa72451636b1149f02b92c644dbf1487fdd66c",
  {
    input: {
      input_video: "https://replicate.delivery/pbxt/MRiXYmOvxqHi6ZFzjubcXUI3N0o4YtHsG2aTOGzGyUCFssr2/videos_videos_797f5.mp4",
      background_image: "https://replicate.delivery/pbxt/MRiXYaCQUm5M4RSXdN7ozMlDaZchXjYrHGfASg9Q8rBGHPPg/coffee-9135194_1280.png"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run tmappdev/change_video_bg using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "tmappdev/change_video_bg:b150accd38553d3332c96efdf3aa72451636b1149f02b92c644dbf1487fdd66c",
    input={
        "input_video": "https://replicate.delivery/pbxt/MRiXYmOvxqHi6ZFzjubcXUI3N0o4YtHsG2aTOGzGyUCFssr2/videos_videos_797f5.mp4",
        "background_image": "https://replicate.delivery/pbxt/MRiXYaCQUm5M4RSXdN7ozMlDaZchXjYrHGfASg9Q8rBGHPPg/coffee-9135194_1280.png"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run tmappdev/change_video_bg using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "b150accd38553d3332c96efdf3aa72451636b1149f02b92c644dbf1487fdd66c",
    "input": {
      "input_video": "https://replicate.delivery/pbxt/MRiXYmOvxqHi6ZFzjubcXUI3N0o4YtHsG2aTOGzGyUCFssr2/videos_videos_797f5.mp4",
      "background_image": "https://replicate.delivery/pbxt/MRiXYaCQUm5M4RSXdN7ozMlDaZchXjYrHGfASg9Q8rBGHPPg/coffee-9135194_1280.png"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/tmappdev/change_video_bg@sha256:b150accd38553d3332c96efdf3aa72451636b1149f02b92c644dbf1487fdd66c \
  -i 'input_video="https://replicate.delivery/pbxt/MRiXYmOvxqHi6ZFzjubcXUI3N0o4YtHsG2aTOGzGyUCFssr2/videos_videos_797f5.mp4"' \
  -i 'background_image="https://replicate.delivery/pbxt/MRiXYaCQUm5M4RSXdN7ozMlDaZchXjYrHGfASg9Q8rBGHPPg/coffee-9135194_1280.png"'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/tmappdev/change_video_bg@sha256:b150accd38553d3332c96efdf3aa72451636b1149f02b92c644dbf1487fdd66c
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "input_video": "https://replicate.delivery/pbxt/MRiXYmOvxqHi6ZFzjubcXUI3N0o4YtHsG2aTOGzGyUCFssr2/videos_videos_797f5.mp4",
      "background_image": "https://replicate.delivery/pbxt/MRiXYaCQUm5M4RSXdN7ozMlDaZchXjYrHGfASg9Q8rBGHPPg/coffee-9135194_1280.png"
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2025-02-13T13:31:48.101821Z",
  "created_at": "2025-02-13T13:30:20.625000Z",
  "data_removed": false,
  "error": null,
  "id": "aerwdfyma5rj00cmzy09qy6ng0",
  "input": {
    "input_video": "https://replicate.delivery/pbxt/MRiXYmOvxqHi6ZFzjubcXUI3N0o4YtHsG2aTOGzGyUCFssr2/videos_videos_797f5.mp4",
    "background_image": "https://replicate.delivery/pbxt/MRiXYaCQUm5M4RSXdN7ozMlDaZchXjYrHGfASg9Q8rBGHPPg/coffee-9135194_1280.png"
  },
  "logs": "pct completed : 0.8\npct completed : 1.6\npct completed : 2.4\npct completed : 3.2\npct completed : 4.0\npct completed : 4.8\npct completed : 5.6\npct completed : 6.4\npct completed : 7.2\npct completed : 8.0\nYou seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset\npct completed : 8.8\npct completed : 9.6\npct completed : 10.4\npct completed : 11.2\npct completed : 12.0\npct completed : 12.8\npct completed : 13.6\npct completed : 14.4\npct completed : 15.2\npct completed : 16.0\npct completed : 16.8\npct completed : 17.6\npct completed : 18.4\npct completed : 19.2\npct completed : 20.0\npct completed : 20.8\npct completed : 21.6\npct completed : 22.4\npct completed : 23.2\npct completed : 24.0\npct completed : 24.8\npct completed : 25.6\npct completed : 26.4\npct completed : 27.2\npct completed : 28.0\npct completed : 28.8\npct completed : 29.6\npct completed : 30.4\npct completed : 31.2\npct completed : 32.0\npct completed : 32.8\npct completed : 33.6\npct completed : 34.4\npct completed : 35.2\npct completed : 36.0\npct completed : 36.8\npct completed : 37.6\npct completed : 38.4\npct completed : 39.2\npct completed : 40.0\npct completed : 40.8\npct completed : 41.6\npct completed : 42.4\npct completed : 43.2\npct completed : 44.0\npct completed : 44.8\npct completed : 45.6\npct completed : 46.4\npct completed : 47.2\npct completed : 48.0\npct completed : 48.8\npct completed : 49.6\npct completed : 50.4\npct completed : 51.2\npct completed : 52.0\npct completed : 52.8\npct completed : 53.6\npct completed : 54.4\npct completed : 55.2\npct completed : 56.0\npct completed : 56.8\npct completed : 57.6\npct completed : 58.4\npct completed : 59.2\npct completed : 60.0\npct completed : 60.8\npct completed : 61.6\npct completed : 62.4\npct completed : 63.2\npct completed : 64.0\npct completed : 64.8\npct completed : 65.6\npct completed : 66.4\npct completed : 67.2\npct completed : 68.0\npct completed : 68.8\npct completed : 69.6\npct completed : 70.4\npct completed : 71.2\npct completed : 72.0\npct completed : 72.8\npct completed : 73.6\npct completed : 74.4\npct completed : 75.2\npct completed : 76.0\npct completed : 76.8\npct completed : 77.6\npct completed : 78.4\npct completed : 79.2\npct completed : 80.0\npct completed : 80.8\npct completed : 81.6\npct completed : 82.4\npct completed : 83.2\npct completed : 84.0\npct completed : 84.8\npct completed : 85.6\npct completed : 86.4\npct completed : 87.2\npct completed : 88.0\npct completed : 88.8\npct completed : 89.6\npct completed : 90.4\npct completed : 91.2\npct completed : 92.0\npct completed : 92.8\npct completed : 93.6\npct completed : 94.4\npct completed : 95.2\npct completed : 96.0\npct completed : 96.8\npct completed : 97.6\npct completed : 98.4\npct completed : 99.2\npct completed : 100.0",
  "metrics": {
    "predict_time": 19.749356407,
    "total_time": 87.476821
  },
  "output": "https://replicate.delivery/yhqm/tw0r5X8P3zqfLq31AdqCnXSCwWos0Tr015W4sYudCHYiMdHKA/output.mp4",
  "started_at": "2025-02-13T13:31:28.352464Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/yswh-oyezg43mmuk63ot4z2cbisywbysr3bdqsqlqzcm4rzgauc5eyxva",
    "get": "https://api.replicate.com/v1/predictions/aerwdfyma5rj00cmzy09qy6ng0",
    "cancel": "https://api.replicate.com/v1/predictions/aerwdfyma5rj00cmzy09qy6ng0/cancel"
  },
  "version": "b150accd38553d3332c96efdf3aa72451636b1149f02b92c644dbf1487fdd66c"
}

Generated in

19.8 seconds

Tweak it ShareReport

pct completed : 0.8
pct completed : 1.6
pct completed : 2.4
pct completed : 3.2
pct completed : 4.0
pct completed : 4.8
pct completed : 5.6
pct completed : 6.4
pct completed : 7.2
pct completed : 8.0
You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset
pct completed : 8.8
pct completed : 9.6
pct completed : 10.4
pct completed : 11.2
pct completed : 12.0
pct completed : 12.8
pct completed : 13.6
pct completed : 14.4
pct completed : 15.2
pct completed : 16.0
pct completed : 16.8
pct completed : 17.6
pct completed : 18.4
pct completed : 19.2
pct completed : 20.0
pct completed : 20.8
pct completed : 21.6
pct completed : 22.4
pct completed : 23.2
pct completed : 24.0
pct completed : 24.8
pct completed : 25.6
pct completed : 26.4
pct completed : 27.2
pct completed : 28.0
pct completed : 28.8
pct completed : 29.6
pct completed : 30.4
pct completed : 31.2
pct completed : 32.0
pct completed : 32.8
pct completed : 33.6
pct completed : 34.4
pct completed : 35.2
pct completed : 36.0
pct completed : 36.8
pct completed : 37.6
pct completed : 38.4
pct completed : 39.2
pct completed : 40.0
pct completed : 40.8
pct completed : 41.6
pct completed : 42.4
pct completed : 43.2
pct completed : 44.0
pct completed : 44.8
pct completed : 45.6
pct completed : 46.4
pct completed : 47.2
pct completed : 48.0
pct completed : 48.8
pct completed : 49.6
pct completed : 50.4
pct completed : 51.2
pct completed : 52.0
pct completed : 52.8
pct completed : 53.6
pct completed : 54.4
pct completed : 55.2
pct completed : 56.0
pct completed : 56.8
pct completed : 57.6
pct completed : 58.4
pct completed : 59.2
pct completed : 60.0
pct completed : 60.8
pct completed : 61.6
pct completed : 62.4
pct completed : 63.2
pct completed : 64.0
pct completed : 64.8
pct completed : 65.6
pct completed : 66.4
pct completed : 67.2
pct completed : 68.0
pct completed : 68.8
pct completed : 69.6
pct completed : 70.4
pct completed : 71.2
pct completed : 72.0
pct completed : 72.8
pct completed : 73.6
pct completed : 74.4
pct completed : 75.2
pct completed : 76.0
pct completed : 76.8
pct completed : 77.6
pct completed : 78.4
pct completed : 79.2
pct completed : 80.0
pct completed : 80.8
pct completed : 81.6
pct completed : 82.4
pct completed : 83.2
pct completed : 84.0
pct completed : 84.8
pct completed : 85.6
pct completed : 86.4
pct completed : 87.2
pct completed : 88.0
pct completed : 88.8
pct completed : 89.6
pct completed : 90.4
pct completed : 91.2
pct completed : 92.0
pct completed : 92.8
pct completed : 93.6
pct completed : 94.4
pct completed : 95.2
pct completed : 96.0
pct completed : 96.8
pct completed : 97.6
pct completed : 98.4
pct completed : 99.2
pct completed : 100.0

Examples

View more examples

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.