Versions
Failed to load versions. Head to the versions page to see all versions for this model.
You're looking at a specific version of this model. Jump to the model overview.
arielreplicate /robust_video_matting:2d2de06a
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=arielreplicate/robust_video_matting
or set up a project from scratch
Install Replicate’s Node.js client library:
npm install replicateSet 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 arielreplicate/robust_video_matting using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"arielreplicate/robust_video_matting:2d2de06a76a837a4ba92b6164bf8bfd3ddb524a1fb64b0d8ae055af17fa22503",
{
input: {
input_video: "https://replicate.delivery/pbxt/HqiGGuuwynO7sCHpcQdYQsIf04NotwOrDdbhBf4M6Pou6MGg/butter.mp4",
output_type: "green-screen"
}
}
);
// 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 replicateSet 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 replicateRun arielreplicate/robust_video_matting using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"arielreplicate/robust_video_matting:2d2de06a76a837a4ba92b6164bf8bfd3ddb524a1fb64b0d8ae055af17fa22503",
input={
"input_video": "https://replicate.delivery/pbxt/HqiGGuuwynO7sCHpcQdYQsIf04NotwOrDdbhBf4M6Pou6MGg/butter.mp4",
"output_type": "green-screen"
}
)
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 arielreplicate/robust_video_matting 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": "arielreplicate/robust_video_matting:2d2de06a76a837a4ba92b6164bf8bfd3ddb524a1fb64b0d8ae055af17fa22503",
"input": {
"input_video": "https://replicate.delivery/pbxt/HqiGGuuwynO7sCHpcQdYQsIf04NotwOrDdbhBf4M6Pou6MGg/butter.mp4",
"output_type": "green-screen"
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
Sign in with GitHub
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2022-11-25T14:17:06.618254Z",
"created_at": "2022-11-25T14:11:53.705436Z",
"data_removed": false,
"error": null,
"id": "iqaowdlwcnbxresiand63tzn5a",
"input": {
"input_video": "https://replicate.delivery/pbxt/HqiGGuuwynO7sCHpcQdYQsIf04NotwOrDdbhBf4M6Pou6MGg/butter.mp4",
"output_type": "green-screen"
},
"logs": "0%| | 0/382 [00:00<?, ?it/s]/root/.pyenv/versions/3.8.15/lib/python3.8/site-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at /pytorch/c10/core/TensorImpl.h:1156.)\nreturn torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)\n 3%|▎ | 12/382 [00:02<01:25, 4.30it/s]\n 6%|▋ | 24/382 [00:04<01:10, 5.05it/s]\n 9%|▉ | 36/382 [00:07<01:05, 5.29it/s]\n 13%|█▎ | 48/382 [00:10<01:19, 4.19it/s]\n 16%|█▌ | 60/382 [00:14<01:22, 3.92it/s]\n 19%|█▉ | 72/382 [00:17<01:22, 3.74it/s]\n 22%|██▏ | 84/382 [00:20<01:16, 3.88it/s]\n 25%|██▌ | 96/382 [00:23<01:12, 3.96it/s]\n 28%|██▊ | 108/382 [00:26<01:06, 4.10it/s]\n 31%|███▏ | 120/382 [00:28<01:03, 4.13it/s]\n 35%|███▍ | 132/382 [00:31<00:59, 4.23it/s]\n 38%|███▊ | 144/382 [00:34<00:57, 4.12it/s]\n 41%|████ | 156/382 [00:37<00:55, 4.07it/s]\n 44%|████▍ | 168/382 [00:40<00:53, 4.04it/s]\n 47%|████▋ | 180/382 [00:43<00:49, 4.07it/s]\n 50%|█████ | 192/382 [00:46<00:46, 4.11it/s]\n 53%|█████▎ | 204/382 [00:49<00:42, 4.16it/s]\n 57%|█████▋ | 216/382 [00:52<00:40, 4.05it/s]\n 60%|█████▉ | 228/382 [00:55<00:38, 4.05it/s]\n 63%|██████▎ | 240/382 [00:58<00:35, 4.02it/s]\n 66%|██████▌ | 252/382 [01:01<00:31, 4.11it/s]\n 69%|██████▉ | 264/382 [01:04<00:28, 4.17it/s]\n 72%|███████▏ | 276/382 [01:06<00:24, 4.28it/s]\n 75%|███████▌ | 288/382 [01:09<00:22, 4.22it/s]\n 79%|███████▊ | 300/382 [01:12<00:19, 4.23it/s]\n 82%|████████▏ | 312/382 [01:15<00:16, 4.26it/s]\n 85%|████████▍ | 324/382 [01:17<00:13, 4.28it/s]\n 88%|████████▊ | 336/382 [01:20<00:10, 4.24it/s]\n 91%|█████████ | 348/382 [01:23<00:07, 4.25it/s]\n 94%|█████████▍| 360/382 [01:26<00:05, 4.20it/s]\n 97%|█████████▋| 372/382 [01:29<00:02, 4.20it/s]\n100%|██████████| 382/382 [01:31<00:00, 4.20it/s]",
"metrics": {
"predict_time": 97.211127,
"total_time": 312.912818
},
"output": "https://replicate.delivery/pbxt/V3iFlL5JotpbLtkUqGcnrpsiRfXume3Jm0020Iu0hX0hBoDQA/green-screen.mp4",
"started_at": "2022-11-25T14:15:29.407127Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/iqaowdlwcnbxresiand63tzn5a",
"cancel": "https://api.replicate.com/v1/predictions/iqaowdlwcnbxresiand63tzn5a/cancel"
},
"version": "2d2de06a76a837a4ba92b6164bf8bfd3ddb524a1fb64b0d8ae055af17fa22503"
}Generated in
0%| | 0/382 [00:00<?, ?it/s]/root/.pyenv/versions/3.8.15/lib/python3.8/site-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at /pytorch/c10/core/TensorImpl.h:1156.)
return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
3%|▎ | 12/382 [00:02<01:25, 4.30it/s]
6%|▋ | 24/382 [00:04<01:10, 5.05it/s]
9%|▉ | 36/382 [00:07<01:05, 5.29it/s]
13%|█▎ | 48/382 [00:10<01:19, 4.19it/s]
16%|█▌ | 60/382 [00:14<01:22, 3.92it/s]
19%|█▉ | 72/382 [00:17<01:22, 3.74it/s]
22%|██▏ | 84/382 [00:20<01:16, 3.88it/s]
25%|██▌ | 96/382 [00:23<01:12, 3.96it/s]
28%|██▊ | 108/382 [00:26<01:06, 4.10it/s]
31%|███▏ | 120/382 [00:28<01:03, 4.13it/s]
35%|███▍ | 132/382 [00:31<00:59, 4.23it/s]
38%|███▊ | 144/382 [00:34<00:57, 4.12it/s]
41%|████ | 156/382 [00:37<00:55, 4.07it/s]
44%|████▍ | 168/382 [00:40<00:53, 4.04it/s]
47%|████▋ | 180/382 [00:43<00:49, 4.07it/s]
50%|█████ | 192/382 [00:46<00:46, 4.11it/s]
53%|█████▎ | 204/382 [00:49<00:42, 4.16it/s]
57%|█████▋ | 216/382 [00:52<00:40, 4.05it/s]
60%|█████▉ | 228/382 [00:55<00:38, 4.05it/s]
63%|██████▎ | 240/382 [00:58<00:35, 4.02it/s]
66%|██████▌ | 252/382 [01:01<00:31, 4.11it/s]
69%|██████▉ | 264/382 [01:04<00:28, 4.17it/s]
72%|███████▏ | 276/382 [01:06<00:24, 4.28it/s]
75%|███████▌ | 288/382 [01:09<00:22, 4.22it/s]
79%|███████▊ | 300/382 [01:12<00:19, 4.23it/s]
82%|████████▏ | 312/382 [01:15<00:16, 4.26it/s]
85%|████████▍ | 324/382 [01:17<00:13, 4.28it/s]
88%|████████▊ | 336/382 [01:20<00:10, 4.24it/s]
91%|█████████ | 348/382 [01:23<00:07, 4.25it/s]
94%|█████████▍| 360/382 [01:26<00:05, 4.20it/s]
97%|█████████▋| 372/382 [01:29<00:02, 4.20it/s]
100%|██████████| 382/382 [01:31<00:00, 4.20it/s]