smoretalk/rembg-enhance – Run with an API on Replicate

smoretalk / rembg-enhance

A background removal model enhanced with ViTMatte.

Warm

Public
4.5M runs
L40S

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=smoretalk/rembg-enhance

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 smoretalk/rembg-enhance using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "smoretalk/rembg-enhance:4067ee2a58f6c161d434a9c077cfa012820b8e076efa2772aa171e26557da919",
  {
    input: {
      image: "https://replicate.delivery/pbxt/Kd8MEq3eYnrqPs4CZcaNKFRaApbP0Jb3pdvcDDQgYIFbvEPY/3DICON-ai-generated-flamel-collections-72753.png"
    }
  }
);
console.log(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 smoretalk/rembg-enhance using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "smoretalk/rembg-enhance:4067ee2a58f6c161d434a9c077cfa012820b8e076efa2772aa171e26557da919",
    input={
        "image": "https://replicate.delivery/pbxt/Kd8MEq3eYnrqPs4CZcaNKFRaApbP0Jb3pdvcDDQgYIFbvEPY/3DICON-ai-generated-flamel-collections-72753.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 smoretalk/rembg-enhance 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": "4067ee2a58f6c161d434a9c077cfa012820b8e076efa2772aa171e26557da919",
    "input": {
      "image": "https://replicate.delivery/pbxt/Kd8MEq3eYnrqPs4CZcaNKFRaApbP0Jb3pdvcDDQgYIFbvEPY/3DICON-ai-generated-flamel-collections-72753.png"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-03-25T08:15:16.352372Z",
  "created_at": "2024-03-25T08:15:01.699970Z",
  "data_removed": false,
  "error": null,
  "id": "alhp5llb43i4gie2ie6ke3j5wi",
  "input": {
    "image": "https://replicate.delivery/pbxt/Kd8MEq3eYnrqPs4CZcaNKFRaApbP0Jb3pdvcDDQgYIFbvEPY/3DICON-ai-generated-flamel-collections-72753.png"
  },
  "logs": "Downloading...\nFrom (original): https://drive.google.com/uc?id=13oBl5MTVcWER3YU4fSxW3ATlVfueFQPY\nFrom (redirected): https://drive.google.com/uc?id=13oBl5MTVcWER3YU4fSxW3ATlVfueFQPY&confirm=t&uuid=50314cee-062c-4c9e-818f-c6715835dfad\nTo: /root/.transparent-background/ckpt_base.pth\n  0%|          | 0.00/368M [00:00<?, ?B/s]\n  0%|          | 524k/368M [00:00<02:49, 2.17MB/s]\n  1%|          | 2.62M/368M [00:00<00:41, 8.71MB/s]\n  3%|▎         | 11.0M/368M [00:00<00:10, 33.6MB/s]\n 10%|▉         | 35.7M/368M [00:00<00:03, 102MB/s] \n 17%|█▋        | 60.8M/368M [00:00<00:02, 149MB/s]\n 23%|██▎       | 85.5M/368M [00:00<00:01, 178MB/s]\n 30%|███       | 111M/368M [00:00<00:01, 201MB/s] \n 37%|███▋      | 135M/368M [00:00<00:01, 213MB/s]\n 44%|████▎     | 160M/368M [00:01<00:00, 223MB/s]\n 50%|█████     | 185M/368M [00:01<00:00, 231MB/s]\n 57%|█████▋    | 210M/368M [00:01<00:00, 237MB/s]\n 64%|██████▍   | 236M/368M [00:01<00:00, 242MB/s]\n 71%|███████   | 261M/368M [00:01<00:00, 182MB/s]\n 78%|███████▊  | 286M/368M [00:01<00:00, 199MB/s]\n 85%|████████▍ | 312M/368M [00:01<00:00, 213MB/s]\n 92%|█████████▏| 338M/368M [00:01<00:00, 224MB/s]\n 98%|█████████▊| 362M/368M [00:01<00:00, 221MB/s]\n100%|██████████| 368M/368M [00:02<00:00, 183MB/s]\n=====================================================\nMode: base | Device: cuda:0 | Torchscript: disabled\n=====================================================\ndone\n[Debug] torch.cuda.is_available:  True",
  "metrics": {
    "predict_time": 14.616108,
    "total_time": 14.652402
  },
  "output": "https://replicate.delivery/pbxt/14qgrcVZmxYEHNGRTFWwP4SWH9vnGB0c623Axlg4Nj1kk7oE/out.png",
  "started_at": "2024-03-25T08:15:01.736264Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/alhp5llb43i4gie2ie6ke3j5wi",
    "cancel": "https://api.replicate.com/v1/predictions/alhp5llb43i4gie2ie6ke3j5wi/cancel"
  },
  "version": "c57bc7626c4b5eda6531ffb84657f5672932d0fad49120b94383ec93f7ad7ac6"
}

Generated in

14.6 seconds

Tweak itReport

This example was created by a different version, smoretalk/rembg-enhance:c57bc762.

Examples

View more examples

Run time and cost

This model costs approximately $0.0088 to run on Replicate, or 113 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 10 seconds.

Readme

A background removal model enhanced with ViTMatte.
You can get better and clearer results.
To create cool 3d objects, visit https://flamel.app/