omniedgeio/virtual-dressing – Run with an API on Replicate

Input

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

npx create-replicate --model=omniedgeio/virtual-dressing

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 omniedgeio/virtual-dressing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "omniedgeio/virtual-dressing:9d39208bb417fdcdf781f81f0bb6a2896e2eee5e024b0ad29cf16027ed5cb918",
  {
    input: {
      seed: 0,
      steps: 30,
      model_image: "https://replicate.delivery/pbxt/KXZRucHM1bbj49bWhUsZRw9GD4DYpgbHuuWyknmIybMMrHWG/ltfp4dlj.jpeg",
      garment_image: "https://replicate.delivery/pbxt/KXZRuw8l44Q7wIML5dhP5o47l2BEpENFQ1VpDejfUlk3nWCh/IMG_1210.jpg",
      guidance_scale: 3,
      garment_category: "upperbody"
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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 omniedgeio/virtual-dressing using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "omniedgeio/virtual-dressing:9d39208bb417fdcdf781f81f0bb6a2896e2eee5e024b0ad29cf16027ed5cb918",
    input={
        "seed": 0,
        "steps": 30,
        "model_image": "https://replicate.delivery/pbxt/KXZRucHM1bbj49bWhUsZRw9GD4DYpgbHuuWyknmIybMMrHWG/ltfp4dlj.jpeg",
        "garment_image": "https://replicate.delivery/pbxt/KXZRuw8l44Q7wIML5dhP5o47l2BEpENFQ1VpDejfUlk3nWCh/IMG_1210.jpg",
        "guidance_scale": 3,
        "garment_category": "upperbody"
    }
)
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 omniedgeio/virtual-dressing 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": "omniedgeio/virtual-dressing:9d39208bb417fdcdf781f81f0bb6a2896e2eee5e024b0ad29cf16027ed5cb918",
    "input": {
      "seed": 0,
      "steps": 30,
      "model_image": "https://replicate.delivery/pbxt/KXZRucHM1bbj49bWhUsZRw9GD4DYpgbHuuWyknmIybMMrHWG/ltfp4dlj.jpeg",
      "garment_image": "https://replicate.delivery/pbxt/KXZRuw8l44Q7wIML5dhP5o47l2BEpENFQ1VpDejfUlk3nWCh/IMG_1210.jpg",
      "guidance_scale": 3,
      "garment_category": "upperbody"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-03-09T16:11:12.545285Z",
  "created_at": "2024-03-09T16:06:42.585097Z",
  "data_removed": false,
  "error": null,
  "id": "pnlitubbsijhrk2eloitp5p4si",
  "input": {
    "seed": 0,
    "steps": 30,
    "model_image": "https://replicate.delivery/pbxt/KXZRucHM1bbj49bWhUsZRw9GD4DYpgbHuuWyknmIybMMrHWG/ltfp4dlj.jpeg",
    "garment_image": "https://replicate.delivery/pbxt/KXZRuw8l44Q7wIML5dhP5o47l2BEpENFQ1VpDejfUlk3nWCh/IMG_1210.jpg",
    "guidance_scale": 3
  },
  "logs": "Model parse in 0.67 seconds.\n0: 640x480 1 person, 153.6ms\nSpeed: 8.1ms preprocess, 153.6ms inference, 508.6ms postprocess per image at shape (1, 3, 640, 480)\nOpen pose in 1.25 seconds.\nInitial seed: 0\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:05,  5.79it/s]\n  7%|▋         | 2/30 [00:00<00:04,  6.32it/s]\n 10%|█         | 3/30 [00:00<00:04,  6.00it/s]\n 13%|█▎        | 4/30 [00:00<00:04,  6.30it/s]\n 17%|█▋        | 5/30 [00:00<00:03,  6.48it/s]\n 20%|██        | 6/30 [00:00<00:03,  6.59it/s]\n 23%|██▎       | 7/30 [00:01<00:03,  6.67it/s]\n 27%|██▋       | 8/30 [00:01<00:03,  6.71it/s]\n 30%|███       | 9/30 [00:01<00:03,  6.76it/s]\n 33%|███▎      | 10/30 [00:01<00:02,  6.77it/s]\n 37%|███▋      | 11/30 [00:01<00:02,  6.77it/s]\n 40%|████      | 12/30 [00:01<00:02,  6.79it/s]\n 43%|████▎     | 13/30 [00:01<00:02,  6.80it/s]\n 47%|████▋     | 14/30 [00:02<00:02,  6.79it/s]\n 50%|█████     | 15/30 [00:02<00:02,  6.79it/s]\n 53%|█████▎    | 16/30 [00:02<00:02,  6.79it/s]\n 57%|█████▋    | 17/30 [00:02<00:01,  6.79it/s]\n 60%|██████    | 18/30 [00:02<00:01,  6.79it/s]\n 63%|██████▎   | 19/30 [00:02<00:01,  6.81it/s]\n 67%|██████▋   | 20/30 [00:02<00:01,  6.81it/s]\n 70%|███████   | 21/30 [00:03<00:01,  6.82it/s]\n 73%|███████▎  | 22/30 [00:03<00:01,  6.85it/s]\n 77%|███████▋  | 23/30 [00:03<00:01,  6.83it/s]\n 80%|████████  | 24/30 [00:03<00:00,  6.83it/s]\n 83%|████████▎ | 25/30 [00:03<00:00,  6.83it/s]\n 87%|████████▋ | 26/30 [00:03<00:00,  6.83it/s]\n 90%|█████████ | 27/30 [00:04<00:00,  6.83it/s]\n 93%|█████████▎| 28/30 [00:04<00:00,  6.83it/s]\n 97%|█████████▋| 29/30 [00:04<00:00,  6.83it/s]\n100%|██████████| 30/30 [00:04<00:00,  6.82it/s]\n100%|██████████| 30/30 [00:04<00:00,  6.73it/s]",
  "metrics": {
    "predict_time": 8.157579,
    "total_time": 269.960188
  },
  "output": "https://replicate.delivery/pbxt/wlxnTmA9zMYDLB3vYKeuLSkFtMMwADiNxWLA9JLf6wEgwjekA/tmphdt92l5m.jpg",
  "started_at": "2024-03-09T16:11:04.387706Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/pnlitubbsijhrk2eloitp5p4si",
    "cancel": "https://api.replicate.com/v1/predictions/pnlitubbsijhrk2eloitp5p4si/cancel"
  },
  "version": "d6835398c2147f0a09a99a9f6cb59f7f87c9f72c67078f3858fc51e7eefde338"
}

Generated in

8.2 seconds

Tweak it Report

Model parse in 0.67 seconds.
0: 640x480 1 person, 153.6ms
Speed: 8.1ms preprocess, 153.6ms inference, 508.6ms postprocess per image at shape (1, 3, 640, 480)
Open pose in 1.25 seconds.
Initial seed: 0
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:05,  5.79it/s]
  7%|▋         | 2/30 [00:00<00:04,  6.32it/s]
 10%|█         | 3/30 [00:00<00:04,  6.00it/s]
 13%|█▎        | 4/30 [00:00<00:04,  6.30it/s]
 17%|█▋        | 5/30 [00:00<00:03,  6.48it/s]
 20%|██        | 6/30 [00:00<00:03,  6.59it/s]
 23%|██▎       | 7/30 [00:01<00:03,  6.67it/s]
 27%|██▋       | 8/30 [00:01<00:03,  6.71it/s]
 30%|███       | 9/30 [00:01<00:03,  6.76it/s]
 33%|███▎      | 10/30 [00:01<00:02,  6.77it/s]
 37%|███▋      | 11/30 [00:01<00:02,  6.77it/s]
 40%|████      | 12/30 [00:01<00:02,  6.79it/s]
 43%|████▎     | 13/30 [00:01<00:02,  6.80it/s]
 47%|████▋     | 14/30 [00:02<00:02,  6.79it/s]
 50%|█████     | 15/30 [00:02<00:02,  6.79it/s]
 53%|█████▎    | 16/30 [00:02<00:02,  6.79it/s]
 57%|█████▋    | 17/30 [00:02<00:01,  6.79it/s]
 60%|██████    | 18/30 [00:02<00:01,  6.79it/s]
 63%|██████▎   | 19/30 [00:02<00:01,  6.81it/s]
 67%|██████▋   | 20/30 [00:02<00:01,  6.81it/s]
 70%|███████   | 21/30 [00:03<00:01,  6.82it/s]
 73%|███████▎  | 22/30 [00:03<00:01,  6.85it/s]
 77%|███████▋  | 23/30 [00:03<00:01,  6.83it/s]
 80%|████████  | 24/30 [00:03<00:00,  6.83it/s]
 83%|████████▎ | 25/30 [00:03<00:00,  6.83it/s]
 87%|████████▋ | 26/30 [00:03<00:00,  6.83it/s]
 90%|█████████ | 27/30 [00:04<00:00,  6.83it/s]
 93%|█████████▎| 28/30 [00:04<00:00,  6.83it/s]
 97%|█████████▋| 29/30 [00:04<00:00,  6.83it/s]
100%|██████████| 30/30 [00:04<00:00,  6.82it/s]
100%|██████████| 30/30 [00:04<00:00,  6.73it/s]

This output was created using a different version of the model, omniedgeio/virtual-dressing:d6835398.

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.