Prediction

ksezyf5vjxrme0cnn4rvk2w7yw

Status

Succeeded

Source

Web

Total duration

2m 11s

Created

over 1 year ago by alquimia-ai

Webhook

–

Input

person: https://replicate.delivery/pbxt/MgGhdsL2rCACbqcW2DbVpmn7iZVRVYCDv0ilzkETea405dXj/Alex%20Consani%20Getty%20Image%201779424797.webp
garment: https://replicate.delivery/pbxt/MgGhe8U8lLnCH4pWnIP7Gc3hkv2Pq8v35zZi1ohTWrirUHTh/WhatsApp%20Image%202025-03-18%20at%2009.11.23.jpeg
repaint: false
seed: 42
guidance_scale: 2.5
denoising_steps: 30
reference_unet_acceleration: false
stroke_width_mask: 35
neck_offset_removal: 20
dilatation_iterations: 5
garment_type: upper_body

{
  "denoising_steps": 30,
  "dilatation_iterations": 5,
  "dilatation_kernel": [
    10,
    10
  ],
  "garment": "https://replicate.delivery/pbxt/MgGhe8U8lLnCH4pWnIP7Gc3hkv2Pq8v35zZi1ohTWrirUHTh/WhatsApp%20Image%202025-03-18%20at%2009.11.23.jpeg",
  "garment_type": "upper_body",
  "guidance_scale": 2.5,
  "neck_offset_removal": 20,
  "person": "https://replicate.delivery/pbxt/MgGhdsL2rCACbqcW2DbVpmn7iZVRVYCDv0ilzkETea405dXj/Alex%20Consani%20Getty%20Image%201779424797.webp",
  "reference_unet_acceleration": false,
  "repaint": false,
  "seed": 42,
  "stroke_width_mask": 35
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_Wwb**********************************

This is your API token. Keep it to yourself.

Import and set up the client:

import Replicate from "replicate";

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

Run alquimia-ai/schiaparelli using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "alquimia-ai/schiaparelli:7b36045b2d4d84c7962afd723f126748e40a3d3b3f7626fbba75c1ddd593771b",
  {
    input: {
      denoising_steps: 30,
      dilatation_iterations: 5,
      dilatation_kernel: [10,10],
      garment: "https://replicate.delivery/pbxt/MgGhe8U8lLnCH4pWnIP7Gc3hkv2Pq8v35zZi1ohTWrirUHTh/WhatsApp%20Image%202025-03-18%20at%2009.11.23.jpeg",
      garment_type: "upper_body",
      guidance_scale: 2.5,
      neck_offset_removal: 20,
      person: "https://replicate.delivery/pbxt/MgGhdsL2rCACbqcW2DbVpmn7iZVRVYCDv0ilzkETea405dXj/Alex%20Consani%20Getty%20Image%201779424797.webp",
      reference_unet_acceleration: false,
      repaint: false,
      seed: 42,
      stroke_width_mask: 35
    }
  }
);

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=r8_Wwb**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run alquimia-ai/schiaparelli using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "alquimia-ai/schiaparelli:7b36045b2d4d84c7962afd723f126748e40a3d3b3f7626fbba75c1ddd593771b",
    input={
        "denoising_steps": 30,
        "dilatation_iterations": 5,
        "dilatation_kernel": [10,10],
        "garment": "https://replicate.delivery/pbxt/MgGhe8U8lLnCH4pWnIP7Gc3hkv2Pq8v35zZi1ohTWrirUHTh/WhatsApp%20Image%202025-03-18%20at%2009.11.23.jpeg",
        "garment_type": "upper_body",
        "guidance_scale": 2.5,
        "neck_offset_removal": 20,
        "person": "https://replicate.delivery/pbxt/MgGhdsL2rCACbqcW2DbVpmn7iZVRVYCDv0ilzkETea405dXj/Alex%20Consani%20Getty%20Image%201779424797.webp",
        "reference_unet_acceleration": False,
        "repaint": False,
        "seed": 42,
        "stroke_width_mask": 35
    }
)

# The alquimia-ai/schiaparelli model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/alquimia-ai/schiaparelli/api#output-schema
    print(item)

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=r8_Wwb**********************************

This is your API token. Keep it to yourself.

Run alquimia-ai/schiaparelli 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": "alquimia-ai/schiaparelli:7b36045b2d4d84c7962afd723f126748e40a3d3b3f7626fbba75c1ddd593771b",
    "input": {
      "denoising_steps": 30,
      "dilatation_iterations": 5,
      "dilatation_kernel": [10,10],
      "garment": "https://replicate.delivery/pbxt/MgGhe8U8lLnCH4pWnIP7Gc3hkv2Pq8v35zZi1ohTWrirUHTh/WhatsApp%20Image%202025-03-18%20at%2009.11.23.jpeg",
      "garment_type": "upper_body",
      "guidance_scale": 2.5,
      "neck_offset_removal": 20,
      "person": "https://replicate.delivery/pbxt/MgGhdsL2rCACbqcW2DbVpmn7iZVRVYCDv0ilzkETea405dXj/Alex%20Consani%20Getty%20Image%201779424797.webp",
      "reference_unet_acceleration": false,
      "repaint": false,
      "seed": 42,
      "stroke_width_mask": 35
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "outputType": "object",
  "properties": {
    "mask": {
      "outputType": "uri",
      "mimeType": "image/png",
      "inferred": false,
      "outputValue": "https://replicate.delivery/xezq/W4ny9MsVf4TDJK0IQyHN8jiSVkdDtwwdq01jOVoTxvTnu4MKA/tmp5zmw8fo9.png",
      "typeMismatch": false
    },
    "vton": {
      "outputType": "uri",
      "mimeType": "image/png",
      "inferred": false,
      "outputValue": "https://replicate.delivery/xezq/e4Tws8EotrwXFC4h3K0hFB9fRjTSpAZSMNB6nwIFLtlOdxZUA/tmpckpq7x24.png",
      "typeMismatch": false
    },
    "open_pose": {
      "outputType": "uri",
      "mimeType": "image/png",
      "inferred": false,
      "outputValue": "https://replicate.delivery/xezq/WEDgw4z3b9qnBBMLMu9Adg4TMtUc2qkELz7vU7TkNAuTXcGF/tmpm7ucr4lu.png",
      "typeMismatch": false
    },
    "dense_pose": {
      "outputType": "uri",
      "mimeType": "image/png",
      "inferred": false,
      "outputValue": "https://replicate.delivery/xezq/wsciNoVfOuw2WSm0IyKSxE3OspnDxepXgq0hZJkyfnmd6izoA/tmp15dzbfp_.png",
      "typeMismatch": false
    },
    "human_parsing": {
      "outputType": "uri",
      "mimeType": "image/png",
      "inferred": false,
      "outputValue": "https://replicate.delivery/xezq/yOkdOKdzW5I5CFWmYNvbQad34MaGxd9Cfkxf4x579nfd6izoA/tmpuiv9ry9j.png",
      "typeMismatch": false
    }
  },
  "inferred": false,
  "outputValue": {
    "dense_pose": "https://replicate.delivery/xezq/wsciNoVfOuw2WSm0IyKSxE3OspnDxepXgq0hZJkyfnmd6izoA/tmp15dzbfp_.png",
    "human_parsing": "https://replicate.delivery/xezq/yOkdOKdzW5I5CFWmYNvbQad34MaGxd9Cfkxf4x579nfd6izoA/tmpuiv9ry9j.png",
    "mask": "https://replicate.delivery/xezq/W4ny9MsVf4TDJK0IQyHN8jiSVkdDtwwdq01jOVoTxvTnu4MKA/tmp5zmw8fo9.png",
    "open_pose": "https://replicate.delivery/xezq/WEDgw4z3b9qnBBMLMu9Adg4TMtUc2qkELz7vU7TkNAuTXcGF/tmpm7ucr4lu.png",
    "vton": "https://replicate.delivery/xezq/e4Tws8EotrwXFC4h3K0hFB9fRjTSpAZSMNB6nwIFLtlOdxZUA/tmpckpq7x24.png"
  },
  "typeMismatch": false
}

5 / 5

{
  "id": "ksezyf5vjxrme0cnn4rvk2w7yw",
  "model": "alquimia-ai/schiaparelli",
  "version": "7b36045b2d4d84c7962afd723f126748e40a3d3b3f7626fbba75c1ddd593771b",
  "deployment": "alquimia-ai/schiaparelli-vton",
  "input": {
    "denoising_steps": 30,
    "dilatation_iterations": 5,
    "dilatation_kernel": [
      10,
      10
    ],
    "garment": "https://replicate.delivery/pbxt/MgGhe8U8lLnCH4pWnIP7Gc3hkv2Pq8v35zZi1ohTWrirUHTh/WhatsApp%20Image%202025-03-18%20at%2009.11.23.jpeg",
    "garment_type": "upper_body",
    "guidance_scale": 2.5,
    "neck_offset_removal": 20,
    "person": "https://replicate.delivery/pbxt/MgGhdsL2rCACbqcW2DbVpmn7iZVRVYCDv0ilzkETea405dXj/Alex%20Consani%20Getty%20Image%201779424797.webp",
    "reference_unet_acceleration": false,
    "repaint": false,
    "seed": 42,
    "stroke_width_mask": 35
  },
  "logs": "0%|          | 0/1 [00:00<?, ?it/s]\n100%|██████████| 1/1 [00:04<00:00,  4.11s/it]\n100%|██████████| 1/1 [00:04<00:00,  4.11s/it]\n  0%|          | 0/1 [00:00<?, ?it/s]\n100%|██████████| 1/1 [00:03<00:00,  3.54s/it]\n100%|██████████| 1/1 [00:03<00:00,  3.54s/it]\n/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/functional.py:539: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:3637.)\nreturn _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]\n  0%|          | 0/30 [00:00<?, ?it/s]/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/models/resnet.py:323: FutureWarning: `scale` is deprecated and will be removed in version 1.0.0. The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`.\ndeprecate(\"scale\", \"1.0.0\", deprecation_message)\n/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/models/activations.py:116: FutureWarning: `scale` is deprecated and will be removed in version 1.0.0. The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`.\ndeprecate(\"scale\", \"1.0.0\", deprecation_message)\n/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/models/downsampling.py:135: FutureWarning: `scale` is deprecated and will be removed in version 1.0.0. The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`.\ndeprecate(\"scale\", \"1.0.0\", deprecation_message)\n/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/models/upsampling.py:145: FutureWarning: `scale` is deprecated and will be removed in version 1.0.0. The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`.\ndeprecate(\"scale\", \"1.0.0\", deprecation_message)\n  3%|▎         | 1/30 [00:00<00:05,  5.12it/s]\n  7%|▋         | 2/30 [00:00<00:05,  5.48it/s]\n 10%|█         | 3/30 [00:00<00:04,  5.57it/s]\n 13%|█▎        | 4/30 [00:00<00:04,  5.64it/s]\n 17%|█▋        | 5/30 [00:00<00:04,  5.68it/s]\n 20%|██        | 6/30 [00:01<00:04,  5.70it/s]\n 23%|██▎       | 7/30 [00:01<00:04,  5.72it/s]\n 27%|██▋       | 8/30 [00:01<00:03,  5.74it/s]\n 30%|███       | 9/30 [00:01<00:03,  5.74it/s]\n 33%|███▎      | 10/30 [00:01<00:03,  5.75it/s]\n 37%|███▋      | 11/30 [00:01<00:03,  5.76it/s]\n 40%|████      | 12/30 [00:02<00:03,  5.74it/s]\n 43%|████▎     | 13/30 [00:02<00:02,  5.74it/s]\n 47%|████▋     | 14/30 [00:02<00:02,  5.74it/s]\n 50%|█████     | 15/30 [00:02<00:02,  5.74it/s]\n 53%|█████▎    | 16/30 [00:02<00:02,  5.74it/s]\n 57%|█████▋    | 17/30 [00:02<00:02,  5.75it/s]\n 60%|██████    | 18/30 [00:03<00:02,  5.76it/s]\n 63%|██████▎   | 19/30 [00:03<00:01,  5.75it/s]\n 67%|██████▋   | 20/30 [00:03<00:01,  5.74it/s]\n 70%|███████   | 21/30 [00:03<00:01,  5.74it/s]\n 73%|███████▎  | 22/30 [00:03<00:01,  5.74it/s]\n 77%|███████▋  | 23/30 [00:04<00:01,  5.73it/s]\n 80%|████████  | 24/30 [00:04<00:01,  5.73it/s]\n 83%|████████▎ | 25/30 [00:04<00:00,  5.74it/s]\n 87%|████████▋ | 26/30 [00:04<00:00,  5.72it/s]\n 90%|█████████ | 27/30 [00:04<00:00,  5.72it/s]\n 93%|█████████▎| 28/30 [00:04<00:00,  5.73it/s]\n 97%|█████████▋| 29/30 [00:05<00:00,  5.74it/s]\n100%|██████████| 30/30 [00:05<00:00,  5.74it/s]\n100%|██████████| 30/30 [00:05<00:00,  5.72it/s]",
  "output": [
    {
      "dense_pose": null,
      "human_parsing": "https://replicate.delivery/xezq/wHsd8yFRKEaCB9vojBDsbPRWDTMenWknLbg2CSzGmi9gu4MKA/tmpuiv9ry9j.png",
      "mask": null,
      "open_pose": null,
      "vton": null
    },
    {
      "dense_pose": null,
      "human_parsing": "https://replicate.delivery/xezq/NN4zsMEf7PULUCjVRRgDIqFqE6v63yRlnJeV0SRvZrXIdxZUA/tmpuiv9ry9j.png",
      "mask": "https://replicate.delivery/xezq/knHJvV8yRV67J1qY1YYNdmlSxvi8VcWZk3OxBkHyjpASXcGF/tmp5zmw8fo9.png",
      "open_pose": null,
      "vton": null
    },
    {
      "dense_pose": null,
      "human_parsing": "https://replicate.delivery/xezq/nnPNFDD5MIbIDRq1ffrmBDaGf4EhbFfdmgYgrnHC5jZj0FnRB/tmpuiv9ry9j.png",
      "mask": "https://replicate.delivery/xezq/SgeLOJoYqpwwGKDrGnxgAifUQyFoBwyHYfuQ4esegJCEpLOjC/tmp5zmw8fo9.png",
      "open_pose": "https://replicate.delivery/xezq/qgQO5uhZFz7JJdZDeN1wb8Dt6GD5Hei75z5LG92ruGeR6izoA/tmpm7ucr4lu.png",
      "vton": null
    },
    {
      "dense_pose": "https://replicate.delivery/xezq/T4JuGxZqu270HlzAF9I77A3hVaj3SzTx2n3pGH4g9AKSXcGF/tmp15dzbfp_.png",
      "human_parsing": "https://replicate.delivery/xezq/J8p7JoV1fAwHASwMstulOtsUuHSKnmDZS9e6aJdi1EFIdxZUA/tmpuiv9ry9j.png",
      "mask": "https://replicate.delivery/xezq/zs03S5ZpYv5TBhbkTY3ew0ElrWXKOhzeEpmjuOJoTvVIdxZUA/tmp5zmw8fo9.png",
      "open_pose": "https://replicate.delivery/xezq/D3cLjj0omQpdARh16ihIFp6Kz12EZ7UF5FmmIXKfmDDku4MKA/tmpm7ucr4lu.png",
      "vton": null
    },
    {
      "dense_pose": "https://replicate.delivery/xezq/wsciNoVfOuw2WSm0IyKSxE3OspnDxepXgq0hZJkyfnmd6izoA/tmp15dzbfp_.png",
      "human_parsing": "https://replicate.delivery/xezq/yOkdOKdzW5I5CFWmYNvbQad34MaGxd9Cfkxf4x579nfd6izoA/tmpuiv9ry9j.png",
      "mask": "https://replicate.delivery/xezq/W4ny9MsVf4TDJK0IQyHN8jiSVkdDtwwdq01jOVoTxvTnu4MKA/tmp5zmw8fo9.png",
      "open_pose": "https://replicate.delivery/xezq/WEDgw4z3b9qnBBMLMu9Adg4TMtUc2qkELz7vU7TkNAuTXcGF/tmpm7ucr4lu.png",
      "vton": "https://replicate.delivery/xezq/e4Tws8EotrwXFC4h3K0hFB9fRjTSpAZSMNB6nwIFLtlOdxZUA/tmpckpq7x24.png"
    }
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2025-03-18T12:19:23.671Z",
  "started_at": "2025-03-18T12:21:14.08845Z",
  "completed_at": "2025-03-18T12:21:34.339401Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/ksezyf5vjxrme0cnn4rvk2w7yw/cancel",
    "get": "https://api.replicate.com/v1/predictions/ksezyf5vjxrme0cnn4rvk2w7yw",
    "web": "https://replicate.com/p/ksezyf5vjxrme0cnn4rvk2w7yw"
  },
  "metrics": {
    "predict_time": 20.250951101,
    "total_time": 130.668401
  }
}

Generated in

20.3 seconds

0%| | 0/1 [00:00<?, ?it/s] 100%|██████████| 1/1 [00:04<00:00, 4.11s/it] 100%|██████████| 1/1 [00:04<00:00, 4.11s/it] 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████| 1/1 [00:03<00:00, 3.54s/it] 100%|██████████| 1/1 [00:03<00:00, 3.54s/it] /root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/functional.py:539: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:3637.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] 0%| | 0/30 [00:00<?, ?it/s]/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/models/resnet.py:323: FutureWarning: `scale` is deprecated and will be removed in version 1.0.0. The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`. deprecate("scale", "1.0.0", deprecation_message) /root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/models/activations.py:116: FutureWarning: `scale` is deprecated and will be removed in version 1.0.0. The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`. deprecate("scale", "1.0.0", deprecation_message) /root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/models/downsampling.py:135: FutureWarning: `scale` is deprecated and will be removed in version 1.0.0. The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`. deprecate("scale", "1.0.0", deprecation_message) /root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/models/upsampling.py:145: FutureWarning: `scale` is deprecated and will be removed in version 1.0.0. The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`. deprecate("scale", "1.0.0", deprecation_message) 3%|▎ | 1/30 [00:00<00:05, 5.12it/s] 7%|▋ | 2/30 [00:00<00:05, 5.48it/s] 10%|█ | 3/30 [00:00<00:04, 5.57it/s] 13%|█▎ | 4/30 [00:00<00:04, 5.64it/s] 17%|█▋ | 5/30 [00:00<00:04, 5.68it/s] 20%|██ | 6/30 [00:01<00:04, 5.70it/s] 23%|██▎ | 7/30 [00:01<00:04, 5.72it/s] 27%|██▋ | 8/30 [00:01<00:03, 5.74it/s] 30%|███ | 9/30 [00:01<00:03, 5.74it/s] 33%|███▎ | 10/30 [00:01<00:03, 5.75it/s] 37%|███▋ | 11/30 [00:01<00:03, 5.76it/s] 40%|████ | 12/30 [00:02<00:03, 5.74it/s] 43%|████▎ | 13/30 [00:02<00:02, 5.74it/s] 47%|████▋ | 14/30 [00:02<00:02, 5.74it/s] 50%|█████ | 15/30 [00:02<00:02, 5.74it/s] 53%|█████▎ | 16/30 [00:02<00:02, 5.74it/s] 57%|█████▋ | 17/30 [00:02<00:02, 5.75it/s] 60%|██████ | 18/30 [00:03<00:02, 5.76it/s] 63%|██████▎ | 19/30 [00:03<00:01, 5.75it/s] 67%|██████▋ | 20/30 [00:03<00:01, 5.74it/s] 70%|███████ | 21/30 [00:03<00:01, 5.74it/s] 73%|███████▎ | 22/30 [00:03<00:01, 5.74it/s] 77%|███████▋ | 23/30 [00:04<00:01, 5.73it/s] 80%|████████ | 24/30 [00:04<00:01, 5.73it/s] 83%|████████▎ | 25/30 [00:04<00:00, 5.74it/s] 87%|████████▋ | 26/30 [00:04<00:00, 5.72it/s] 90%|█████████ | 27/30 [00:04<00:00, 5.72it/s] 93%|█████████▎| 28/30 [00:04<00:00, 5.73it/s] 97%|█████████▋| 29/30 [00:05<00:00, 5.74it/s] 100%|██████████| 30/30 [00:05<00:00, 5.74it/s] 100%|██████████| 30/30 [00:05<00:00, 5.72it/s]