Prediction

ID

9wxj8c2adsrgg0cf8zt9c1v99c

Status

Succeeded

Source

Web

Hardware

A40

Total duration

2m 17s

Created

over 1 year ago

Input

input_image

{
  "input_image": "https://cdn.fishki.net/upload/post/2019/08/01/3047343/tn/d333f85d3bcfccf832e70b5e7c155077-01.jpg"
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

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

const output = await replicate.run(
  "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
  {
    input: {
      input_image: "https://cdn.fishki.net/upload/post/2019/08/01/3047343/tn/d333f85d3bcfccf832e70b5e7c155077-01.jpg"
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

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

output = replicate.run(
    "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
    input={
        "input_image": "https://cdn.fishki.net/upload/post/2019/08/01/3047343/tn/d333f85d3bcfccf832e70b5e7c155077-01.jpg"
    }
)

# To access the file URL:
print(output.url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output.read())

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

Run kitaef/mytestmodel 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": "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
    "input": {
      "input_image": "https://cdn.fishki.net/upload/post/2019/08/01/3047343/tn/d333f85d3bcfccf832e70b5e7c155077-01.jpg"
    }
  }' \
  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/kitaef/mytestmodel@sha256:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191 \
  -i 'input_image="https://cdn.fishki.net/upload/post/2019/08/01/3047343/tn/d333f85d3bcfccf832e70b5e7c155077-01.jpg"'

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/kitaef/mytestmodel@sha256:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "input_image": "https://cdn.fishki.net/upload/post/2019/08/01/3047343/tn/d333f85d3bcfccf832e70b5e7c155077-01.jpg"
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-05-05T08:54:40.024484Z",
  "created_at": "2024-05-05T08:52:23.278000Z",
  "data_removed": false,
  "error": null,
  "id": "9wxj8c2adsrgg0cf8zt9c1v99c",
  "input": {
    "input_image": "https://cdn.fishki.net/upload/post/2019/08/01/3047343/tn/d333f85d3bcfccf832e70b5e7c155077-01.jpg"
  },
  "logs": "0%|          | 0/20 [00:00<?, ?it/s]/root/.pyenv/versions/3.11.9/lib/python3.11/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)\nreturn F.conv2d(input, weight, bias, self.stride,\n  5%|▌         | 1/20 [00:02<00:41,  2.19s/it]\n 10%|█         | 2/20 [00:02<00:20,  1.16s/it]\n 15%|█▌        | 3/20 [00:03<00:14,  1.20it/s]\n 20%|██        | 4/20 [00:03<00:10,  1.48it/s]\n 25%|██▌       | 5/20 [00:03<00:08,  1.70it/s]\n 30%|███       | 6/20 [00:04<00:07,  1.86it/s]\n 35%|███▌      | 7/20 [00:04<00:06,  1.98it/s]\n 40%|████      | 8/20 [00:05<00:05,  2.07it/s]\n 45%|████▌     | 9/20 [00:05<00:05,  2.14it/s]\n 50%|█████     | 10/20 [00:06<00:04,  2.18it/s]\n 55%|█████▌    | 11/20 [00:06<00:04,  2.21it/s]\n 60%|██████    | 12/20 [00:06<00:03,  2.24it/s]\n 65%|██████▌   | 13/20 [00:07<00:03,  2.25it/s]\n 70%|███████   | 14/20 [00:07<00:02,  2.26it/s]\n 75%|███████▌  | 15/20 [00:08<00:02,  2.27it/s]\n 80%|████████  | 16/20 [00:08<00:01,  2.28it/s]\n 85%|████████▌ | 17/20 [00:09<00:01,  2.28it/s]\n 90%|█████████ | 18/20 [00:09<00:00,  2.28it/s]\n 95%|█████████▌| 19/20 [00:10<00:00,  2.29it/s]\n100%|██████████| 20/20 [00:10<00:00,  2.29it/s]\n100%|██████████| 20/20 [00:10<00:00,  1.91it/s]",
  "metrics": {
    "predict_time": 18.179087,
    "total_time": 136.746484
  },
  "output": "https://replicate.delivery/pbxt/8oFfucYpBYQWOip5ngf6xzrY9DnC5GcIY8V1G2gMQgIPtPxSA/output.jpg",
  "started_at": "2024-05-05T08:54:21.845397Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/9wxj8c2adsrgg0cf8zt9c1v99c",
    "cancel": "https://api.replicate.com/v1/predictions/9wxj8c2adsrgg0cf8zt9c1v99c/cancel"
  },
  "version": "a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191"
}

Generated in

18.2 seconds

kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191

Prediction

Model

ID

7pxsqpes01rgp0cf8zwr57n8tr

Status

Succeeded

Source

Web

Hardware

A40

Total duration

35.0s

Created

over 1 year ago

Input

input_image

{
  "input_image": "https://www.meme-arsenal.com/memes/b34efd7b163e816f620c2f8da7029d7b.jpg"
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

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

const output = await replicate.run(
  "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
  {
    input: {
      input_image: "https://www.meme-arsenal.com/memes/b34efd7b163e816f620c2f8da7029d7b.jpg"
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

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

output = replicate.run(
    "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
    input={
        "input_image": "https://www.meme-arsenal.com/memes/b34efd7b163e816f620c2f8da7029d7b.jpg"
    }
)

# To access the file URL:
print(output.url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output.read())

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

Run kitaef/mytestmodel 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": "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
    "input": {
      "input_image": "https://www.meme-arsenal.com/memes/b34efd7b163e816f620c2f8da7029d7b.jpg"
    }
  }' \
  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/kitaef/mytestmodel@sha256:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191 \
  -i 'input_image="https://www.meme-arsenal.com/memes/b34efd7b163e816f620c2f8da7029d7b.jpg"'

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/kitaef/mytestmodel@sha256:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "input_image": "https://www.meme-arsenal.com/memes/b34efd7b163e816f620c2f8da7029d7b.jpg"
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-05-05T08:59:02.463892Z",
  "created_at": "2024-05-05T08:58:27.456000Z",
  "data_removed": false,
  "error": null,
  "id": "7pxsqpes01rgp0cf8zwr57n8tr",
  "input": {
    "input_image": "https://www.meme-arsenal.com/memes/b34efd7b163e816f620c2f8da7029d7b.jpg"
  },
  "logs": "0%|          | 0/20 [00:00<?, ?it/s]/root/.pyenv/versions/3.11.9/lib/python3.11/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)\nreturn F.conv2d(input, weight, bias, self.stride,\n  5%|▌         | 1/20 [00:02<00:45,  2.41s/it]\n 10%|█         | 2/20 [00:02<00:21,  1.17s/it]\n 15%|█▌        | 3/20 [00:03<00:13,  1.28it/s]\n 20%|██        | 4/20 [00:03<00:09,  1.69it/s]\n 25%|██▌       | 5/20 [00:03<00:07,  2.05it/s]\n 30%|███       | 6/20 [00:03<00:05,  2.35it/s]\n 35%|███▌      | 7/20 [00:04<00:05,  2.60it/s]\n 40%|████      | 8/20 [00:04<00:04,  2.79it/s]\n 45%|████▌     | 9/20 [00:04<00:03,  2.93it/s]\n 50%|█████     | 10/20 [00:05<00:03,  3.04it/s]\n 55%|█████▌    | 11/20 [00:05<00:02,  3.11it/s]\n 60%|██████    | 12/20 [00:05<00:02,  3.16it/s]\n 65%|██████▌   | 13/20 [00:06<00:02,  3.20it/s]\n 70%|███████   | 14/20 [00:06<00:01,  3.23it/s]\n 75%|███████▌  | 15/20 [00:06<00:01,  3.25it/s]\n 80%|████████  | 16/20 [00:06<00:01,  3.26it/s]\n 85%|████████▌ | 17/20 [00:07<00:00,  3.27it/s]\n 90%|█████████ | 18/20 [00:07<00:00,  3.28it/s]\n 95%|█████████▌| 19/20 [00:07<00:00,  3.28it/s]\n100%|██████████| 20/20 [00:08<00:00,  3.28it/s]\n100%|██████████| 20/20 [00:08<00:00,  2.44it/s]",
  "metrics": {
    "predict_time": 14.741133,
    "total_time": 35.007892
  },
  "output": "https://replicate.delivery/pbxt/DdyDdWFmlEafJSlP6nx0TCYaghXqwjYPXytqGw3NzfqVxPxSA/output.jpg",
  "started_at": "2024-05-05T08:58:47.722759Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/7pxsqpes01rgp0cf8zwr57n8tr",
    "cancel": "https://api.replicate.com/v1/predictions/7pxsqpes01rgp0cf8zwr57n8tr/cancel"
  },
  "version": "a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191"
}

Generated in

14.8 seconds

kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191

Prediction

Model

ID

sx2xda9qwxrgm0cf8zyt44zwc0

Status

Succeeded

Source

Web

Hardware

A40

Total duration

8.4s

Created

over 1 year ago

Input

input_image

{
  "input_image": "https://replicate.delivery/pbxt/KrhNPcgSMXCvtGcTt5YuLXvgD5IeRPRFTIJ86f2VdZp8CMMv/image.png"
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

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

const output = await replicate.run(
  "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
  {
    input: {
      input_image: "https://replicate.delivery/pbxt/KrhNPcgSMXCvtGcTt5YuLXvgD5IeRPRFTIJ86f2VdZp8CMMv/image.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.

pip install replicate

Import the client:

import replicate

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

output = replicate.run(
    "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
    input={
        "input_image": "https://replicate.delivery/pbxt/KrhNPcgSMXCvtGcTt5YuLXvgD5IeRPRFTIJ86f2VdZp8CMMv/image.png"
    }
)

# To access the file URL:
print(output.url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output.read())

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

Run kitaef/mytestmodel 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": "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
    "input": {
      "input_image": "https://replicate.delivery/pbxt/KrhNPcgSMXCvtGcTt5YuLXvgD5IeRPRFTIJ86f2VdZp8CMMv/image.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/kitaef/mytestmodel@sha256:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191 \
  -i 'input_image="https://replicate.delivery/pbxt/KrhNPcgSMXCvtGcTt5YuLXvgD5IeRPRFTIJ86f2VdZp8CMMv/image.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/kitaef/mytestmodel@sha256:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "input_image": "https://replicate.delivery/pbxt/KrhNPcgSMXCvtGcTt5YuLXvgD5IeRPRFTIJ86f2VdZp8CMMv/image.png"
    }
  }' \
  http://localhost:5000/predictions

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

Output

Generated in

8.4 seconds

kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191

Prediction

Model

ID

q81gs02n21rgj0cf905trq4hw8

Status

Succeeded

Source

Web

Hardware

A40

Total duration

33.3s

Created

over 1 year ago

Input

input_image

{
  "input_image": "https://glavcom.ua/img/article/5431/70_main.jpg"
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

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

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

const output = await replicate.run(
  "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
  {
    input: {
      input_image: "https://glavcom.ua/img/article/5431/70_main.jpg"
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

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

output = replicate.run(
    "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
    input={
        "input_image": "https://glavcom.ua/img/article/5431/70_main.jpg"
    }
)

# To access the file URL:
print(output.url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output.read())

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

Run kitaef/mytestmodel 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": "kitaef/mytestmodel:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191",
    "input": {
      "input_image": "https://glavcom.ua/img/article/5431/70_main.jpg"
    }
  }' \
  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/kitaef/mytestmodel@sha256:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191 \
  -i 'input_image="https://glavcom.ua/img/article/5431/70_main.jpg"'

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/kitaef/mytestmodel@sha256:a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "input_image": "https://glavcom.ua/img/article/5431/70_main.jpg"
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-05-05T09:18:06.613822Z",
  "created_at": "2024-05-05T09:17:33.328000Z",
  "data_removed": false,
  "error": null,
  "id": "q81gs02n21rgj0cf905trq4hw8",
  "input": {
    "input_image": "https://glavcom.ua/img/article/5431/70_main.jpg"
  },
  "logs": "0%|          | 0/20 [00:00<?, ?it/s]/root/.pyenv/versions/3.11.9/lib/python3.11/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)\nreturn F.conv2d(input, weight, bias, self.stride,\n  5%|▌         | 1/20 [00:02<00:42,  2.26s/it]\n 10%|█         | 2/20 [00:02<00:19,  1.08s/it]\n 15%|█▌        | 3/20 [00:02<00:12,  1.40it/s]\n 20%|██        | 4/20 [00:03<00:08,  1.88it/s]\n 25%|██▌       | 5/20 [00:03<00:06,  2.30it/s]\n 30%|███       | 6/20 [00:03<00:05,  2.67it/s]\n 35%|███▌      | 7/20 [00:03<00:04,  2.97it/s]\n 40%|████      | 8/20 [00:04<00:03,  3.22it/s]\n 45%|████▌     | 9/20 [00:04<00:03,  3.40it/s]\n 50%|█████     | 10/20 [00:04<00:02,  3.54it/s]\n 55%|█████▌    | 11/20 [00:04<00:02,  3.64it/s]\n 60%|██████    | 12/20 [00:05<00:02,  3.71it/s]\n 65%|██████▌   | 13/20 [00:05<00:01,  3.75it/s]\n 70%|███████   | 14/20 [00:05<00:01,  3.79it/s]\n 75%|███████▌  | 15/20 [00:05<00:01,  3.82it/s]\n 80%|████████  | 16/20 [00:06<00:01,  3.84it/s]\n 85%|████████▌ | 17/20 [00:06<00:00,  3.86it/s]\n 90%|█████████ | 18/20 [00:06<00:00,  3.87it/s]\n 95%|█████████▌| 19/20 [00:06<00:00,  3.87it/s]\n100%|██████████| 20/20 [00:07<00:00,  3.87it/s]\n100%|██████████| 20/20 [00:07<00:00,  2.79it/s]",
  "metrics": {
    "predict_time": 14.339265,
    "total_time": 33.285822
  },
  "output": "https://replicate.delivery/pbxt/2uYjnUBfzvTIZq622fJkjQembhq6931fVrykda7xpN63MAFLB/output.jpg",
  "started_at": "2024-05-05T09:17:52.274557Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/q81gs02n21rgj0cf905trq4hw8",
    "cancel": "https://api.replicate.com/v1/predictions/q81gs02n21rgj0cf905trq4hw8/cancel"
  },
  "version": "a0ebe82aad0744fbc8f6964143760ed306af3864daa4b62a776b656636c1f191"
}

Generated in

14.3 seconds