andreasjansson / dreamsim

Image similarity metric that that compares a reference image to a set of images.

Cold

Public
303 runs
A100 (80GB)
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Prediction

andreasjansson/dreamsim:57b87c80e71c103eebc3499bb602b411ff8a385b52caa74c0b8cfd45e1ea6520

Model

andreasjansson/dreamsim:57b87c80

z24fmwb4t9rj40cjeamb458hnm

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

77.7s

Created

8 months ago

Input

images: https://bflapistorage.blob.core.windows.net/public/c8145aa6e5894cbd815d6ce708fea9f2/sample.jpg,https://replicate.delivery/czjl/dTjOfyxTTSQyc65ushgtv9O9z4oLoI4gVOW3Y7bHIgcFLhyJA/output.webp

{
  "images": "https://bflapistorage.blob.core.windows.net/public/c8145aa6e5894cbd815d6ce708fea9f2/sample.jpg,https://replicate.delivery/czjl/dTjOfyxTTSQyc65ushgtv9O9z4oLoI4gVOW3Y7bHIgcFLhyJA/output.webp"
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

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

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

const output = await replicate.run(
  "andreasjansson/dreamsim:57b87c80e71c103eebc3499bb602b411ff8a385b52caa74c0b8cfd45e1ea6520",
  {
    input: {
      images: "https://bflapistorage.blob.core.windows.net/public/c8145aa6e5894cbd815d6ce708fea9f2/sample.jpg,https://replicate.delivery/czjl/dTjOfyxTTSQyc65ushgtv9O9z4oLoI4gVOW3Y7bHIgcFLhyJA/output.webp"
    }
  }
);

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

Import the client:

import replicate

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

output = replicate.run(
    "andreasjansson/dreamsim:57b87c80e71c103eebc3499bb602b411ff8a385b52caa74c0b8cfd45e1ea6520",
    input={
        "images": "https://bflapistorage.blob.core.windows.net/public/c8145aa6e5894cbd815d6ce708fea9f2/sample.jpg,https://replicate.delivery/czjl/dTjOfyxTTSQyc65ushgtv9O9z4oLoI4gVOW3Y7bHIgcFLhyJA/output.webp"
    }
)
print(output)

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

Run andreasjansson/dreamsim 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": "andreasjansson/dreamsim:57b87c80e71c103eebc3499bb602b411ff8a385b52caa74c0b8cfd45e1ea6520",
    "input": {
      "images": "https://bflapistorage.blob.core.windows.net/public/c8145aa6e5894cbd815d6ce708fea9f2/sample.jpg,https://replicate.delivery/czjl/dTjOfyxTTSQyc65ushgtv9O9z4oLoI4gVOW3Y7bHIgcFLhyJA/output.webp"
    }
  }' \
  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/andreasjansson/dreamsim@sha256:57b87c80e71c103eebc3499bb602b411ff8a385b52caa74c0b8cfd45e1ea6520 \
  -i 'images="https://bflapistorage.blob.core.windows.net/public/c8145aa6e5894cbd815d6ce708fea9f2/sample.jpg,https://replicate.delivery/czjl/dTjOfyxTTSQyc65ushgtv9O9z4oLoI4gVOW3Y7bHIgcFLhyJA/output.webp"'

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/andreasjansson/dreamsim@sha256:57b87c80e71c103eebc3499bb602b411ff8a385b52caa74c0b8cfd45e1ea6520
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "images": "https://bflapistorage.blob.core.windows.net/public/c8145aa6e5894cbd815d6ce708fea9f2/sample.jpg,https://replicate.delivery/czjl/dTjOfyxTTSQyc65ushgtv9O9z4oLoI4gVOW3Y7bHIgcFLhyJA/output.webp"
    }
  }' \
  http://localhost:5000/predictions

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

Output

{ "https://bflapistorage.blob.core.windows.net/public/c8145aa6e5894cbd815d6ce708fea9f2/sample.jpg": { "https://replicate.delivery/czjl/dTjOfyxTTSQyc65ushgtv9O9z4oLoI4gVOW3Y7bHIgcFLhyJA/output.webp": 0.44552165269851685 } }

Generated in

2.6 seconds

Tweak it Share Report

Want to make some of these yourself?

Run this model