Prediction

ID

ftm2pz3bqxkftg3g5aqnazr4ta

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

10.9s

Created

over 1 year ago

Input

image1
prompt: swimming underwater
num_images: 4
negative_prompt
num_inference_steps: 50
text_guidance_scale: 6

{
  "image1": "https://replicate.delivery/pbxt/K0TrpSohDsH9c5EkQU8MgmYEruX4j8LCGYOJ2fFPAUmbp2QL/dog.jpg",
  "prompt": "<i> swimming underwater",
  "num_images": 4,
  "negative_prompt": "",
  "num_inference_steps": 50,
  "text_guidance_scale": 6
}

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 adirik/kosmos-g using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
  {
    input: {
      image1: "https://replicate.delivery/pbxt/K0TrpSohDsH9c5EkQU8MgmYEruX4j8LCGYOJ2fFPAUmbp2QL/dog.jpg",
      prompt: "<i> swimming underwater",
      num_images: 4,
      negative_prompt: "",
      num_inference_steps: 50,
      text_guidance_scale: 6
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run adirik/kosmos-g using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
    input={
        "image1": "https://replicate.delivery/pbxt/K0TrpSohDsH9c5EkQU8MgmYEruX4j8LCGYOJ2fFPAUmbp2QL/dog.jpg",
        "prompt": "<i> swimming underwater",
        "num_images": 4,
        "negative_prompt": "",
        "num_inference_steps": 50,
        "text_guidance_scale": 6
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run adirik/kosmos-g 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": "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
    "input": {
      "image1": "https://replicate.delivery/pbxt/K0TrpSohDsH9c5EkQU8MgmYEruX4j8LCGYOJ2fFPAUmbp2QL/dog.jpg",
      "prompt": "<i> swimming underwater",
      "num_images": 4,
      "negative_prompt": "",
      "num_inference_steps": 50,
      "text_guidance_scale": 6
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

10.9 seconds

adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9

Prediction

Model

ID

wqw4bedbizmz35455slnlpdbsq

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

4.1s

Created

over 1 year ago

Input

image1
prompt: in Minecraft
num_images: 1
negative_prompt
num_inference_steps: 50
text_guidance_scale: 6

{
  "image1": "https://replicate.delivery/pbxt/K0TwWeDjoJbW3ckNsgms5wONhFHtjeCGXl3ZMgrZt7zDq06T/dog2.jpg",
  "prompt": "<i> in Minecraft",
  "num_images": 1,
  "negative_prompt": "",
  "num_inference_steps": 50,
  "text_guidance_scale": 6
}

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 adirik/kosmos-g using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
  {
    input: {
      image1: "https://replicate.delivery/pbxt/K0TwWeDjoJbW3ckNsgms5wONhFHtjeCGXl3ZMgrZt7zDq06T/dog2.jpg",
      prompt: "<i> in Minecraft",
      num_images: 1,
      negative_prompt: "",
      num_inference_steps: 50,
      text_guidance_scale: 6
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run adirik/kosmos-g using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
    input={
        "image1": "https://replicate.delivery/pbxt/K0TwWeDjoJbW3ckNsgms5wONhFHtjeCGXl3ZMgrZt7zDq06T/dog2.jpg",
        "prompt": "<i> in Minecraft",
        "num_images": 1,
        "negative_prompt": "",
        "num_inference_steps": 50,
        "text_guidance_scale": 6
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run adirik/kosmos-g 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": "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
    "input": {
      "image1": "https://replicate.delivery/pbxt/K0TwWeDjoJbW3ckNsgms5wONhFHtjeCGXl3ZMgrZt7zDq06T/dog2.jpg",
      "prompt": "<i> in Minecraft",
      "num_images": 1,
      "negative_prompt": "",
      "num_inference_steps": 50,
      "text_guidance_scale": 6
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

4.1 seconds

adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9

Prediction

Model

ID

e4abqbtb3bvqljppvuoee2z63i

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

4.8s

Created

over 1 year ago

Input

image1
image2
prompt: in \'s jacket
num_images: 1
negative_prompt
num_inference_steps: 50
text_guidance_scale: 6

{
  "image1": "https://replicate.delivery/pbxt/K0TxF0O8QXgPaz8rKUF5QmzN46SXpvwmeHVUVXsvM1luSG7e/bengio.jpg",
  "image2": "https://replicate.delivery/pbxt/K0TxETpbGqLdjEQ7Ly6jEhQ4j1ipa9hMutoEiNUimAckBC2E/huang.jpg",
  "prompt": "<i> in <i>\\'s jacket",
  "num_images": 1,
  "negative_prompt": "",
  "num_inference_steps": 50,
  "text_guidance_scale": 6
}

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 adirik/kosmos-g using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
  {
    input: {
      image1: "https://replicate.delivery/pbxt/K0TxF0O8QXgPaz8rKUF5QmzN46SXpvwmeHVUVXsvM1luSG7e/bengio.jpg",
      image2: "https://replicate.delivery/pbxt/K0TxETpbGqLdjEQ7Ly6jEhQ4j1ipa9hMutoEiNUimAckBC2E/huang.jpg",
      prompt: "<i> in <i>\\'s jacket",
      num_images: 1,
      negative_prompt: "",
      num_inference_steps: 50,
      text_guidance_scale: 6
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run adirik/kosmos-g using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
    input={
        "image1": "https://replicate.delivery/pbxt/K0TxF0O8QXgPaz8rKUF5QmzN46SXpvwmeHVUVXsvM1luSG7e/bengio.jpg",
        "image2": "https://replicate.delivery/pbxt/K0TxETpbGqLdjEQ7Ly6jEhQ4j1ipa9hMutoEiNUimAckBC2E/huang.jpg",
        "prompt": "<i> in <i>\\'s jacket",
        "num_images": 1,
        "negative_prompt": "",
        "num_inference_steps": 50,
        "text_guidance_scale": 6
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run adirik/kosmos-g 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": "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
    "input": {
      "image1": "https://replicate.delivery/pbxt/K0TxF0O8QXgPaz8rKUF5QmzN46SXpvwmeHVUVXsvM1luSG7e/bengio.jpg",
      "image2": "https://replicate.delivery/pbxt/K0TxETpbGqLdjEQ7Ly6jEhQ4j1ipa9hMutoEiNUimAckBC2E/huang.jpg",
      "prompt": "<i> in <i>\\\\\'s jacket",
      "num_images": 1,
      "negative_prompt": "",
      "num_inference_steps": 50,
      "text_guidance_scale": 6
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

4.8 seconds

adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9

Prediction

Model

ID

cbh3n53bnkv246qxcxcm2ep7gu

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

4.6s

Created

over 1 year ago

Input

image1
image2
prompt: as an oil painting in the style of
num_images: 1
negative_prompt
num_inference_steps: 50
text_guidance_scale: 6

{
  "image1": "https://replicate.delivery/pbxt/K0U0uXzVNWTg1YsRV28fKzUneHU3tI5Nxfdcav3ysG35VYSa/doctor.jpg",
  "image2": "https://replicate.delivery/pbxt/K0U0v0d1nJaGk6xok96eAlr1tTe5WtYlBy2cFy1DnNbEvISO/vangogh.jpg",
  "prompt": "<i> as an oil painting in the style of <i>",
  "num_images": 1,
  "negative_prompt": "",
  "num_inference_steps": 50,
  "text_guidance_scale": 6
}

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 adirik/kosmos-g using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
  {
    input: {
      image1: "https://replicate.delivery/pbxt/K0U0uXzVNWTg1YsRV28fKzUneHU3tI5Nxfdcav3ysG35VYSa/doctor.jpg",
      image2: "https://replicate.delivery/pbxt/K0U0v0d1nJaGk6xok96eAlr1tTe5WtYlBy2cFy1DnNbEvISO/vangogh.jpg",
      prompt: "<i> as an oil painting in the style of <i>",
      num_images: 1,
      negative_prompt: "",
      num_inference_steps: 50,
      text_guidance_scale: 6
    }
  }
);

// 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.

pip install replicate

Import the client:

import replicate

Run adirik/kosmos-g using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
    input={
        "image1": "https://replicate.delivery/pbxt/K0U0uXzVNWTg1YsRV28fKzUneHU3tI5Nxfdcav3ysG35VYSa/doctor.jpg",
        "image2": "https://replicate.delivery/pbxt/K0U0v0d1nJaGk6xok96eAlr1tTe5WtYlBy2cFy1DnNbEvISO/vangogh.jpg",
        "prompt": "<i> as an oil painting in the style of <i>",
        "num_images": 1,
        "negative_prompt": "",
        "num_inference_steps": 50,
        "text_guidance_scale": 6
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

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

Run adirik/kosmos-g 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": "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
    "input": {
      "image1": "https://replicate.delivery/pbxt/K0U0uXzVNWTg1YsRV28fKzUneHU3tI5Nxfdcav3ysG35VYSa/doctor.jpg",
      "image2": "https://replicate.delivery/pbxt/K0U0v0d1nJaGk6xok96eAlr1tTe5WtYlBy2cFy1DnNbEvISO/vangogh.jpg",
      "prompt": "<i> as an oil painting in the style of <i>",
      "num_images": 1,
      "negative_prompt": "",
      "num_inference_steps": 50,
      "text_guidance_scale": 6
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

4.5 seconds

adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9

Prediction

Model

ID

po7r5j3beyfcgdqc34vg7fmcvi

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

4.6s

Created

over 1 year ago

Input

seed: 20
image1
image2
prompt: in the suit of
num_images: 1
negative_prompt
num_inference_steps: 50
text_guidance_scale: 6

{
  "seed": 20,
  "image1": "https://replicate.delivery/pbxt/K0Tzk2bsc76SSsRgrJSoh0fnzrB5M0Dqeqe7YHLxf1x7fU4S/FELV-cat.jpg",
  "image2": "https://replicate.delivery/pbxt/K0TzkJl3lco0aPVIg8iQYUB0ursK7ZWO0ECEVsxMMQlf5eKH/ironman.jpg",
  "prompt": "<i> in the suit of <i>",
  "num_images": 1,
  "negative_prompt": "",
  "num_inference_steps": 50,
  "text_guidance_scale": 6
}

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 adirik/kosmos-g using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/kosmos-g:56f9fde586eeecfd03c9c34da1c40f5e513af2d511d4b1961f810df1334cc6e9",
  {
    input: {
      seed: 20,
      image1: "https://replicate.delivery/pbxt/K0Tzk2bsc76SSsRgrJSoh0fnzrB5M0Dqeqe7YHLxf1x7fU4S/FELV-cat.jpg",
      image2: "https://replicate.delivery/pbxt/K0TzkJl3lco0aPVIg8iQYUB0ursK7ZWO0ECEVsxMMQlf5eKH/ironman.jpg",
      prompt: "<i> in the suit of <i>",
      num_images: 1,
      negative_prompt: "",
      num_inference_steps: 50,
      text_guidance_scale: 6
    }
  }
);

// 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.