charlesmccarthy/blend-images | Run with an API on Replicate

charlesmccarthy

blend-images

High quality image blending using Kandinsky 2.2 blending pipeline brought to you by your best friends at FullJourney.AI :)

Public

78.5K runs

L40S

Run with an API

Pricing

Playground API Examples README Versions

Input

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

npx create-replicate --model=charlesmccarthy/blend-images

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";
import fs from "node:fs";

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

Run charlesmccarthy/blend-images using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "charlesmccarthy/blend-images:1ed8aaaa04fa84f0c1191679e765d209b94866f6503038416dcbcb340fede892",
  {
    input: {
      image1: "https://replicate.delivery/pbxt/JYUwgFNQbajoEQxvkJIPjDfIpE5Pj51iSfeU8CaYe1896Hyk/generatedimg_4_43531b30-b813-4226-9d5a-a80b5a29f613_1695126618.png",
      image2: "https://replicate.delivery/pbxt/JYUwgCRwYFmMbVAK0RmU5ftY6zg86x6zjTrLG9Bq3abzB6Mw/generatedimg_2_466bb97d-67eb-406a-8a20-2aeb975ea45c_1695134551.png",
      prompt: "A deer shaped clock"
    }
  }
);

// 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.

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 charlesmccarthy/blend-images using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "charlesmccarthy/blend-images:1ed8aaaa04fa84f0c1191679e765d209b94866f6503038416dcbcb340fede892",
    input={
        "image1": "https://replicate.delivery/pbxt/JYUwgFNQbajoEQxvkJIPjDfIpE5Pj51iSfeU8CaYe1896Hyk/generatedimg_4_43531b30-b813-4226-9d5a-a80b5a29f613_1695126618.png",
        "image2": "https://replicate.delivery/pbxt/JYUwgCRwYFmMbVAK0RmU5ftY6zg86x6zjTrLG9Bq3abzB6Mw/generatedimg_2_466bb97d-67eb-406a-8a20-2aeb975ea45c_1695134551.png",
        "prompt": "A deer shaped clock"
    }
)

# 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.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run charlesmccarthy/blend-images 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": "charlesmccarthy/blend-images:1ed8aaaa04fa84f0c1191679e765d209b94866f6503038416dcbcb340fede892",
    "input": {
      "image1": "https://replicate.delivery/pbxt/JYUwgFNQbajoEQxvkJIPjDfIpE5Pj51iSfeU8CaYe1896Hyk/generatedimg_4_43531b30-b813-4226-9d5a-a80b5a29f613_1695126618.png",
      "image2": "https://replicate.delivery/pbxt/JYUwgCRwYFmMbVAK0RmU5ftY6zg86x6zjTrLG9Bq3abzB6Mw/generatedimg_2_466bb97d-67eb-406a-8a20-2aeb975ea45c_1695134551.png",
      "prompt": "A deer shaped clock"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-09-19T14:47:18.855162Z",
  "created_at": "2023-09-19T14:44:58.838855Z",
  "data_removed": false,
  "error": null,
  "id": "y6fgly3be4x5erx5sxj2ekhwxa",
  "input": {
    "image1": "https://replicate.delivery/pbxt/JYUwgFNQbajoEQxvkJIPjDfIpE5Pj51iSfeU8CaYe1896Hyk/generatedimg_4_43531b30-b813-4226-9d5a-a80b5a29f613_1695126618.png",
    "image2": "https://replicate.delivery/pbxt/JYUwgCRwYFmMbVAK0RmU5ftY6zg86x6zjTrLG9Bq3abzB6Mw/generatedimg_2_466bb97d-67eb-406a-8a20-2aeb975ea45c_1695134551.png",
    "prompt": "A deer shaped clock"
  },
  "logs": "0%|          | 0/25 [00:00<?, ?it/s]\n 32%|███▏      | 8/25 [00:00<00:00, 74.16it/s]\n 64%|██████▍   | 16/25 [00:00<00:00, 76.68it/s]\n 96%|█████████▌| 24/25 [00:00<00:00, 77.78it/s]\n100%|██████████| 25/25 [00:00<00:00, 77.27it/s]\n  0%|          | 0/25 [00:00<?, ?it/s]\n 32%|███▏      | 8/25 [00:00<00:00, 78.77it/s]\n 64%|██████▍   | 16/25 [00:00<00:00, 76.97it/s]\n 96%|█████████▌| 24/25 [00:00<00:00, 76.73it/s]\n100%|██████████| 25/25 [00:00<00:00, 77.01it/s]\n  0%|          | 0/100 [00:00<?, ?it/s]\n  1%|          | 1/100 [00:00<00:12,  7.84it/s]\n  2%|▏         | 2/100 [00:00<00:12,  7.79it/s]\n  3%|▎         | 3/100 [00:00<00:12,  7.77it/s]\n  4%|▍         | 4/100 [00:00<00:12,  7.76it/s]\n  5%|▌         | 5/100 [00:00<00:12,  7.77it/s]\n  6%|▌         | 6/100 [00:00<00:12,  7.78it/s]\n  7%|▋         | 7/100 [00:00<00:11,  7.77it/s]\n  8%|▊         | 8/100 [00:01<00:11,  7.77it/s]\n  9%|▉         | 9/100 [00:01<00:11,  7.76it/s]\n 10%|█         | 10/100 [00:01<00:11,  7.76it/s]\n 11%|█         | 11/100 [00:01<00:11,  7.76it/s]\n 12%|█▏        | 12/100 [00:01<00:11,  7.76it/s]\n 13%|█▎        | 13/100 [00:01<00:11,  7.75it/s]\n 14%|█▍        | 14/100 [00:01<00:11,  7.75it/s]\n 15%|█▌        | 15/100 [00:01<00:10,  7.75it/s]\n 16%|█▌        | 16/100 [00:02<00:10,  7.76it/s]\n 17%|█▋        | 17/100 [00:02<00:10,  7.76it/s]\n 18%|█▊        | 18/100 [00:02<00:10,  7.75it/s]\n 19%|█▉        | 19/100 [00:02<00:10,  7.75it/s]\n 20%|██        | 20/100 [00:02<00:10,  7.75it/s]\n 21%|██        | 21/100 [00:02<00:10,  7.76it/s]\n 22%|██▏       | 22/100 [00:02<00:10,  7.75it/s]\n 23%|██▎       | 23/100 [00:02<00:09,  7.75it/s]\n 24%|██▍       | 24/100 [00:03<00:09,  7.76it/s]\n 25%|██▌       | 25/100 [00:03<00:09,  7.76it/s]\n 26%|██▌       | 26/100 [00:03<00:09,  7.76it/s]\n 27%|██▋       | 27/100 [00:03<00:09,  7.76it/s]\n 28%|██▊       | 28/100 [00:03<00:09,  7.75it/s]\n 29%|██▉       | 29/100 [00:03<00:09,  7.75it/s]\n 30%|███       | 30/100 [00:03<00:09,  7.75it/s]\n 31%|███       | 31/100 [00:03<00:08,  7.74it/s]\n 32%|███▏      | 32/100 [00:04<00:08,  7.74it/s]\n 33%|███▎      | 33/100 [00:04<00:08,  7.74it/s]\n 34%|███▍      | 34/100 [00:04<00:08,  7.75it/s]\n 35%|███▌      | 35/100 [00:04<00:08,  7.75it/s]\n 36%|███▌      | 36/100 [00:04<00:08,  7.75it/s]\n 37%|███▋      | 37/100 [00:04<00:08,  7.75it/s]\n 38%|███▊      | 38/100 [00:04<00:08,  7.75it/s]\n 39%|███▉      | 39/100 [00:05<00:07,  7.75it/s]\n 40%|████      | 40/100 [00:05<00:07,  7.75it/s]\n 41%|████      | 41/100 [00:05<00:07,  7.75it/s]\n 42%|████▏     | 42/100 [00:05<00:07,  7.74it/s]\n 43%|████▎     | 43/100 [00:05<00:07,  7.73it/s]\n 44%|████▍     | 44/100 [00:05<00:07,  7.73it/s]\n 45%|████▌     | 45/100 [00:05<00:07,  7.73it/s]\n 46%|████▌     | 46/100 [00:05<00:06,  7.73it/s]\n 47%|████▋     | 47/100 [00:06<00:06,  7.74it/s]\n 48%|████▊     | 48/100 [00:06<00:06,  7.74it/s]\n 49%|████▉     | 49/100 [00:06<00:06,  7.74it/s]\n 50%|█████     | 50/100 [00:06<00:06,  7.75it/s]\n 51%|█████     | 51/100 [00:06<00:06,  7.75it/s]\n 52%|█████▏    | 52/100 [00:06<00:06,  7.75it/s]\n 53%|█████▎    | 53/100 [00:06<00:06,  7.74it/s]\n 54%|█████▍    | 54/100 [00:06<00:05,  7.74it/s]\n 55%|█████▌    | 55/100 [00:07<00:05,  7.74it/s]\n 56%|█████▌    | 56/100 [00:07<00:05,  7.74it/s]\n 57%|█████▋    | 57/100 [00:07<00:05,  7.74it/s]\n 58%|█████▊    | 58/100 [00:07<00:05,  7.74it/s]\n 59%|█████▉    | 59/100 [00:07<00:05,  7.74it/s]\n 60%|██████    | 60/100 [00:07<00:05,  7.74it/s]\n 61%|██████    | 61/100 [00:07<00:05,  7.74it/s]\n 62%|██████▏   | 62/100 [00:08<00:04,  7.74it/s]\n 63%|██████▎   | 63/100 [00:08<00:04,  7.74it/s]\n 64%|██████▍   | 64/100 [00:08<00:04,  7.74it/s]\n 65%|██████▌   | 65/100 [00:08<00:04,  7.74it/s]\n 66%|██████▌   | 66/100 [00:08<00:04,  7.74it/s]\n 67%|██████▋   | 67/100 [00:08<00:04,  7.74it/s]\n 68%|██████▊   | 68/100 [00:08<00:04,  7.73it/s]\n 69%|██████▉   | 69/100 [00:08<00:04,  7.72it/s]\n 70%|███████   | 70/100 [00:09<00:03,  7.72it/s]\n 71%|███████   | 71/100 [00:09<00:03,  7.73it/s]\n 72%|███████▏  | 72/100 [00:09<00:03,  7.72it/s]\n 73%|███████▎  | 73/100 [00:09<00:03,  7.72it/s]\n 74%|███████▍  | 74/100 [00:09<00:03,  7.72it/s]\n 75%|███████▌  | 75/100 [00:09<00:03,  7.72it/s]\n 76%|███████▌  | 76/100 [00:09<00:03,  7.73it/s]\n 77%|███████▋  | 77/100 [00:09<00:02,  7.74it/s]\n 78%|███████▊  | 78/100 [00:10<00:02,  7.73it/s]\n 79%|███████▉  | 79/100 [00:10<00:02,  7.74it/s]\n 80%|████████  | 80/100 [00:10<00:02,  7.74it/s]\n 81%|████████  | 81/100 [00:10<00:02,  7.73it/s]\n 82%|████████▏ | 82/100 [00:10<00:02,  7.73it/s]\n 83%|████████▎ | 83/100 [00:10<00:02,  7.73it/s]\n 84%|████████▍ | 84/100 [00:10<00:02,  7.73it/s]\n 85%|████████▌ | 85/100 [00:10<00:01,  7.73it/s]\n 86%|████████▌ | 86/100 [00:11<00:01,  7.72it/s]\n 87%|████████▋ | 87/100 [00:11<00:01,  7.71it/s]\n 88%|████████▊ | 88/100 [00:11<00:01,  7.72it/s]\n 89%|████████▉ | 89/100 [00:11<00:01,  7.72it/s]\n 90%|█████████ | 90/100 [00:11<00:01,  7.72it/s]\n 91%|█████████ | 91/100 [00:11<00:01,  7.73it/s]\n 92%|█████████▏| 92/100 [00:11<00:01,  7.73it/s]\n 93%|█████████▎| 93/100 [00:12<00:00,  7.73it/s]\n 94%|█████████▍| 94/100 [00:12<00:00,  7.74it/s]\n 95%|█████████▌| 95/100 [00:12<00:00,  7.74it/s]\n 96%|█████████▌| 96/100 [00:12<00:00,  7.73it/s]\n 97%|█████████▋| 97/100 [00:12<00:00,  7.74it/s]\n 98%|█████████▊| 98/100 [00:12<00:00,  7.74it/s]\n 99%|█████████▉| 99/100 [00:12<00:00,  7.73it/s]\n100%|██████████| 100/100 [00:12<00:00,  7.73it/s]\n100%|██████████| 100/100 [00:12<00:00,  7.74it/s]",
  "metrics": {
    "predict_time": 17.637254,
    "total_time": 140.016307
  },
  "output": "https://pbxt.replicate.delivery/jWpveeiis2oXLE4cmnTu5l2SpfKGdbqKBbLAHgBDFykqzsLjA/output.png",
  "started_at": "2023-09-19T14:47:01.217908Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/y6fgly3be4x5erx5sxj2ekhwxa",
    "cancel": "https://api.replicate.com/v1/predictions/y6fgly3be4x5erx5sxj2ekhwxa/cancel"
  },
  "version": "1ed8aaaa04fa84f0c1191679e765d209b94866f6503038416dcbcb340fede892"
}

Generated in

17.6 seconds

Tweak it Iterate in playground Report View full prediction

0%|          | 0/25 [00:00<?, ?it/s]
 32%|███▏      | 8/25 [00:00<00:00, 74.16it/s]
 64%|██████▍   | 16/25 [00:00<00:00, 76.68it/s]
 96%|█████████▌| 24/25 [00:00<00:00, 77.78it/s]
100%|██████████| 25/25 [00:00<00:00, 77.27it/s]
  0%|          | 0/25 [00:00<?, ?it/s]
 32%|███▏      | 8/25 [00:00<00:00, 78.77it/s]
 64%|██████▍   | 16/25 [00:00<00:00, 76.97it/s]
 96%|█████████▌| 24/25 [00:00<00:00, 76.73it/s]
100%|██████████| 25/25 [00:00<00:00, 77.01it/s]
  0%|          | 0/100 [00:00<?, ?it/s]
  1%|          | 1/100 [00:00<00:12,  7.84it/s]
  2%|▏         | 2/100 [00:00<00:12,  7.79it/s]
  3%|▎         | 3/100 [00:00<00:12,  7.77it/s]
  4%|▍         | 4/100 [00:00<00:12,  7.76it/s]
  5%|▌         | 5/100 [00:00<00:12,  7.77it/s]
  6%|▌         | 6/100 [00:00<00:12,  7.78it/s]
  7%|▋         | 7/100 [00:00<00:11,  7.77it/s]
  8%|▊         | 8/100 [00:01<00:11,  7.77it/s]
  9%|▉         | 9/100 [00:01<00:11,  7.76it/s]
 10%|█         | 10/100 [00:01<00:11,  7.76it/s]
 11%|█         | 11/100 [00:01<00:11,  7.76it/s]
 12%|█▏        | 12/100 [00:01<00:11,  7.76it/s]
 13%|█▎        | 13/100 [00:01<00:11,  7.75it/s]
 14%|█▍        | 14/100 [00:01<00:11,  7.75it/s]
 15%|█▌        | 15/100 [00:01<00:10,  7.75it/s]
 16%|█▌        | 16/100 [00:02<00:10,  7.76it/s]
 17%|█▋        | 17/100 [00:02<00:10,  7.76it/s]
 18%|█▊        | 18/100 [00:02<00:10,  7.75it/s]
 19%|█▉        | 19/100 [00:02<00:10,  7.75it/s]
 20%|██        | 20/100 [00:02<00:10,  7.75it/s]
 21%|██        | 21/100 [00:02<00:10,  7.76it/s]
 22%|██▏       | 22/100 [00:02<00:10,  7.75it/s]
 23%|██▎       | 23/100 [00:02<00:09,  7.75it/s]
 24%|██▍       | 24/100 [00:03<00:09,  7.76it/s]
 25%|██▌       | 25/100 [00:03<00:09,  7.76it/s]
 26%|██▌       | 26/100 [00:03<00:09,  7.76it/s]
 27%|██▋       | 27/100 [00:03<00:09,  7.76it/s]
 28%|██▊       | 28/100 [00:03<00:09,  7.75it/s]
 29%|██▉       | 29/100 [00:03<00:09,  7.75it/s]
 30%|███       | 30/100 [00:03<00:09,  7.75it/s]
 31%|███       | 31/100 [00:03<00:08,  7.74it/s]
 32%|███▏      | 32/100 [00:04<00:08,  7.74it/s]
 33%|███▎      | 33/100 [00:04<00:08,  7.74it/s]
 34%|███▍      | 34/100 [00:04<00:08,  7.75it/s]
 35%|███▌      | 35/100 [00:04<00:08,  7.75it/s]
 36%|███▌      | 36/100 [00:04<00:08,  7.75it/s]
 37%|███▋      | 37/100 [00:04<00:08,  7.75it/s]
 38%|███▊      | 38/100 [00:04<00:08,  7.75it/s]
 39%|███▉      | 39/100 [00:05<00:07,  7.75it/s]
 40%|████      | 40/100 [00:05<00:07,  7.75it/s]
 41%|████      | 41/100 [00:05<00:07,  7.75it/s]
 42%|████▏     | 42/100 [00:05<00:07,  7.74it/s]
 43%|████▎     | 43/100 [00:05<00:07,  7.73it/s]
 44%|████▍     | 44/100 [00:05<00:07,  7.73it/s]
 45%|████▌     | 45/100 [00:05<00:07,  7.73it/s]
 46%|████▌     | 46/100 [00:05<00:06,  7.73it/s]
 47%|████▋     | 47/100 [00:06<00:06,  7.74it/s]
 48%|████▊     | 48/100 [00:06<00:06,  7.74it/s]
 49%|████▉     | 49/100 [00:06<00:06,  7.74it/s]
 50%|█████     | 50/100 [00:06<00:06,  7.75it/s]
 51%|█████     | 51/100 [00:06<00:06,  7.75it/s]
 52%|█████▏    | 52/100 [00:06<00:06,  7.75it/s]
 53%|█████▎    | 53/100 [00:06<00:06,  7.74it/s]
 54%|█████▍    | 54/100 [00:06<00:05,  7.74it/s]
 55%|█████▌    | 55/100 [00:07<00:05,  7.74it/s]
 56%|█████▌    | 56/100 [00:07<00:05,  7.74it/s]
 57%|█████▋    | 57/100 [00:07<00:05,  7.74it/s]
 58%|█████▊    | 58/100 [00:07<00:05,  7.74it/s]
 59%|█████▉    | 59/100 [00:07<00:05,  7.74it/s]
 60%|██████    | 60/100 [00:07<00:05,  7.74it/s]
 61%|██████    | 61/100 [00:07<00:05,  7.74it/s]
 62%|██████▏   | 62/100 [00:08<00:04,  7.74it/s]
 63%|██████▎   | 63/100 [00:08<00:04,  7.74it/s]
 64%|██████▍   | 64/100 [00:08<00:04,  7.74it/s]
 65%|██████▌   | 65/100 [00:08<00:04,  7.74it/s]
 66%|██████▌   | 66/100 [00:08<00:04,  7.74it/s]
 67%|██████▋   | 67/100 [00:08<00:04,  7.74it/s]
 68%|██████▊   | 68/100 [00:08<00:04,  7.73it/s]
 69%|██████▉   | 69/100 [00:08<00:04,  7.72it/s]
 70%|███████   | 70/100 [00:09<00:03,  7.72it/s]
 71%|███████   | 71/100 [00:09<00:03,  7.73it/s]
 72%|███████▏  | 72/100 [00:09<00:03,  7.72it/s]
 73%|███████▎  | 73/100 [00:09<00:03,  7.72it/s]
 74%|███████▍  | 74/100 [00:09<00:03,  7.72it/s]
 75%|███████▌  | 75/100 [00:09<00:03,  7.72it/s]
 76%|███████▌  | 76/100 [00:09<00:03,  7.73it/s]
 77%|███████▋  | 77/100 [00:09<00:02,  7.74it/s]
 78%|███████▊  | 78/100 [00:10<00:02,  7.73it/s]
 79%|███████▉  | 79/100 [00:10<00:02,  7.74it/s]
 80%|████████  | 80/100 [00:10<00:02,  7.74it/s]
 81%|████████  | 81/100 [00:10<00:02,  7.73it/s]
 82%|████████▏ | 82/100 [00:10<00:02,  7.73it/s]
 83%|████████▎ | 83/100 [00:10<00:02,  7.73it/s]
 84%|████████▍ | 84/100 [00:10<00:02,  7.73it/s]
 85%|████████▌ | 85/100 [00:10<00:01,  7.73it/s]
 86%|████████▌ | 86/100 [00:11<00:01,  7.72it/s]
 87%|████████▋ | 87/100 [00:11<00:01,  7.71it/s]
 88%|████████▊ | 88/100 [00:11<00:01,  7.72it/s]
 89%|████████▉ | 89/100 [00:11<00:01,  7.72it/s]
 90%|█████████ | 90/100 [00:11<00:01,  7.72it/s]
 91%|█████████ | 91/100 [00:11<00:01,  7.73it/s]
 92%|█████████▏| 92/100 [00:11<00:01,  7.73it/s]
 93%|█████████▎| 93/100 [00:12<00:00,  7.73it/s]
 94%|█████████▍| 94/100 [00:12<00:00,  7.74it/s]
 95%|█████████▌| 95/100 [00:12<00:00,  7.74it/s]
 96%|█████████▌| 96/100 [00:12<00:00,  7.73it/s]
 97%|█████████▋| 97/100 [00:12<00:00,  7.74it/s]
 98%|█████████▊| 98/100 [00:12<00:00,  7.74it/s]
 99%|█████████▉| 99/100 [00:12<00:00,  7.73it/s]
100%|██████████| 100/100 [00:12<00:00,  7.73it/s]
100%|██████████| 100/100 [00:12<00:00,  7.74it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.0085 to run on Replicate, or 117 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 9 seconds. The predict time for this model varies significantly based on the inputs.

Readme

High quality image blending using Kandinsky 2.2 blending pipeline brought to you by FullJourney.AI