kuprel/min-dalle:ee5b034a – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

kuprel /min-dalle:ee5b034a

Playground API

Input

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

npx create-replicate --model=kuprel/min-dalle

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";

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

Run kuprel/min-dalle using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "kuprel/min-dalle:ee5b034a2b9525bc32f84ea885ef98b4a7847264f9453aa01de58994018234e0",
  {
    input: {
      text: "A vintage photo of a capybara wearing a tuxedo and top hat, black and white",
      top_k: 16384,
      grid_size: 5,
      save_as_png: false,
      temperature: "4",
      progressive_outputs: true,
      supercondition_factor: 64
    }
  }
);

// 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.

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 kuprel/min-dalle using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "kuprel/min-dalle:ee5b034a2b9525bc32f84ea885ef98b4a7847264f9453aa01de58994018234e0",
    input={
        "text": "A vintage photo of a capybara wearing a tuxedo and top hat, black and white",
        "top_k": 16384,
        "grid_size": 5,
        "save_as_png": False,
        "temperature": "4",
        "progressive_outputs": True,
        "supercondition_factor": 64
    }
)

# The kuprel/min-dalle 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/kuprel/min-dalle/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=<paste-your-token-here>

Find your API token in your account settings.

Run kuprel/min-dalle 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": "kuprel/min-dalle:ee5b034a2b9525bc32f84ea885ef98b4a7847264f9453aa01de58994018234e0",
    "input": {
      "text": "A vintage photo of a capybara wearing a tuxedo and top hat, black and white",
      "top_k": 16384,
      "grid_size": 5,
      "save_as_png": false,
      "temperature": "4",
      "progressive_outputs": true,
      "supercondition_factor": 64
    }
  }' \
  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/kuprel/min-dalle@sha256:ee5b034a2b9525bc32f84ea885ef98b4a7847264f9453aa01de58994018234e0 \
  -i 'text="A vintage photo of a capybara wearing a tuxedo and top hat, black and white"' \
  -i 'top_k=16384' \
  -i 'grid_size=5' \
  -i 'save_as_png=false' \
  -i 'temperature="4"' \
  -i 'progressive_outputs=true' \
  -i 'supercondition_factor=64'

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/kuprel/min-dalle@sha256:ee5b034a2b9525bc32f84ea885ef98b4a7847264f9453aa01de58994018234e0
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "text": "A vintage photo of a capybara wearing a tuxedo and top hat, black and white",
      "top_k": 16384,
      "grid_size": 5,
      "save_as_png": false,
      "temperature": "4",
      "progressive_outputs": true,
      "supercondition_factor": 64
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2022-07-15T13:25:24.592470Z",
  "created_at": "2022-07-15T13:25:07.052163Z",
  "data_removed": false,
  "error": null,
  "id": "e5ebn5qa5fhvbl5an2ner4fylq",
  "input": {
    "text": "A vintage photo of a capybara wearing a tuxedo and top hat, black and white",
    "top_k": "16384",
    "grid_size": "5",
    "temperature": "4",
    "progressive_outputs": true,
    "supercondition_factor": "64"
  },
  "logs": "tokenizing text\n['Ġa']\n['Ġvintage']\n['Ġphoto']\n['Ġof']\n['Ġa']\n['Ġcap', 'yb', 'ara']\n['Ġwearing']\n['Ġa']\n['Ġtuxedo']\n['Ġand']\n['Ġtop']\n['Ġhat', ',']\n['Ġblack']\n['Ġand']\n['Ġwhite']\n20 text tokens [0, 58, 996, 564, 111, 58, 712, 21854, 761, 8995, 58, 26047, 128, 479, 2583, 11, 486, 128, 657, 2]\nencoding text tokens\nsampling row 1 of 16\nsampling row 2 of 16\ndetokenizing image\nsampling row 3 of 16\nsampling row 4 of 16\ndetokenizing image\nsampling row 5 of 16\nsampling row 6 of 16\ndetokenizing image\nsampling row 7 of 16\nsampling row 8 of 16\ndetokenizing image\nsampling row 9 of 16\nsampling row 10 of 16\ndetokenizing image\nsampling row 11 of 16\nsampling row 12 of 16\ndetokenizing image\nsampling row 13 of 16\nsampling row 14 of 16\ndetokenizing image\nsampling row 15 of 16\nsampling row 16 of 16\ndetokenizing image",
  "metrics": {
    "predict_time": 16.350287,
    "total_time": 17.540307
  },
  "output": [
    "https://replicate.delivery/mgxm/d4b9786a-8f3d-4881-ae7c-a984e3fbc093/min-dalle-iter-1.jpg",
    "https://replicate.delivery/mgxm/fefee167-08e6-4770-b66c-c4866dd3d24c/min-dalle-iter-2.jpg",
    "https://replicate.delivery/mgxm/c08656c4-99c3-4237-9a47-e49687ecd37d/min-dalle-iter-3.jpg",
    "https://replicate.delivery/mgxm/b0c200f5-3947-465a-80d7-7a995b7cdf75/min-dalle-iter-4.jpg",
    "https://replicate.delivery/mgxm/1c136dc6-716d-43b5-aede-f73493fbc511/min-dalle-iter-5.jpg",
    "https://replicate.delivery/mgxm/c4333592-a326-4c50-97b4-aaad9ecee001/min-dalle-iter-6.jpg",
    "https://replicate.delivery/mgxm/35ae8d3f-bfb3-4dbc-9822-884ece2d35bc/min-dalle-iter-7.jpg",
    "https://replicate.delivery/mgxm/957c66ef-dec4-4e6c-bf1e-a693f444a270/min-dalle-iter-8.jpg"
  ],
  "started_at": "2022-07-15T13:25:08.242183Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/e5ebn5qa5fhvbl5an2ner4fylq",
    "cancel": "https://api.replicate.com/v1/predictions/e5ebn5qa5fhvbl5an2ner4fylq/cancel"
  },
  "version": "ee5b034a2b9525bc32f84ea885ef98b4a7847264f9453aa01de58994018234e0"
}

Generated in

16.4 seconds

Tweak itReport