kyrick/prompt-parrot – Run with an API on Replicate

kyrick / prompt-parrot

Prompt Parrot generates text2image prompts from finetuned distilgpt2

Cold

Public
251.9K runs
T4
GitHub
License

Run with an API

Playground API Examples README Versions

Input

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

npx create-replicate --model=kyrick/prompt-parrot

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 kyrick/prompt-parrot using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "kyrick/prompt-parrot:7349c6ce7eb83fc9bc2e98e505a55ee28d7a8f4aa5fb6f711fad18724b4f2389",
  {
    input: {
      prompt: "a majestic tower in a field of flowers landscape by"
    }
  }
);
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

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 kyrick/prompt-parrot using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "kyrick/prompt-parrot:7349c6ce7eb83fc9bc2e98e505a55ee28d7a8f4aa5fb6f711fad18724b4f2389",
    input={
        "prompt": "a majestic tower in a field of flowers landscape by"
    }
)
print(output)

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 kyrick/prompt-parrot 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": "7349c6ce7eb83fc9bc2e98e505a55ee28d7a8f4aa5fb6f711fad18724b4f2389",
    "input": {
      "prompt": "a majestic tower in a field of flowers landscape by"
    }
  }' \
  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/kyrick/prompt-parrot@sha256:7349c6ce7eb83fc9bc2e98e505a55ee28d7a8f4aa5fb6f711fad18724b4f2389 \
  -i 'prompt="a majestic tower in a field of flowers landscape by"'

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/kyrick/prompt-parrot@sha256:7349c6ce7eb83fc9bc2e98e505a55ee28d7a8f4aa5fb6f711fad18724b4f2389
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "prompt": "a majestic tower in a field of flowers landscape by"
    }
  }' \
  http://localhost:5000/predictions

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

Output

a majestic tower in a field of flowers landscape by Tooth Wu, wlop, beeple, dan hillier, rossdraws, artstation, octane render rendered 8k highly detailed, cinematic, hyper realistic, hyper ------------------------------------------ a majestic tower in a field of flowers landscape by Yoshitaka Amano, Trending artstation pixiv fanbox, cinematic lighting 2 3 4 cinematic lighting, ArtstationHD, high quality render 4 d, ------------------------------------------ a majestic tower in a field of flowers landscape by luis royo, artstation, beautiful, cinematic lighting, highly detailed, concept art - n 4, by frank frazetta and zdzisław be ------------------------------------------ a majestic tower in a field of flowers landscape by boris vallejo, hyperdetailed, digital art, wallpaper, trending on artstation, cinematic composition, dramatic lighting, hyper detailed, 8 k, masterpiece, trending on artstation, ------------------------------------------ a majestic tower in a field of flowers landscape by edwin longben, craig mullins, j. c. leyendecker, artgerm, fantasy, cosmic horror, dramatic lighting 4 k 8 k 4 k

{
  "completed_at": "2022-10-02T18:38:29.055789Z",
  "created_at": "2022-10-02T18:38:26.397893Z",
  "data_removed": false,
  "error": null,
  "id": "2qhcwcnbqrgedefcldhg2dquei",
  "input": {
    "prompt": "a majestic tower in a field of flowers landscape by"
  },
  "logs": "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n\t- Avoid using `tokenizers` before the fork if possible\n\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n\t- Avoid using `tokenizers` before the fork if possible\n\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)",
  "metrics": {
    "predict_time": 2.488947,
    "total_time": 2.657896
  },
  "output": "a majestic tower in a field of flowers landscape by Tooth Wu, wlop, beeple, dan hillier, rossdraws, artstation, octane render rendered 8k highly detailed, cinematic, hyper realistic, hyper\n------------------------------------------\na majestic tower in a field of flowers landscape by Yoshitaka Amano, Trending artstation pixiv fanbox, cinematic lighting 2 3 4 cinematic lighting, ArtstationHD, high quality render 4 d,\n------------------------------------------\na majestic tower in a field of flowers landscape by luis royo, artstation, beautiful, cinematic lighting, highly detailed, concept art - n 4, by frank frazetta and zdzisław be\n------------------------------------------\na majestic tower in a field of flowers landscape by boris vallejo, hyperdetailed, digital art, wallpaper, trending on artstation, cinematic composition, dramatic lighting, hyper detailed, 8 k, masterpiece, trending on artstation,\n------------------------------------------\na majestic tower in a field of flowers landscape by edwin longben, craig mullins, j. c. leyendecker, artgerm, fantasy, cosmic horror, dramatic lighting 4 k 8 k 4 k",
  "started_at": "2022-10-02T18:38:26.566842Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/2qhcwcnbqrgedefcldhg2dquei",
    "cancel": "https://api.replicate.com/v1/predictions/2qhcwcnbqrgedefcldhg2dquei/cancel"
  },
  "version": "9306ebde7ad6b748552548a4962eccbf037643d31d35e914283c4baca4c3b597"
}

Generated in

2.5 seconds

Tweak it Report

This example was created by a different version, kyrick/prompt-parrot:9306ebde.

Run time and cost

This model costs approximately $0.027 to run on Replicate, or 37 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 T4 GPU hardware. Predictions typically complete within 122 seconds. The predict time for this model varies significantly based on the inputs.

Readme

How to use:

Prompt Parrot generates text2image prompts for use with Stable Diffusion, Midjourney, etc. To use it, simply provide a subject and prompt parrot will spit out stylized text promtps for you to try! For example try input: “a majestic horse in a field” and see what the Parrot comes up with!

What is is:

The model is distilgpt2 fine-tuned on a corpus of 51,747 community provided text prompts. The model generates prompts for text2image prompt generators.