adymaharana/story-dalle:cc2302dc – Run with an API on Replicate

Version

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

adymaharana /story-dalle:cc2302dc

Playground API

Input

caption_1

*string

Shift + Return to add a new line

First scene in your story

caption_2

*string

Shift + Return to add a new line

Second scene in your story

caption_3

*string

Shift + Return to add a new line

Third scene in your story

caption_4

*string

Shift + Return to add a new line

Final scene in your story

source

string

The main character of your story

Default: "Pororo"

top_k

integer

the number of highest probability vocabulary tokens to keep for top-k-filtering

Default: 32

top_p

number

Only the most probable tokens with probabilities that add up to `top_p` or higher are kept for generation

Default: 0.2

n_candidates

integer

(minimum: 1, maximum: 4)

Num candidates to generate for each story panel

Default: 4

supercondition

boolean

Set `supercondition` to True to enable generation using a null hypothesis.

Default: false

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

npx create-replicate --model=adymaharana/story-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 adymaharana/story-dalle using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adymaharana/story-dalle:cc2302dcd0d7b7d0fbfafecdb1a3cab31af40aa85d3d59d0b8767baaceecc4c0",
  {
    input: {
      top_k: 32,
      top_p: 0.2,
      source: "Pororo",
      n_candidates: 4,
      supercondition: false
    }
  }
);
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 adymaharana/story-dalle using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adymaharana/story-dalle:cc2302dcd0d7b7d0fbfafecdb1a3cab31af40aa85d3d59d0b8767baaceecc4c0",
    input={
        "top_k": 32,
        "top_p": 0.2,
        "source": "Pororo",
        "n_candidates": 4,
        "supercondition": False
    }
)
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 adymaharana/story-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": "cc2302dcd0d7b7d0fbfafecdb1a3cab31af40aa85d3d59d0b8767baaceecc4c0",
    "input": {
      "top_k": 32,
      "top_p": 0.2,
      "source": "Pororo",
      "n_candidates": 4,
      "supercondition": false
    }
  }' \
  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/daanelson/story-dalle@sha256:cc2302dcd0d7b7d0fbfafecdb1a3cab31af40aa85d3d59d0b8767baaceecc4c0 \
  -i 'top_k=32' \
  -i 'top_p=0.2' \
  -i 'source="Pororo"' \
  -i 'n_candidates=4' \
  -i 'supercondition=false'

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/daanelson/story-dalle@sha256:cc2302dcd0d7b7d0fbfafecdb1a3cab31af40aa85d3d59d0b8767baaceecc4c0
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "top_k": 32,
      "top_p": 0.2,
      "source": "Pororo",
      "n_candidates": 4,
      "supercondition": false
    }
  }' \
  http://localhost:5000/predictions

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

Output

No output yet! Press "Submit" to start a prediction.