ltejedor/differentiable-rasterizer-vector-graphics:cc9115d7

Version

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

ltejedor /differentiable-rasterizer-vector-graphics:cc9115d7

Playground API

Input

prompt

string

Shift + Return to add a new line

The global prompt for generating the collage.

Default: "a photorealistic chicken"

patch_url

string

Shift + Return to add a new line

https://storage.googleapis.com/dm_arnheim_3_assets/collage_patches/animals.npyhttps://storage.googleapis.com/dm_arnheim_3_assets/collage_patches/animals.npy

An .npy file for the collage patches.

Default: "https://storage.googleapis.com/dm_arnheim_3_assets/collage_patches/animals.npy"

num_patches

integer

Number of images to start with

Default: 100

background_red

integer

Default: 0

background_green

integer

Default: 0

background_blue

integer

Default: 0

initial_positions

List of lists representing the initial positions of patches.

Default: []

initial_transformations

Default: []

initial_colours

Default: []

optim_steps

integer

Number of optimization steps to run during collage generation.

Default: 250

color_space

string

An enumeration.

Default: "RGB space"

loss

string

Loss function to optimize the collage. Choose between CLIP and MSE. If MSE is selected, the prompt won't affect the image and target_image is required.

Default: "CLIP"

target_image

file

Upload an image file for MSE loss. Required if loss is set to MSE.

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

npx create-replicate --model=ltejedor/differentiable-rasterizer-vector-graphics

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 ltejedor/differentiable-rasterizer-vector-graphics using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "ltejedor/differentiable-rasterizer-vector-graphics:cc9115d780532c82f9cafaea7256989c70a6a664cd98f481565ab13b280e8b37",
  {
    input: {
      loss: "CLIP",
      prompt: "a photorealistic chicken",
      patch_url: "https://storage.googleapis.com/dm_arnheim_3_assets/collage_patches/animals.npy",
      color_space: "RGB space",
      num_patches: 100,
      optim_steps: 250,
      background_red: 0,
      background_blue: 0,
      initial_colours: [],
      background_green: 0,
      initial_positions: [],
      initial_transformations: []
    }
  }
);
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 ltejedor/differentiable-rasterizer-vector-graphics using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "ltejedor/differentiable-rasterizer-vector-graphics:cc9115d780532c82f9cafaea7256989c70a6a664cd98f481565ab13b280e8b37",
    input={
        "loss": "CLIP",
        "prompt": "a photorealistic chicken",
        "patch_url": "https://storage.googleapis.com/dm_arnheim_3_assets/collage_patches/animals.npy",
        "color_space": "RGB space",
        "num_patches": 100,
        "optim_steps": 250,
        "background_red": 0,
        "background_blue": 0,
        "initial_colours": [],
        "background_green": 0,
        "initial_positions": [],
        "initial_transformations": []
    }
)
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 ltejedor/differentiable-rasterizer-vector-graphics 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": "cc9115d780532c82f9cafaea7256989c70a6a664cd98f481565ab13b280e8b37",
    "input": {
      "loss": "CLIP",
      "prompt": "a photorealistic chicken",
      "patch_url": "https://storage.googleapis.com/dm_arnheim_3_assets/collage_patches/animals.npy",
      "color_space": "RGB space",
      "num_patches": 100,
      "optim_steps": 250,
      "background_red": 0,
      "background_blue": 0,
      "initial_colours": [],
      "background_green": 0,
      "initial_positions": [],
      "initial_transformations": []
    }
  }' \
  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/ltejedor/differentiable-rasterizer-vector-graphics@sha256:cc9115d780532c82f9cafaea7256989c70a6a664cd98f481565ab13b280e8b37 \
  -i 'loss="CLIP"' \
  -i 'prompt="a photorealistic chicken"' \
  -i 'patch_url="https://storage.googleapis.com/dm_arnheim_3_assets/collage_patches/animals.npy"' \
  -i 'color_space="RGB space"' \
  -i 'num_patches=100' \
  -i 'optim_steps=250' \
  -i 'background_red=0' \
  -i 'background_blue=0' \
  -i 'initial_colours=[]' \
  -i 'background_green=0' \
  -i 'initial_positions=[]' \
  -i 'initial_transformations=[]'

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/ltejedor/differentiable-rasterizer-vector-graphics@sha256:cc9115d780532c82f9cafaea7256989c70a6a664cd98f481565ab13b280e8b37
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "loss": "CLIP",
      "prompt": "a photorealistic chicken",
      "patch_url": "https://storage.googleapis.com/dm_arnheim_3_assets/collage_patches/animals.npy",
      "color_space": "RGB space",
      "num_patches": 100,
      "optim_steps": 250,
      "background_red": 0,
      "background_blue": 0,
      "initial_colours": [],
      "background_green": 0,
      "initial_positions": [],
      "initial_transformations": []
    }
  }' \
  http://localhost:5000/predictions

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

Output

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