microsoft/vq-diffusion:81ca56aa | Run with an API on Replicate

Version

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

microsoft /vq-diffusion:81ca56aa

Playground API

Input

generation_type

string

Choose generating images from in-the-wild text, MSCOCO datasets, or ImageNet class label.

Default: "in-the-wild text"

prompt

string

Shift + Return to add a new line

Prompt for generating image. Valid when generation_type is set to in-the-wild text and MSCOCO datasets.

Default: ""

image_class

string

Choose the ImageNet label. Valid when generation_type is set to ImageNet class label.

Default: "None"

num_images

integer

(minimum: 1, maximum: 8)

Number of generated images.

Default: 4

truncation_rate

number

(minimum: 0, maximum: 1)

Sample with truncation.

Default: 0.86

guidance_scale

number

Improved VQ-Diffusion with learnable classifier-free sampling.

Default: 1

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

npx create-replicate --model=microsoft/vq-diffusion

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 microsoft/vq-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "microsoft/vq-diffusion:81ca56aa6c06543cf0398aa5a13102a294abfb8cea8f1aa307a7c1556e638ac9",
  {
    input: {
      prompt: "teddy bear playing in the pool",
      num_images: 4,
      image_class: "None",
      guidance_scale: 5,
      generation_type: "in-the-wild text",
      truncation_rate: 1
    }
  }
);

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 microsoft/vq-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "microsoft/vq-diffusion:81ca56aa6c06543cf0398aa5a13102a294abfb8cea8f1aa307a7c1556e638ac9",
    input={
        "prompt": "teddy bear playing in the pool",
        "num_images": 4,
        "image_class": "None",
        "guidance_scale": 5,
        "generation_type": "in-the-wild text",
        "truncation_rate": 1
    }
)
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 microsoft/vq-diffusion 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": "microsoft/vq-diffusion:81ca56aa6c06543cf0398aa5a13102a294abfb8cea8f1aa307a7c1556e638ac9",
    "input": {
      "prompt": "teddy bear playing in the pool",
      "num_images": 4,
      "image_class": "None",
      "guidance_scale": 5,
      "generation_type": "in-the-wild text",
      "truncation_rate": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

51.1 seconds

Tweak itReport View full prediction