https://github.com/jakiestfu/stability-ts

DreamStudio Client written in TypeScript
https://github.com/jakiestfu/stability-ts

Last synced: 7 days ago
JSON representation

DreamStudio Client written in TypeScript

• Host: GitHub
• URL: https://github.com/jakiestfu/stability-ts
• Owner: jakiestfu
• Created: 2022-08-31T18:50:12.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2022-11-29T08:38:51.000Z (almost 2 years ago)
• Last Synced: 2024-10-31T13:33:47.683Z (14 days ago)
• Language: TypeScript
• Size: 147 KB
• Stars: 158
• Watchers: 12
• Forks: 32
• Open Issues: 8
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Stability TS

A TypeScript client for the Stability AI SDK.

[Requires an API Key for DreamStudio which can be found here.](https://beta.dreamstudio.ai/membership)

## Installation

```sh

# NPM

npm i -g stability-ts

# To Update

npm update -g stability-ts

# Yarn

yarn global add stability-ts

```

## Example

```sh

stability \

  -s 150 \ # Steps

  -c 15 \ # Cfg Scale

  -a k_euler_ancestral \ # Diffusion Method

  -S 3465383516 \ # Seed

  -o ./examples \ # Output Directory

  -n 5 \ # 5 images

  "a anime still of an highly detailed night cyberpunk city life, bladerunner style!! detailed shops, neon lights, ray tracing, advertising everywhere, people and robots walking around. art by satoshi kon and studio ghibli, in the style of ghost in the shell, muted colours, hyperrealism, cinematic lighting, lush detail, award winning, wlop, octane render, trending on artstation" 

```

### Output

||||||

|---|---|---|---|---|

***

## API

```ts

import { generate } from 'stability-ts'

const api = generate({

  prompt: 'A Stunning House',

  apiKey: process.env.DREAMSTUDIO_API_KEY,

})

api.on('image', ({ buffer, filePath }) => {

  console.log('Image', buffer, filePath)

})

api.on('end', (data) => {

  console.log('Generating Complete', data)

})

```

Async/Promise API

```ts

import { generateAsync } from 'stability-ts'

try {

  const { res, images } = await generateAsync({

    prompt: 'A Stunning House',

    apiKey: process.env.DREAMSTUDIO_API_KEY,

  })

  console.log(images)

} catch (e) {

  // ...

}

```

## CLI

```sh

Usage: stability [options] [prompt]

Generate an image

Arguments:

  prompt                           The text prompt you want to use

Options:

  -V, --version                    output the version number

  -H, --height             height of image (default: 512)

  -W, --width               width of image (default: 512)

  -c, --cfg_scale           CFG scale factor (default: 7)

  -a, --sampler           Diffusion Method (choices: "ddim", "plms", "k_euler", "k_euler_ancestral", "k_heun", "k_dpm_2", "k_dpm_2_ancestral", "k_lms", default: "k_lms")

  -s, --steps               number of steps (default: 50)

  -S, --seed                 random seed to use (default: 1614811539)

  -n, --num_samples   number of samples to generate (default: 1)

  -e, --engine             engine to use for inference (default: "stable-diffusion-v1")

  --no-store                       do not write aritfacts to disk

  -k, --api-key           DreamStudio API Key (env: DREAMSTUDIO_API_KEY)

  -o, --output-dir      directory to store images (default: "/Users/jacobkelley/code/stability-ts")

  -d, --debug                      Additional logging

  -h, --help                       display help for command

```

## Developing

```

nvm use

yarn

yarn build

npm link

export DREAMSTUDIO_API_KEY=...

stability "A stunning house"

```