npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

stable-diffusion-rest-api

v0.0.4

Published

Run Stable Diffusion locally via a REST API on an M1/M2 MacBook

Downloads

10

Readme

Stable Diffusion REST API npm Version stability experimental build

Run Stable Diffusion locally via a REST API on an M1/M2 MacBook

Pre-requisites

Initial setup

Adapted from Run Stable Diffusion on your M1 Mac’s GPU by Ben Firshman

Update Homebrew and upgrade all existing Homebrew packages:

brew update
brew upgrade

Install Homebrew dependencies:

brew install cmake mkcert protobuf rust

Clone the Stable Diffusion fork:

git clone -b apple-silicon-mps-support https://github.com/bfirsh/stable-diffusion.git

Set up a virtualenv and install dependencies:

cd stable-diffusion
python3 -m pip install virtualenv
python3 -m virtualenv venv
pip install -r requirements.txt
cd ..

Download the text-to-image and inpaint model checkpoints:

mkdir -p models
curl --output models/text-to-image.ckpt https://www.googleapis.com/storage/v1/b/aai-blog-files/o/sd-v1-4.ckpt?alt=media
curl --output models/inpaint-image.ckpt https://ommer-lab.com/files/latent-diffusion/inpainting_big.zip

Generate a HTTPS certificate and key:

mkcert -install
mkcert -cert-file cert.pem -key-file key.pem 0.0.0.0

Usage


  Usage
    $ stable-diffusion-rest-api [options]

  Options
    --cert                   Path to the SSL certicate  (default ./cert.pem)
    --concurrency            Number of concurrent image generation tasks  (default 1)
    --cors                   Whether to enable CORS  (default true)
    --delete-incomplete      Delete all incomplete image generation tasks before starting the server  (default false)
    --inpaint-image-model    Path to the inpaint image model checkpoint  (default ./models/inpaint-image.ckpt)
    --key                    Path to the SSL certicate key  (default ./key.pem)
    --output                 Directory to output generated images  (default ./output)
    --port                   Port to serve the REST API  (default 8888)
    --repository             Path to the Stable Diffusion repository  (default ./stable-diffusion)
    --text-to-image-model    Path to the text-to-image model checkpoint  (default ./models/text-to-image.ckpt)
    -v, --version            Displays current version
    -h, --help               Displays this message

Start the API server:

npx --yes -- stable-diffusion-rest-api \
  --text-to-image-model ./models/text-to-image.ckpt \
  --inpaint-image-model ./models/inpaint-image.ckpt \
  --concurrency 1 \
  --output ./output \
  --cert ./cert.pem \
  --key ./key.pem \
  --port 8888

API response

All REST API endpoints return JSON with one of the following shapes, depending on the status of the image generation task:

{
  status: 'QUEUED'
  resultUrl: string
}
{
  status: 'IN_PROGRESS'
  resultUrl: string
  progress: {
    currentImageIndex: number
    currentImageProgress: number
    totalImages: number
  }
  imageUrls: Array<string>
}
{
  status: 'COMPLETE'
  resultUrl: string
  imageUrls: Array<string>
}
  • status is one of QUEUED, IN_PROGRESS or COMPLETE
  • resultUrl is the URL to access the results of the image generation task
  • progress contains details about the progress of the image generation task:
    • currentImageIndex is the index of the image currently being generated
    • currentImageProgress is a value between 0 and 1 representing the progress of generating the current image
    • totalImages is the total number of images to be generated
  • imageUrls is the list of URLs of the generated images

Text to Image

POST /text-to-image

curl https://0.0.0.0:8888/text-to-image \
  --form prompt="A digital illustration of a beautiful mountain landscape, detailed, thom tenerys, epic composition, 4k, trending on artstation, fantasy vivid colors" \
  --form iterations="3" \
  --form steps="8" \
  --form seed="42" \
  --header "Content-Type: multipart/form-data" \
  --location

Sample response

{
  "status": "QUEUED",
  "resultUrl": "/text-to-image/61f957e4462ea8eff36d9e7a7b650994"
}

GET /text-to-image/<ID>

curl https://0.0.0.0:8888/text-to-image/61f957e4462ea8eff36d9e7a7b650994

Sample response

{
  "status": "IN_PROGRESS",
  "resultUrl": "/text-to-image/61f957e4462ea8eff36d9e7a7b650994",
  "progress": {
    "totalImages": 3,
    "currentImageIndex": 3,
    "currentImageProgress": 0.5
  },
  "imageUrls": [
    "/text-to-image/61f957e4462ea8eff36d9e7a7b650994/1.png",
    "/text-to-image/61f957e4462ea8eff36d9e7a7b650994/2.png"
  ]
}
{
  "status": "COMPLETE",
  "resultUrl": "/text-to-image/61f957e4462ea8eff36d9e7a7b650994",
  "imageUrls": [
    "/text-to-image/61f957e4462ea8eff36d9e7a7b650994/1.png",
    "/text-to-image/61f957e4462ea8eff36d9e7a7b650994/2.png",
    "/text-to-image/61f957e4462ea8eff36d9e7a7b650994/3.png"
  ]
}

Image to Image

POST /image-to-image

curl https://0.0.0.0:8888/image-to-image \
  --form prompt="A digital illustration of a beautiful mountain landscape, detailed, thom tenery, epic composition, 4k, trending on artstation, fantasy vivid colors" \
  --form image=@./image.png \
  --form iterations="3" \
  --form steps="24" \
  --form seed="42" \
  --header "Content-Type: multipart/form-data" \
  --location

Sample response

{
  "status": "QUEUED",
  "resultUrl": "/image-to-image/ab1104f3b55fbab7779cdbdc73ed276e"
}

GET /image-to-image/<ID>

curl https://0.0.0.0:8888/image-to-image/ab1104f3b55fbab7779cdbdc73ed276e

Sample response

{
  "status": "IN_PROGRESS",
  "resultUrl": "/image-to-image/ab1104f3b55fbab7779cdbdc73ed276e",
  "progress": {
    "totalImages": 3,
    "currentImageIndex": 3,
    "currentImageProgress": 0.5
  },
  "imageUrls": [
    "/image-to-image/ab1104f3b55fbab7779cdbdc73ed276e/1.png",
    "/image-to-image/ab1104f3b55fbab7779cdbdc73ed276e/2.png"
  ]
}
{
  "status": "COMPLETE",
  "resultUrl": "/image-to-image/ab1104f3b55fbab7779cdbdc73ed276e",
  "imageUrls": [
    "/image-to-image/ab1104f3b55fbab7779cdbdc73ed276e/1.png",
    "/image-to-image/ab1104f3b55fbab7779cdbdc73ed276e/2.png"
    "/image-to-image/ab1104f3b55fbab7779cdbdc73ed276e/3.png"
  ]
}

Inpaint Image

POST /inpaint-image

curl https://0.0.0.0:8888/inpaint-image \
  --form image=@./image.png \
  --form mask=@./image-mask.png \
  --form steps="32" \
  --form seed="42" \
  --header "Content-Type: multipart/form-data" \
  --location

Sample response

{
  "status": "QUEUED",
  "resultUrl": "/inpaint-image/59a89dfc9f075942ce9afc08312b8296"
}

GET /inpaint-image/<ID>

curl https://0.0.0.0:8888/inpaint-image/59a89dfc9f075942ce9afc08312b8296

Sample response

{
  "status": "IN_PROGRESS",
  "resultUrl": "/inpaint-image/59a89dfc9f075942ce9afc08312b8296",
  "progress": {
    "totalImages": 1,
    "currentImageIndex": 1,
    "currentImageProgress": 0.5
  },
  "imageUrls": []
}
{
  "status": "COMPLETE",
  "resultUrl": "/inpaint-image/59a89dfc9f075942ce9afc08312b8296",
  "imageUrls": [
    "/inpaint-image/59a89dfc9f075942ce9afc08312b8296/1.png",
  ]
}