StableDiffusionWebUI: Mac Installation

Preface

Currently there are several common approaches for AIGC image generation:

SD image generation
Midjourney image generation: https://www.midjourney.com/home
Other large model image generation

Here is a brief comparison across several dimensions:

SD Introduction

There are 3 SD-related projects on GitHub:

https://github.com/CompVis/stable-diffusion

https://github.com/Stability-AI/stablediffusion

https://github.com/AUTOMATIC1111/stable-diffusion-webui

The first one is V1, which is currently the most widely used version.

The second one is V2, which is used less frequently.

The third one is a WebUI for V1 developed by the community.

The first two don’t have a UI interface. Generally, the third one with a WebUI is used.

Mac Installation

Mac installation guide for sd-webui: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon

Install Homebrew

Since sd-webui depends on many third-party packages, it is recommended to install Homebrew for Mac first.

Link: https://brew.sh/

Since Homebrew downloads from overseas servers,

it is recommended to configure a proxy for much faster speeds.

export https_proxy=http://127.0.0.1:7890
export http_proxy=http://127.0.0.1:7890

Install Dependencies

After installing Homebrew, install the sd-webui dependencies:

brew install cmake protobuf rust python@3.10 git wget

Clone the Project

Clone the sd-webui project:

git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui

Download Image Generation Models

Download the desired image generation models to this location:

stable-diffusion-webui/models/Stable-diffusion

Launch WebUI

cd stable-diffusion-webui
./webui.sh

pip Proxy

The startup process requires installing Python dependencies,

which can also be slow. It is recommended to configure a proxy.

export HTTPS_PROXY=http://127.0.0.1:7890
export HTTP_PROXY=http://127.0.0.1:7890

sd-webui

After a long wait, sd-webui has started.

It will automatically open a page.

SDWebUI

|—Link: https://sdwebui.ai/?from=vq

|—Authentic Stable Diffusion WebUI V1.10.1~

|—Top-tier 4090 GPU, premium members get exclusive single 4090 card for image generation~

|—Supports Mac client, Windows client, and Web online usage~

|—Innovative instant model transfer feature, instantly use local models~

|—Supports txt2img, img2img, extras, and PNG info

|—Supports CLIP interrogation and DeepBooru interrogation

|—Supports Hires.fix with 21 built-in upscaling models

|—Supports ADetailer with 11 built-in repair models

|—Supports ControlNet with 44 built-in preprocessors and 68 built-in models

|—Supports super-resolution upscaling (Tiled Diffusion, Demo Fusion, Tiled VAE)

|—Supports old photo restoration with 21 built-in upscaling models, plus GFPGAN and CodeFormer restoration models

|—Built-in 2 common Styles, 11 popular Checkpoint models, 7 popular LoRA models, 14 common embeddings

|—Built-in oldsix prompt plugin

|—Built-in 23-lesson beginner tutorial