Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update documentation

Browse Source
This commit is contained in:
Armando C. Santisbon 2022-09-09 23:15:09 -05:00
parent 6d2084e030
commit 4185afea5c
1 changed files with 49 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

85
README-Mac-Docker.md
View File

@ -18,6 +18,10 @@ Table of Contents
* [Web Interface](#web-interface) * [Web Interface](#web-interface)
* [Notes](#notes) * [Notes](#notes)
Go to [Hugging Face](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original), and click "Access repository" to Download ```sd-v1-4.ckpt``` (~4 GB) to ```~/Downloads```.
You'll need to create an account but it's quick and free.
# Installation # Installation
## Option 1 - Directly on Apple silicon ## Option 1 - Directly on Apple silicon
@ -33,8 +37,9 @@ conda init zsh && source ~/.zshrc # or bash and .bashrc
``` ```
### Setup ### Setup
Set it to the fork you want to use.
```Shell ```Shell
# Set the fork you want to use.
GITHUB_STABLE_DIFFUSION=https://github.com/santisbon/stable-diffusion.git GITHUB_STABLE_DIFFUSION=https://github.com/santisbon/stable-diffusion.git
git clone $GITHUB_STABLE_DIFFUSION git clone $GITHUB_STABLE_DIFFUSION
@ -42,8 +47,6 @@ cd stable-diffusion
mkdir -p models/ldm/stable-diffusion-v1/ mkdir -p models/ldm/stable-diffusion-v1/
``` ```
Go to [Hugging Face](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original), and click "Access repository" to Download ```sd-v1-4.ckpt``` (~4 GB). You'll need to create an account but it's quick and free. Then set up the environment:
```Shell ```Shell
PATH_TO_CKPT="$HOME/Downloads" # or wherever you saved sd-v1-4.ckpt PATH_TO_CKPT="$HOME/Downloads" # or wherever you saved sd-v1-4.ckpt
ln -s "$PATH_TO_CKPT/sd-v1-4.ckpt" models/ldm/stable-diffusion-v1/model.ckpt ln -s "$PATH_TO_CKPT/sd-v1-4.ckpt" models/ldm/stable-diffusion-v1/model.ckpt
@ -70,10 +73,7 @@ You [can't access the Macbook M1/M2 GPU cores from the Docker containers](https:
### Prerequisites ### Prerequisites
[Install Docker](https://gist.github.com/santisbon/2165fd1c9aaa1f7974f424535d3756f7#install-2) [Install Docker](https://gist.github.com/santisbon/2165fd1c9aaa1f7974f424535d3756f7#install-2)
On the Docker Desktop app, go to Preferences, Resources, Advanced. Adjust the CPUs and Memory to the largest amount available to avoid this [Issue](https://github.com/lstein/stable-diffusion/issues/342). You may need to increase Swap and Disk image size too. On the Docker Desktop app, go to Preferences, Resources, Advanced. Increase the CPUs and Memory to avoid this [Issue](https://github.com/lstein/stable-diffusion/issues/342). You may need to increase Swap and Disk image size too.
Go to [Hugging Face](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original), and click "Access repository" to Download ```sd-v1-4.ckpt``` (~4 GB) to ```~/Downloads```.
You'll need to create an account but it's quick and free.
Create a Docker volume for the downloaded model file Create a Docker volume for the downloaded model file
``` ```
@ -82,38 +82,39 @@ docker volume create my-vol
Populate the volume using a lightweight Linux container. You just need to create the container with the mountpoint; no need to run it. Populate the volume using a lightweight Linux container. You just need to create the container with the mountpoint; no need to run it.
```Shell ```Shell
docker create --name dummy --mount source=my-vol,target=/data alpine docker create --platform linux/arm64 --name dummy --mount source=my-vol,target=/data alpine # or arm64v8/alpine
cd ~/Downloads # or wherever you saved sd-v1-4.ckpt cd ~/Downloads # or wherever you saved sd-v1-4.ckpt
docker cp sd-v1-4.ckpt dummy:/data docker cp sd-v1-4.ckpt dummy:/data
``` ```
### Setup ### Setup
Start a container for Stable Diffusion Start a container for Stable Diffusion. The container's 9090 port is mapped to the host's 80. That way you'll be able to use the Web interface from your Mac.
```Shell ```Shell
docker run -it \ docker run -it \
--platform linux/arm64 \ --platform linux/arm64 \
--name stable-diffusion \ --name stable-diffusion \
--hostname stable-diffusion \ --hostname stable-diffusion \
--mount source=my-vol,target=/data \ --mount source=my-vol,target=/data \
--expose 9090 \
--publish 80:9090 \
debian debian
# or arm64v8/debian # or arm64v8/debian
``` ```
You're now on the container. Set the fork you want to use and set up the container: You're now on the container.
```Shell ```Shell
GITHUB_STABLE_DIFFUSION="-b docker-apple-silicon https://github.com/santisbon/stable-diffusion.git" # Set the fork you want to use
GITHUB_STABLE_DIFFUSION="-b docker-apple-silicon https://github.com/santisbon/stable-diffusion.git" \
apt update && apt upgrade -y && apt install -y \ && apt update && apt upgrade -y \
&& apt install -y \
git \ git \
pip3 \ pip \
python3 \ python3 \
wget wget
# you won't need to close and reopen your terminal after this because we'll source our .<shell>rc file # you won't need to close and reopen your terminal after this because we'll source our .<shell>rc file
cd /data && wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-aarch64.sh -O anaconda.sh \ cd /data && wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-aarch64.sh -O anaconda.sh \
&& chmod +x anaconda.sh && bash anaconda.sh -b -u -p /anaconda && /anaconda/bin/conda init bash && source ~/.bashrc && chmod +x anaconda.sh && bash anaconda.sh -b -u -p /anaconda && /anaconda/bin/conda init bash && source ~/.bashrc
# update conda
conda update -y -n base -c defaults conda
cd / && git clone $GITHUB_STABLE_DIFFUSION && cd stable-diffusion cd / && git clone $GITHUB_STABLE_DIFFUSION && cd stable-diffusion
@ -122,11 +123,11 @@ cd / && git clone $GITHUB_STABLE_DIFFUSION && cd stable-diffusion
PIP_EXISTS_ACTION=w PIP_EXISTS_ACTION=w
CONDA_SUBDIR=osx-arm64 CONDA_SUBDIR=osx-arm64
# Create the environment # Create the environment, activate it, install requirements.
# conda env create -f environment.yaml && conda activate ldm conda create -y --name ldm && conda activate ldm \
conda create -y --name ldm && conda activate ldm && pip3 install -r requirements-linux-arm64.txt
pip3 install -r requirements-linux-arm64.txt
# Only need to do this once (ok twice if you decide to add face restoration and upscaling):
python3 scripts/preload_models.py python3 scripts/preload_models.py
mkdir -p models/ldm/stable-diffusion-v1 \ mkdir -p models/ldm/stable-diffusion-v1 \
@ -139,6 +140,9 @@ Whether you're directly on macOS or a Linux container.
### Setup ### Setup
```Shell ```Shell
# If you're on a Linux container
apt install -y libgl1-mesa-glx libglib2.0-0
# by default expected in a sibling directory to stable-diffusion # by default expected in a sibling directory to stable-diffusion
cd .. && git clone https://github.com/TencentARC/GFPGAN.git && cd GFPGAN cd .. && git clone https://github.com/TencentARC/GFPGAN.git && cd GFPGAN
@ -152,9 +156,11 @@ pip3 install realesrgan # to enhance the background (non-face) regions and do up
wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth -P experiments/pretrained_models wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth -P experiments/pretrained_models
cd ../stable-diffusion cd ../stable-diffusion
python3 scripts/preload_models.py # if not, it will download model files from the Internet the first time you run dream.py with GFPGAN and Real-ESRGAN turned on. # if we don't preload models it will download model files from the Internet the first time you run dream.py with GFPGAN and Real-ESRGAN turned on.
python3 scripts/preload_models.py
``` ```
# Usage # Usage
## Startup ## Startup
@ -162,12 +168,12 @@ With the Conda environment activated (```conda activate ldm```), run the interac
Use the more accurate but VRAM-intensive full precision math because half-precision requires autocast and won't work. Use the more accurate but VRAM-intensive full precision math because half-precision requires autocast and won't work.
By default the images are saved in ```outputs/img-samples/```. By default the images are saved in ```outputs/img-samples/```.
If you're on a docker container set the output dir to the Docker volume. If you're on a docker container set the output dir to the Docker volume you created.
```Shell ```Shell
# If on Macbook # If on Macbook
python3 scripts/dream.py --full_precision python3 scripts/dream.py --full_precision
# If on Linux container # If on Linux container
python3 scripts/dream.py --full_precision -o /data python3 scripts/dream.py --full_precision -o /data
``` ```
You'll get the script's prompt. You can see available options or quit. You'll get the script's prompt. You can see available options or quit.
@ -177,21 +183,25 @@ dream> q
``` ```
## Text to Image ## Text to Image
For quick (and rough) results test with 5 steps (default 50), 1 sample image. For quick (but very rough) results test with 5 steps (default 50) and 1 sample image. This will let you know that everything is set up correctly.
Increase steps to 100 or more for good (but slower) results. Then increase steps to 100 or more for good (but slower) results.
The prompt can be in quotes or not. The prompt can be in quotes or not.
``` ```Shell
dream> The hulk fighting with sheldon cooper -s5 -n1 dream> The hulk fighting with sheldon cooper -s5 -n1
dream> "woman closeup highly detailed" -s 150 dream> "woman closeup highly detailed" -s 150
# Reuse previous seed and apply face restoration (if you installed GFPGAN) # Reuse previous seed and apply face restoration (if you installed GFPGAN)
dream> "woman closeup highly detailed" --steps 150 --seed -1 -G 0.8 dream> "woman closeup highly detailed" --steps 150 --seed -1 -G 0.75
# TODO: example for upscaling.
``` ```
TODO: example for upscaling. The -U option currently [doesn't work](https://github.com/lstein/stable-diffusion/issues/297) on Mac. You'll need to experiment to see if face restoration is making it better or worse for your specific prompt.
The -U option for upscaling has an [Issue](https://github.com/lstein/stable-diffusion/issues/297) on Mac.
If you're on a container and set the output to the Docker volume (or moved it there with ```mv outputs/img-samples/ /data/```) you can copy it easily wherever you want. If you're on a container and set the output to the Docker volume (or moved it there with ```mv outputs/img-samples/ /data/```) you can copy it wherever you want.
You can download it from the Docker Desktop app, Volumes, my-vol, data.
Or you can copy it from your terminal. Keep in mind ```docker cp``` can't expand ```*.png``` so you'll need to specify the image file name:
```Shell ```Shell
# On your host Macbook (you can use the name of any container that mounted the volume) # On your host Macbook (you can use the name of any container that mounted the volume)
docker cp dummy:/data/ ~/Pictures docker cp dummy:/data/000001.928403745.png /Users/<your-user>/Pictures
``` ```
## Image to Image ## Image to Image
@ -201,23 +211,26 @@ Make sure your input image size dimensions are multiples of 64 e.g. 512x512. Oth
If you're on a docker container, copy your input image into the Docker volume If you're on a docker container, copy your input image into the Docker volume
```Shell ```Shell
docker cp ~/Pictures/sketch-mountains-input.jpg dummy:/data/ docker cp /Users/<your-user>/Pictures/sketch-mountains-input.jpg dummy:/data/
``` ```
Try it out generating an image (or 4). Try it out generating an image (or 4).
The ```dream``` script needs absolute paths to find the image so don't use ```~```.
```Shell ```Shell
# If you're on your Macbook # If you're on your Macbook
dream> "A fantasy landscape, trending on artstation" -I ~/Pictures/sketch-mountains-input.jpg --strength 0.8 --steps 100 -n4 dream> "A fantasy landscape, trending on artstation" -I /Users/<your-user>/Pictures/sketch-mountains-input.jpg --strength 0.8 --steps 100 -n4
# If you're on a Linux container on your Macbook # If you're on a Linux container on your Macbook
dream> "A fantasy landscape, trending on artstation" -I /data/sketch-mountains-input.jpg --strength 0.8 --steps 100 -n1 dream> "A fantasy landscape, trending on artstation" -I /data/sketch-mountains-input.jpg --strength 0.75 --steps 100 -n1
``` ```
## Web Interface ## Web Interface
You can use the script with a graphical web interface You can use the ```dream``` script with a graphical web interface. Start the web server with:
```Shell ```Shell
python3 scripts/dream.py --full_precision --web python3 scripts/dream.py --full_precision --web
``` ```
and point your browser to http://127.0.0.1:9090 If it's running on your Mac point your Mac web browser to http://127.0.0.1:9090
Press Control-C at the command line to stop the web server.
## Notes ## Notes