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

Merge branch 'release-candidate-2-1-3' of github.com:/invoke-ai/InvokeAI into release-candidate-2-1-3

Browse Source
This commit is contained in:
Lincoln Stein 2022-11-11 06:50:04 +00:00
commit 061fb4ef00
6 changed files with 443 additions and 404 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
docs/features/IMG2IMG.md
View File

@ -19,13 +19,13 @@ tree on a hill with a river, nature photograph, national geographic -I./test-pic
This will take the original image shown here:
<figure markdown>
![](https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png)
![original-image](https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png){ width=320 }
</figure>
and generate a new image based on it as shown here:
<figure markdown>
![](https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png)
![generated-image](https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png){ width=320 }
</figure>
The `--init_img` (`-I`) option gives the path to the seed picture. `--strength`
@ -45,15 +45,16 @@ Note that the prompt makes a big difference. For example, this slight variation
on the prompt produces a very different image:
<figure markdown>
![](https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png)
![](https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png){ width=320 }
<caption markdown>photograph of a tree on a hill with a river</caption>
</figure>
!!! tip
When designing prompts, think about how the images scraped from the internet were captioned. Very few photographs will
be labeled "photograph" or "photorealistic." They will, however, be captioned with the publication, photographer, camera
model, or film settings.
When designing prompts, think about how the images scraped from the internet were
captioned. Very few photographs will be labeled "photograph" or "photorealistic."
They will, however, be captioned with the publication, photographer, camera model,
or film settings.
If the initial image contains transparent regions, then Stable Diffusion will
only draw within the transparent regions, a process called
@ -61,17 +62,17 @@ only draw within the transparent regions, a process called
However, for this to work correctly, the color information underneath the
transparent needs to be preserved, not erased.
!!! warning
!!! warning "**IMPORTANT ISSUE** "
**IMPORTANT ISSUE** `img2img` does not work properly on initial images smaller
than 512x512. Please scale your image to at least 512x512 before using it.
Larger images are not a problem, but may run out of VRAM on your GPU card. To
fix this, use the --fit option, which downscales the initial image to fit within
the box specified by width x height:
`img2img` does not work properly on initial images smaller
than 512x512. Please scale your image to at least 512x512 before using it.
Larger images are not a problem, but may run out of VRAM on your GPU card. To
fix this, use the --fit option, which downscales the initial image to fit within
the box specified by width x height:
```
tree on a hill with a river, national geographic -I./test-pictures/big-sketch.png -H512 -W512 --fit
```
```
tree on a hill with a river, national geographic -I./test-pictures/big-sketch.png -H512 -W512 --fit
```
## How does it actually work, though?
@ -87,7 +88,7 @@ from a prompt. If the step count is 10, then the "latent space" (Stable
Diffusion's internal representation of the image) for the prompt "fire" with
seed `1592514025` develops something like this:
```commandline
```bash
invoke> "fire" -s10 -W384 -H384 -S1592514025
```
@ -133,9 +134,9 @@ Notice how much more fuzzy the starting image is for strength `0.7` compared to
| | strength = 0.7 | strength = 0.4 |
| --------------------------- | ------------------------------------------------------------- | ------------------------------------------------------------- |
| initial image that SD sees | ![](../assets/img2img/000032.step-0.png) | ![](../assets/img2img/000030.step-0.png) |
| initial image that SD sees | ![step-0](../assets/img2img/000032.step-0.png) | ![step-0](../assets/img2img/000030.step-0.png) |
| steps argument to `invoke>` | `-S10` | `-S10` |
| steps actually taken | 7 | 4 |
| steps actually taken | `7` | `4` |
| latent space at each step | ![gravity32](../assets/img2img/000032.steps.gravity.png) | ![gravity30](../assets/img2img/000030.steps.gravity.png) |
| output | ![000032.1592514025](../assets/img2img/000032.1592514025.png) | ![000030.1592514025](../assets/img2img/000030.1592514025.png) |
@ -150,7 +151,7 @@ If you want to try this out yourself, all of these are using a seed of
`1592514025` with a width/height of `384`, step count `10`, the default sampler
(`k_lms`), and the single-word prompt `"fire"`:
```commandline
```bash
invoke> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
```
@ -170,7 +171,7 @@ give each generation 20 steps.
Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD
does `20` steps from my image):
```commandline
```bash
invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
```

19
docs/installation/INSTALL_DOCKER.md
View File

@ -4,12 +4,17 @@ title: Docker
# :fontawesome-brands-docker: Docker
## Before you begin
!!! warning "For end users"
- For end users: Install InvokeAI locally using the instructions for your OS.
- For developers: For container-related development tasks or for enabling easy
We highly recommend to Install InvokeAI locally using [these instructions](index.md)"
!!! tip "For developers"
For container-related development tasks or for enabling easy
deployment to other environments (on-premises or cloud), follow these
instructions. For general use, install locally to leverage your machine's GPU.
instructions.
For general use, install locally to leverage your machine's GPU.
## Why containers?
@ -94,11 +99,11 @@ After the build process is done, you can run the container via the provided
./docker-build/run.sh
```
When used without arguments, the container will start the website and provide
When used without arguments, the container will start the webserver and provide
you the link to open it. But if you want to use some other parameters you can
also do so.
!!! example
!!! example ""
```bash
docker-build/run.sh --from_file tests/validate_pr_prompt.txt
@ -112,7 +117,7 @@ also do so.
!!! warning "Deprecated"
From here on you will find the rest of the previous Docker-Docs, which will still
From here on you will find the the previous Docker-Docs, which will still
provide some usefull informations.
## Usage (time to have fun)

3
docs/installation/INSTALL_JUPYTER.md
View File

@ -14,8 +14,7 @@ download the notebook from the link above and load it up in VSCode
(with the appropriate extensions installed)/Jupyter/JupyterLab and
start running the cells one-by-one.
Note that you will need NVIDIA drivers, Python 3.10, and Git installed beforehand.
!!! Note "you will need NVIDIA drivers, Python 3.10, and Git installed beforehand"
## Walkthrough

428
docs/installation/INSTALL_MANUAL.md
View File

@ -2,51 +2,54 @@
title: Manual Installation
---
# :fontawesome-brands-linux: Linux
# :fontawesome-brands-apple: macOS
# :fontawesome-brands-windows: Windows
<figure markdown>
# :fontawesome-brands-linux: Linux | :fontawesome-brands-apple: macOS | :fontawesome-brands-windows: Windows
</figure>
!!! warning "This is for advanced Users"
who are already expirienced with using conda or pip
## Introduction
You have two choices for manual installation, the [first
one](#Conda_method) based on the Anaconda3 package manager (`conda`),
and [a second one](#PIP_method) which uses basic Python virtual
environment (`venv`) commands and the PIP package manager. Both
methods require you to enter commands on the command-line shell, also
known as the "console".
You have two choices for manual installation, the [first one](#Conda_method)
based on the Anaconda3 package manager (`conda`), and
[a second one](#PIP_method) which uses basic Python virtual environment (`venv`)
commands and the PIP package manager. Both methods require you to enter commands
on the terminal, also known as the "console".
On Windows systems you are encouraged to install and use the
[Powershell](https://learn.microsoft.com/en-us/powershell/scripting/install/installing-powershell-on-windows?view=powershell-7.3),
which provides compatibility with Linux and Mac shells and nice
features such as command-line completion.
which provides compatibility with Linux and Mac shells and nice features such as
command-line completion.
### Conda method
1. Check that your system meets the [hardware
requirements](index.md#Hardware_Requirements) and has the appropriate
GPU drivers installed. In particular, if you are a Linux user with an
AMD GPU installed, you may need to install the [ROCm
driver](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html).
1. Check that your system meets the
[hardware requirements](index.md#Hardware_Requirements) and has the
appropriate GPU drivers installed. In particular, if you are a Linux user
with an AMD GPU installed, you may need to install the
[ROCm driver](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html).
InvokeAI does not yet support Windows machines with AMD GPUs due to
the lack of ROCm driver support on this platform.
InvokeAI does not yet support Windows machines with AMD GPUs due to the lack
of ROCm driver support on this platform.
To confirm that the appropriate drivers are installed, run
`nvidia-smi` on NVIDIA/CUDA systems, and `rocm-smi` on AMD
systems. These should return information about the installed video
card.
To confirm that the appropriate drivers are installed, run `nvidia-smi` on
NVIDIA/CUDA systems, and `rocm-smi` on AMD systems. These should return
information about the installed video card.
Macintosh users with MPS acceleration, or anybody with a CPU-only
system, can skip this step.
Macintosh users with MPS acceleration, or anybody with a CPU-only system,
can skip this step.
2. You will need to install Anaconda3 and Git if they are not already
available. Use your operating system's preferred installer, or
download installers from the following URLs
available. Use your operating system's preferred package manager, or
download the installers manually. You can find them here:
- Anaconda3 (https://www.anaconda.com/)
- git (https://git-scm.com/downloads)
- [Anaconda3](https://www.anaconda.com/)
- [git](https://git-scm.com/downloads)
3. Copy the InvokeAI source code from GitHub using `git`:
3. Clone the [InvokeAI](https://github.com/invoke-ai/InvokeAI) source code from
GitHub:
```bash
git clone https://github.com/invoke-ai/InvokeAI.git
@ -55,122 +58,160 @@ download installers from the following URLs
This will create InvokeAI folder where you will follow the rest of the
steps.
3. Enter the newly-created InvokeAI folder. From this step forward make sure
that you are working in the InvokeAI directory!
4. Enter the newly-created InvokeAI folder:
```bash
cd InvokeAI
```
4. Select the appropriate environment file:
We have created a series of environment files suited for different
operating systems and GPU hardware. They are located in the
From this step forward make sure that you are working in the InvokeAI
directory!
5. Select the appropriate environment file:
We have created a series of environment files suited for different operating
systems and GPU hardware. They are located in the
`environments-and-requirements` directory:
```bash
environment-lin-amd.yml # Linux with an AMD (ROCm) GPU
environment-lin-cuda.yml # Linux with an NVIDIA CUDA GPU
environment-mac.yml # Macintoshes with MPS acceleration
environment-win-cuda.yml # Windows with an NVIDA CUDA GPU
```
<figure markdown>
Select the appropriate environment file, and make a link to it
from `environment.yml` in the top-level InvokeAI directory. The
command to do this from the top-level directory is:
| filename | OS |
| :----------------------: | :----------------------------: |
| environment-lin-amd.yml | Linux with an AMD (ROCm) GPU |
| environment-lin-cuda.yml | Linux with an NVIDIA CUDA GPU |
| environment-mac.yml | Macintosh |
| environment-win-cuda.yml | Windows with an NVIDA CUDA GPU |
!!! todo "Macintosh and Linux"
</figure>
Choose the appropriate environment file for your system and link or copy it
to `environment.yml` in InvokeAI's top-level directory. To do so, run
following command from the repository-root:
!!! Example ""
=== "Macintosh and Linux"
!!! todo
Replace `xxx` and `yyy` with the appropriate OS and GPU codes as seen in the
table above
```bash
ln -sf environments-and-requirements/environment-xxx-yyy.yml environment.yml
```
Replace `xxx` and `yyy` with the appropriate OS and GPU codes.
!!! todo "Windows requires admin privileges to make links, so we use the copy (cp) command"
```bash
cp environments-and-requirements\environment-win-cuda.yml environment.yml
```
When this is done, confirm that a file `environment.yml` has been created in
When this is done, confirm that a file `environment.yml` has been linked in
the InvokeAI root directory and that it points to the correct file in the
`environments-and-requirements`.
4. Run conda:
```bash
ls -la
```
=== "Windows"
Since it requires admin privileges to create links, we will use the copy (cp)
command to create your `environment.yml`
```cmd
cp environments-and-requirements\environment-win-cuda.yml environment.yml
```
Afterwards verify that the file `environment.yml` has been created, either via the
explorer or by using the command `dir` from the terminal
```cmd
dir
```
6. Create the conda environment:
```bash
conda env update
```
This will create a new environment named `invokeai` and install all
InvokeAI dependencies into it.
This will create a new environment named `invokeai` and install all InvokeAI
dependencies into it. If something goes wrong you should take a look at
[troubleshooting](#troubleshooting).
If something goes wrong at this point, see
[troubleshooting](#Troubleshooting).
7. Activate the `invokeai` environment:
5. Activate the `invokeai` environment:
In order to use the newly created environment you will first need to
activate it
```bash
conda activate invokeai
```
Your command-line prompt should change to indicate that `invokeai` is active.
Your command-line prompt should change to indicate that `invokeai` is active
by prepending `(invokeai)`.
6. Load the model weights files:
8. Pre-Load the model weights files:
!!! tip
If you have already downloaded the weights file(s) for another Stable
Diffusion distribution, you may skip this step (by selecting "skip" when
prompted) and configure InvokeAI to use the previously-downloaded files. The
process for this is described in [here](INSTALLING_MODELS.md).
```bash
python scripts/preload_models.py
```
(Windows users should use the backslash instead of the slash)
The script `preload_models.py` will interactively guide you through the
process of downloading and installing the weights files needed for InvokeAI.
Note that the main Stable Diffusion weights file is protected by a license
agreement that you have to agree to. The script will list the steps you need
to take to create an account on the site that hosts the weights files,
accept the agreement, and provide an access token that allows InvokeAI to
legally download and install the weights files.
The script `preload_models.py` will interactively guide you through
downloading and installing the weights files needed for
InvokeAI. Note that the main Stable Diffusion weights file is
protected by a license agreement that you have to agree to. The
script will list the steps you need to take to create an account on
the site that hosts the weights files, accept the agreement, and
provide an access token that allows InvokeAI to legally download
and install the weights files.
If you get an error message about a module not being installed, check that
the `invokeai` environment is active and if not, repeat step 5.
If you have already downloaded the weights file(s) for another
Stable Diffusion distribution, you may skip this step (by selecting
"skip" when prompted) and configure InvokeAI to use the
previously-downloaded files. The process for this is described in
[INSTALLING_MODELS.md].
9. Run the command-line- or the web- interface:
If you get an error message about a module not being installed,
check that the `invokeai` environment is active and if not, repeat
step 5.
!!! example ""
7. Run the command-line interface or the web interface:
!!! warning "Make sure that the conda environment is activated, which should create `(invokeai)` in front of your prompt!"
=== "CLI"
```bash
python scripts/invoke.py # command line
python scripts/invoke.py --web # web interface
python scripts/invoke.py
```
(Windows users replace backslash with forward slash)
=== "local Webserver"
```bash
python scripts/invoke.py --web
```
=== "Public Webserver"
```bash
python scripts/invoke.py --web --host 0.0.0.0
```
If you choose the run the web interface, point your browser at
http://localhost:9090 in order to load the GUI.
8. Render away!
10. Render away!
Browse the features listed in the [Stable Diffusion Toolkit
Docs](https://invoke-ai.git) to learn about all the things you can
do with InvokeAI.
Browse the [features](../features) section to learn about all the things you
can do with InvokeAI.
Note that some GPUs are slow to warm up. In particular, when using
an AMD card with the ROCm driver, you may have to wait for over a
minute the first time you try to generate an image. Fortunately, after
the warm up period rendering will be fast.
Note that some GPUs are slow to warm up. In particular, when using an AMD
card with the ROCm driver, you may have to wait for over a minute the first
time you try to generate an image. Fortunately, after the warm up period
rendering will be fast.
9. Subsequently, to relaunch the script, be sure to run "conda
activate invokeai", enter the `InvokeAI` directory, and then launch
the invoke script. If you forget to activate the 'invokeai'
environment, the script will fail with multiple `ModuleNotFound`
errors.
11. Subsequently, to relaunch the script, be sure to run "conda activate
invokeai", enter the `InvokeAI` directory, and then launch the invoke
script. If you forget to activate the 'invokeai' environment, the script
will fail with multiple `ModuleNotFound` errors.
## Updating to newer versions of the script
@ -184,15 +225,15 @@ conda env update
python scripts/preload_models.py --no-interactive #optional
```
This will bring your local copy into sync with the remote one. The
last step may be needed to take advantage of new features or released
models. The `--no-interactive` flag will prevent the script from
prompting you to download the big Stable Diffusion weights files.
This will bring your local copy into sync with the remote one. The last step may
be needed to take advantage of new features or released models. The
`--no-interactive` flag will prevent the script from prompting you to download
the big Stable Diffusion weights files.
## pip Install
To install InvokeAI with only the PIP package manager, please follow
these steps:
To install InvokeAI with only the PIP package manager, please follow these
steps:
1. Make sure you are using Python 3.9 or higher. The rest of the install
procedure depends on this:
@ -202,167 +243,174 @@ these steps:
```
2. Install the `virtualenv` tool if you don't have it already:
```bash
pip install virtualenv
```
3. From within the InvokeAI top-level directory, create and activate a
virtual environment named `invokeai`:
3. From within the InvokeAI top-level directory, create and activate a virtual
environment named `invokeai`:
```bash
virtualenv invokeai
source invokeai/bin/activate
```
4. Pick the correct `requirements*.txt` file for your hardware and
operating system.
4. Pick the correct `requirements*.txt` file for your hardware and operating
system.
We have created a series of environment files suited for different
operating systems and GPU hardware. They are located in the
We have created a series of environment files suited for different operating
systems and GPU hardware. They are located in the
`environments-and-requirements` directory:
```bash
requirements-lin-amd.txt # Linux with an AMD (ROCm) GPU
requirements-lin-arm64.txt # Linux running on arm64 systems
requirements-lin-cuda.txt # Linux with an NVIDIA (CUDA) GPU
requirements-mac-mps-cpu.txt # Macintoshes with MPS acceleration
requirements-lin-win-colab-cuda.txt # Windows with an NVIDA (CUDA) GPU
# (supports Google Colab too)
```
<figure markdown>
Select the appropriate requirements file, and make a link to it
from `environment.txt` in the top-level InvokeAI directory. The
command to do this from the top-level directory is:
| filename | OS |
| :---------------------------------: | :-------------------------------------------------------------: |
| requirements-lin-amd.txt | Linux with an AMD (ROCm) GPU |
| requirements-lin-arm64.txt | Linux running on arm64 systems |
| requirements-lin-cuda.txt | Linux with an NVIDIA (CUDA) GPU |
| requirements-mac-mps-cpu.txt | Macintoshes with MPS acceleration |
| requirements-lin-win-colab-cuda.txt | Windows with an NVIDA (CUDA) GPU<br>(supports Google Colab too) |
!!! todo "Macintosh and Linux"
</figure>
Select the appropriate requirements file, and make a link to it from
`requirements.txt` in the top-level InvokeAI directory. The command to do
this from the top-level directory is:
!!! example ""
=== "Macintosh and Linux"
!!! info "Replace `xxx` and `yyy` with the appropriate OS and GPU codes."
```bash
ln -sf environments-and-requirements/requirements-xxx-yyy.txt requirements.txt
```
Replace `xxx` and `yyy` with the appropriate OS and GPU codes.
=== "Windows"
!!! todo "Windows requires admin privileges to make links, so we use the copy (cp) command instead"
!!! info "since admin privileges are required to make links, so we use the copy (`cp`) command instead"
```bash
```cmd
cp environments-and-requirements\requirements-lin-win-colab-cuda.txt requirements.txt
```
Note that the order of arguments is reversed between the Linux/Mac and Windows
commands!
!!! warning
Please do not link directly to the file
`environments-and-requirements/requirements.txt`. This is a base requirements
file that does not have the platform-specific libraries.
Please do not link or copy `environments-and-requirements/requirements.txt`.
This is a base requirements file that does not have the platform-specific
libraries.
When this is done, confirm that a file `requirements.txt` has been
created in the InvokeAI root directory and that it points to the
correct file in the `environments-and-requirements`.
When this is done, confirm that a file named `requirements.txt` has been
created in the InvokeAI root directory and that it points to the correct
file in `environments-and-requirements`.
5. Run PIP
Be sure that the `invokeai` environment is active before doing
this:
Be sure that the `invokeai` environment is active before doing this:
```bash
pip install --prefer-binary -r requirements.txt
```
---
## Troubleshooting
Here are some common issues and their suggested solutions.
### Conda install
### Conda
1. Conda fails before completing `conda update`:
#### Conda fails before completing `conda update`
The usual source of these errors is a package
incompatibility. While we have tried to minimize these, over time
packages get updated and sometimes introduce incompatibilities.
The usual source of these errors is a package incompatibility. While we have
tried to minimize these, over time packages get updated and sometimes introduce
incompatibilities.
We suggest that you search
[Issues](https://github.com/invoke-ai/InvokeAI/issues) or the
"bugs-and-support" channel of the [InvokeAI
Discord](https://discord.gg/ZmtBAhwWhy).
We suggest that you search
[Issues](https://github.com/invoke-ai/InvokeAI/issues) or the "bugs-and-support"
channel of the [InvokeAI Discord](https://discord.gg/ZmtBAhwWhy).
You may also try to install the broken packages manually using PIP. To do this, activate
the `invokeai` environment, and run `pip install` with the name and version of the
package that is causing the incompatibility. For example:
You may also try to install the broken packages manually using PIP. To do this,
activate the `invokeai` environment, and run `pip install` with the name and
version of the package that is causing the incompatibility. For example:
```bash
pip install test-tube==0.7.5
```
```bash
pip install test-tube==0.7.5
```
You can keep doing this until all requirements are satisfied and
the `invoke.py` script runs without errors. Please report to
[Issues](https://github.com/invoke-ai/InvokeAI/issues) what you
were able to do to work around the problem so that others can
benefit from your investigation.
You can keep doing this until all requirements are satisfied and the `invoke.py`
script runs without errors. Please report to
[Issues](https://github.com/invoke-ai/InvokeAI/issues) what you were able to do
to work around the problem so that others can benefit from your investigation.
2. `preload_models.py` or `invoke.py` crashes at an early stage
#### `preload_models.py` or `invoke.py` crashes at an early stage
This is usually due to an incomplete or corrupted Conda install.
Make sure you have linked to the correct environment file and run
`conda update` again.
This is usually due to an incomplete or corrupted Conda install. Make sure you
have linked to the correct environment file and run `conda update` again.
If the problem persists, a more extreme measure is to clear Conda's
caches and remove the `invokeai` environment:
If the problem persists, a more extreme measure is to clear Conda's caches and
remove the `invokeai` environment:
```bash
conda deactivate
conda env remove -n invokeai
conda clean -a
conda update
```
```bash
conda deactivate
conda env remove -n invokeai
conda clean -a
conda update
```
This removes all cached library files, including ones that may have
been corrupted somehow. (This is not supposed to happen, but does
anyway).
This removes all cached library files, including ones that may have been
corrupted somehow. (This is not supposed to happen, but does anyway).
3. `invoke.py` crashes at a later stage.
#### `invoke.py` crashes at a later stage
If the CLI or web site had been working ok, but something
unexpected happens later on during the session, you've encountered
a code bug that is probably unrelated to an install issue. Please
search [Issues](https://github.com/invoke-ai/InvokeAI/issues), file
a bug report, or ask for help on [Discord](https://discord.gg/ZmtBAhwWhy)
If the CLI or web site had been working ok, but something unexpected happens
later on during the session, you've encountered a code bug that is probably
unrelated to an install issue. Please search
[Issues](https://github.com/invoke-ai/InvokeAI/issues), file a bug report, or
ask for help on [Discord](https://discord.gg/ZmtBAhwWhy)
4. My renders are running very slowly!
#### My renders are running very slowly
You may have installed the wrong torch (machine learning) package,
and the system is running on CPU rather than the GPU. To check,
look at the log messages that appear when `invoke.py` is first
starting up. One of the earlier lines should say `Using device type
cuda`. On AMD systems, it will also say "cuda", and on Macintoshes,
it should say "mps". If instead the message says it is running on
"cpu", then you may need to install the correct torch library.
You may have installed the wrong torch (machine learning) package, and the
system is running on CPU rather than the GPU. To check, look at the log messages
that appear when `invoke.py` is first starting up. One of the earlier lines
should say `Using device type cuda`. On AMD systems, it will also say "cuda",
and on Macintoshes, it should say "mps". If instead the message says it is
running on "cpu", then you may need to install the correct torch library.
You may be able to fix this by installing a different torch
library. Here are the magic incantations for Conda and PIP.
You may be able to fix this by installing a different torch library. Here are
the magic incantations for Conda and PIP.
!!! todo "For CUDA systems"
!!! todo "For CUDA systems"
- conda
(conda)
```bash
conda install pytorch torchvision torchaudio pytorch-cuda=11.6 -c pytorch -c nvidia
```
(pip)
- pip
```bash
pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116
```
!!! todo "For AMD systems"
!!! todo "For AMD systems"
- conda
(conda)
```bash
conda activate invokeai
pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/rocm5.2/
```
(pip)
- pip
```bash
pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/rocm5.2/
```
More information and troubleshooting tips can be found at https://pytorch.org.
More information and troubleshooting tips can be found at https://pytorch.org.

196
docs/installation/INSTALL_SOURCE.md
View File

@ -1,49 +1,49 @@
---
title: The InvokeAI Source Installer
title: Source Installer
---
# The InvokeAI Source Installer
## Introduction
The source installer is a shell script that attempts to automate every
step needed to install and run InvokeAI on a stock computer running
recent versions of Linux, MacOSX or Windows. It will leave you with a
version that runs a stable version of InvokeAI with the option to
upgrade to experimental versions later. It is not as foolproof as the
[InvokeAI installer](INSTALL_INVOKE.md)
The source installer is a shell script that attempts to automate every step
needed to install and run InvokeAI on a stock computer running recent versions
of Linux, MacOS or Windows. It will leave you with a version that runs a stable
version of InvokeAI with the option to upgrade to experimental versions later.
It is not as foolproof as the [InvokeAI installer](INSTALL_INVOKE.md)
Before you begin, make sure that you meet the [hardware
requirements](index.md#Hardware_Requirements) and has the appropriate
GPU drivers installed. In particular, if you are a Linux user with an
AMD GPU installed, you may need to install the [ROCm
driver](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html).
Before you begin, make sure that you meet the
[hardware requirements](index.md#Hardware_Requirements) and has the appropriate
GPU drivers installed. In particular, if you are a Linux user with an AMD GPU
installed, you may need to install the
[ROCm driver](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html).
Installation requires roughly 18G of free disk space to load the
libraries and recommended model weights files.
Installation requires roughly 18G of free disk space to load the libraries and
recommended model weights files.
## Walk through
Though there are multiple steps, there really is only one click
involved to kick off the process.
Though there are multiple steps, there really is only one click involved to kick
off the process.
1. The source installer is distributed in ZIP files. Go to the [latest
release](https://github.com/invoke-ai/InvokeAI/releases/latest), and
1. The source installer is distributed in ZIP files. Go to the
[latest release](https://github.com/invoke-ai/InvokeAI/releases/latest), and
look for a series of files named:
- invokeAI-src-installer-mac.zip
- invokeAI-src-installer-windows.zip
- invokeAI-src-installer-linux.zip
Download the one that is appropriate for your operating system.
Download the one that is appropriate for your operating system.
2. Unpack the zip file into a directory that has at least 18G of free
space. Do *not* unpack into a directory that has an earlier version of
InvokeAI.
2. Unpack the zip file into a directory that has at least 18G of free space. Do
_not_ unpack into a directory that has an earlier version of InvokeAI.
This will create a new directory named "InvokeAI". This example
shows how this would look using the `unzip` command-line tool,
but you may use any graphical or command-line Zip extractor:
This will create a new directory named "InvokeAI". This example shows how
this would look using the `unzip` command-line tool, but you may use any
graphical or command-line Zip extractor:
```bash
```cmd
C:\Documents\Linco> unzip invokeAI-windows.zip
Archive: C: \Linco\Downloads\invokeAI-linux.zip
creating: invokeAI\
@ -51,98 +51,87 @@ Download the one that is appropriate for your operating system.
inflating: invokeAI\readme.txt
```
3. If you are using a desktop GUI, double-click the installer file.
It will be named `install.bat` on Windows systems and `install.sh`
on Linux and Macintosh systems.
3. If you are using a desktop GUI, double-click the installer file. It will be
named `install.bat` on Windows systems and `install.sh` on Linux and
Macintosh systems.
4. Alternatively, form the command line, run the shell script or .bat
file:
4. Alternatively, form the command line, run the shell script or .bat file:
```bash
```cmd
C:\Documents\Linco> cd invokeAI
C:\Documents\Linco> install.bat
C:\Documents\Linco\invokeAI> install.bat
```
5. Sit back and let the install script work. It will install various
binary requirements including Conda, Git and Python, then download
the current InvokeAI code and install it along with its
dependencies.
5. Sit back and let the install script work. It will install various binary
requirements including Conda, Git and Python, then download the current
InvokeAI code and install it along with its dependencies.
6. After installation completes, the installer will launch a script
called `preload_models.py`, which will guide you through the
first-time process of selecting one or more Stable Diffusion model
weights files, downloading and configuring them.
6. After installation completes, the installer will launch a script called
`preload_models.py`, which will guide you through the first-time process of
selecting one or more Stable Diffusion model weights files, downloading and
configuring them.
Note that the main Stable Diffusion weights file is protected by a
license agreement that you must agree to in order to use. The
script will list the steps you need to take to create an account on
the official site that hosts the weights files, accept the
agreement, and provide an access token that allows InvokeAI to
legally download and install the weights files.
Note that the main Stable Diffusion weights file is protected by a license
agreement that you must agree to in order to use. The script will list the
steps you need to take to create an account on the official site that hosts
the weights files, accept the agreement, and provide an access token that
allows InvokeAI to legally download and install the weights files.
If you have already downloaded the weights file(s) for another
Stable Diffusion distribution, you may skip this step (by selecting
"skip" when prompted) and configure InvokeAI to use the
previously-downloaded files. The process for this is described in
[INSTALLING_MODELS.md].
If you have already downloaded the weights file(s) for another Stable
Diffusion distribution, you may skip this step (by selecting "skip" when
prompted) and configure InvokeAI to use the previously-downloaded files. The
process for this is described in [Installing Models](INSTALLING_MODELS.md).
7. The script will now exit and you'll be ready to generate some
images. The invokeAI directory will contain numerous files. Look
for a shell script named `invoke.sh` (Linux/Mac) or `invoke.bat`
(Windows). Launch the script by double-clicking it or typing
its name at the command-line:
7. The script will now exit and you'll be ready to generate some images. The
invokeAI directory will contain numerous files. Look for a shell script
named `invoke.sh` (Linux/Mac) or `invoke.bat` (Windows). Launch the script
by double-clicking it or typing its name at the command-line:
```bash
C:\Documents\Linco\invokeAI> cd invokeAI
```cmd
C:\Documents\Linco> cd invokeAI
C:\Documents\Linco\invokeAI> invoke.bat
```
The `invoke.bat` (`invoke.sh`) script will give you the choice of
starting (1) the command-line interface, or (2) the web GUI. If you
start the latter, you can load the user interface by pointing your
browser at http://localhost:9090.
The `invoke.bat` (`invoke.sh`) script will give you the choice of starting (1)
the command-line interface, or (2) the web GUI. If you start the latter, you can
load the user interface by pointing your browser at http://localhost:9090.
The `invoke` script also offers you a third option labeled "open
the developer console". If you choose this option, you will be
dropped into a command-line interface in which you can run python
commands directly, access developer tools, and launch InvokeAI
with customized options. To do the latter, you would launch the
script `scripts/invoke.py` as shown in this example:
The `invoke` script also offers you a third option labeled "open the developer
console". If you choose this option, you will be dropped into a command-line
interface in which you can run python commands directly, access developer tools,
and launch InvokeAI with customized options. To do the latter, you would launch
the script `scripts/invoke.py` as shown in this example:
```bash
python scripts\invoke.py --web --max_load_models=3 \
```cmd
python scripts/invoke.py --web --max_load_models=3 \
--model=waifu-1.3 --steps=30 --outdir=C:/Documents/AIPhotos
```
```
These options are described in detail in the [Command-Line
Interface](../features/CLI.md) documentation.
These options are described in detail in the
[Command-Line Interface](../features/CLI.md) documentation.
## Updating to newer versions
This section describes how to update InvokeAI to new versions of the
software.
This section describes how to update InvokeAI to new versions of the software.
### Updating the stable version
This distribution is changing rapidly, and we add new features on a
daily basis. To update to the latest released version (recommended),
run the `update.sh` (Linux/Mac) or `update.bat` (Windows)
scripts. This will fetch the latest release and re-run the
`preload_models` script to download any updated models files that may
be needed. You can also use this to add additional models that you did
not select at installation time.
This distribution is changing rapidly, and we add new features on a daily basis.
To update to the latest released version (recommended), run the `update.sh`
(Linux/Mac) or `update.bat` (Windows) scripts. This will fetch the latest
release and re-run the `preload_models` script to download any updated models
files that may be needed. You can also use this to add additional models that
you did not select at installation time.
### Updating to the development version
There may be times that there is a feature in the `development` branch
of InvokeAI that you'd like to take advantage of. Or perhaps there is
a branch that corrects an annoying bug. To do this, you will use the
developer's console.
There may be times that there is a feature in the `development` branch of
InvokeAI that you'd like to take advantage of. Or perhaps there is a branch that
corrects an annoying bug. To do this, you will use the developer's console.
From within the invokeAI directory, run the command `invoke.sh`
(Linux/Mac) or `invoke.bat` (Windows) and selection option (3) to open
the developers console. Then run the following command to get the
`development branch`:
From within the invokeAI directory, run the command `invoke.sh` (Linux/Mac) or
`invoke.bat` (Windows) and selection option (3) to open the developers console.
Then run the following command to get the `development branch`:
```bash
git checkout development
@ -150,19 +139,18 @@ git pull
conda env update
```
You can now close the developer console and run `invoke` as before.
If you get complaints about missing models, then you may need to do
the additional step of running `preload_models.py`. This happens
relatively infrequently. To do this, simply open up the developer's
console again and type `python scripts/preload_models.py`.
You can now close the developer console and run `invoke` as before. If you get
complaints about missing models, then you may need to do the additional step of
running `preload_models.py`. This happens relatively infrequently. To do this,
simply open up the developer's console again and type
`python scripts/preload_models.py`.
## Troubleshooting
If you run into problems during or after installation, the InvokeAI
team is available to help you. Either create an
[Issue](https://github.com/invoke-ai/InvokeAI/issues) at our GitHub
site, or make a request for help on the "bugs-and-support" channel of
our [Discord server](https://discord.gg/ZmtBAhwWhy). We are a 100%
volunteer organization, but typically somebody will be available to
help you within 24 hours, and often much sooner.
If you run into problems during or after installation, the InvokeAI team is
available to help you. Either create an
[Issue](https://github.com/invoke-ai/InvokeAI/issues) at our GitHub site, or
make a request for help on the "bugs-and-support" channel of our
[Discord server](https://discord.gg/ZmtBAhwWhy). We are a 100% volunteer
organization, but typically somebody will be available to help you within 24
hours, and often much sooner.

4
docs/installation/INSTALL.md → docs/installation/index.md
View File

@ -1,9 +1,7 @@
---
title: Installation Overview
title: Overview
---
## Installation
We offer several ways to install InvokeAI, each one suited to your
experience and preferences.