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 'main' into fix-samefile

Browse Source
This commit is contained in:
Lincoln Stein 2023-02-03 13:02:01 -05:00 committed by GitHub
commit b0ad109886
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
11 changed files with 271 additions and 560 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

155
docs/installation/020_INSTALL_MANUAL.md
View File

@ -14,22 +14,15 @@ title: Installing Manually
## Introduction
You have two choices for manual installation. The [first one](#pip-Install) uses
basic Python virtual environment (`venv`) command and `pip` package manager. The
[second one](#Conda-method) uses Anaconda3 package manager (`conda`). Both
methods require you to enter commands on the terminal, also known as the
"console".
Note that the `conda` installation method is currently deprecated and will not
be supported at some point in the future.
!!! tip As of InvokeAI v2.3.0 installation using the `conda` package manager
is no longer being supported. It will likely still work, but we are not testing
this installation method.
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.
## pip Install
To install InvokeAI with virtual environments and the PIP package manager,
please follow these steps:
@ -50,44 +43,64 @@ please follow these steps:
This will create InvokeAI folder where you will follow the rest of the
steps.
3. From within the InvokeAI top-level directory, create and activate a virtual
environment named `.venv` and prompt displaying `InvokeAI`:
```bash
python -m venv .venv \
--prompt InvokeAI \
--upgrade-deps
source .venv/bin/activate
```
4. Make sure that pip is installed in your virtual environment an up to date:
```bash
python -m ensurepip \
--upgrade
python -m pip install \
--upgrade pip
```
5. Install Package
```bash
pip install --use-pep517 .
```
6. Set up the runtime directory
In this step you will initialize a runtime directory that will contain the
models, model config files, directory for textual inversion embeddings, and
your outputs. This keeps the runtime directory separate from the source code
and aids in updating.
You may pick any location for this directory using the `--root_dir` option
(abbreviated --root). If you don't pass this option, it will default to
`~/invokeai`.
3. Create a directory of to contain your InvokeAI installation (known as the "runtime"
or "root" directory). This is where your models, configs, and outputs will live
by default. Please keep in mind the disk space requirements - you will need at
least 18GB (as of this writing) for the models and the virtual environment.
From now on we will refer to this directory as `INVOKEAI_ROOT`. This keeps the
runtime directory separate from the source code and aids in updating.
```bash
invokeai-configure --root_dir ~/Programs/invokeai
export INVOKEAI_ROOT="~/invokeai"
mkdir ${INVOKEAI_ROOT}
```
4. From within the InvokeAI top-level directory, create and activate a virtual
environment named `.venv` and prompt displaying `InvokeAI`:
```bash
python -m venv ${INVOKEAI_ROOT}/.venv \
--prompt invokeai \
--upgrade-deps \
--copies
source ${INVOKEAI_ROOT}/.venv/bin/activate
```
!!! warning
You **may** create your virtual environment anywhere on the filesystem.
But IF you choose a location that is *not* inside the `$INVOKEAI_ROOT` directory,
then you must set the `INVOKEAI_ROOT` environment variable in your shell environment,
for example, by editing `~/.bashrc` or `~/.zshrc` files, or setting the Windows environment
variable. Refer to your operating system / shell documentation for the correct way of doing so.
5. Make sure that pip is installed in your virtual environment an up to date:
```bash
python -m pip install --upgrade pip
```
6. Install Package
```bash
pip install --use-pep517 .
```
Deactivate and reactivate your runtime directory so that the invokeai-specific commands
become available in the environment
```
deactivate && source ${INVOKEAI_ROOT}/.venv/bin/activate
```
7. Set up the runtime directory
In this step you will initialize your runtime directory with the downloaded
models, model config files, directory for textual inversion embeddings, and
your outputs.
```bash
invokeai-configure --root ${INVOKEAI_ROOT}
```
The script `invokeai-configure` will interactively guide you through the
@ -101,11 +114,6 @@ please follow these steps:
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.
Note that `invokeai-configure` and `invokeai` should be installed under your
virtual environment directory and the system should find them on the PATH.
If this isn't working on your system, you can call the scripts directory
using `python scripts/configure_invokeai.py` and `python scripts/invoke.py`.
!!! tip
If you have already downloaded the weights file(s) for another Stable
@ -127,19 +135,19 @@ please follow these steps:
=== "CLI"
```bash
invoke.py --root ~/Programs/invokeai
invokeai --root ~/invokeai
```
=== "local Webserver"
```bash
invoke.py --web --root ~/Programs/invokeai
invokeai --web --root ~/invokeai
```
=== "Public Webserver"
```bash
invoke.py --web --host 0.0.0.0 --root ~/Programs/invokeai
invokeai --web --host 0.0.0.0 --root ~/invokeai
```
If you choose the run the web interface, point your browser at
@ -147,7 +155,8 @@ please follow these steps:
!!! tip
You can permanently set the location of the runtime directory by setting the environment variable INVOKEAI_ROOT to the path of the directory.
You can permanently set the location of the runtime directory by setting the environment variable `INVOKEAI_ROOT` to the path of the directory. As mentioned previously, this is
**required** if your virtual environment is located outside of your runtime directory.
8. Render away!
@ -163,38 +172,6 @@ please follow these steps:
then launch `invokeai` command. If you forget to activate the virtual
environment you will most likeley receive a `command not found` error.
!!! tip
Do not move the source code repository after installation. The virtual environment directory has absolute paths in it that get confused if the directory is moved.
## Creating an "install" version of InvokeAI
If you wish you can install InvokeAI and all its dependencies in the runtime
directory. This allows you to delete the source code repository and eliminates
the need to provide `--root_dir` at startup time. Note that this method only
works with the PIP method.
1. Follow the instructions for the PIP install, but in step #2 put the virtual
environment into the runtime directory. For example, assuming the runtime
directory lives in `~/Programs/invokeai`, you'd run:
```bash
python -m venv ~/Programs/invokeai
```
2. Now follow steps 3 to 5 in the PIP recipe, ending with the `pip install`
step.
3. Run one additional step while you are in the source code repository directory
```
pip install --use-pep517 . # note the dot in the end!!!
```
4. That's all! Now, whenever you activate the virtual environment, `invokeai`
will know where to look for the runtime directory without needing a
`--root_dir` argument. In addition, you can now move or delete the source
code repository entirely.
(Don't move the runtime directory!)
!!! warning
Do not move the runtime directory after installation. The virtual environment has absolute paths in it that get confused if the directory is moved.

1
docs/installation/INSTALL_AUTOMATED.md
View File

@ -1 +0,0 @@
010_INSTALL_AUTOMATED.md

374
docs/installation/INSTALL_MANUAL.md
View File

@ -1,374 +0,0 @@
---
title: Manual Installation
---
<figure markdown>
# :fontawesome-brands-linux: Linux | :fontawesome-brands-apple: macOS | :fontawesome-brands-windows: Windows
</figure>
!!! warning "This is for advanced Users"
who are already experienced 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 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.
### 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).
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.
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 package manager, or
download the installers manually. You can find them here:
- [Anaconda3](https://www.anaconda.com/)
- [git](https://git-scm.com/downloads)
3. Clone the [InvokeAI](https://github.com/invoke-ai/InvokeAI) source code from
GitHub:
```bash
git clone https://github.com/invoke-ai/InvokeAI.git
```
This will create InvokeAI folder where you will follow the rest of the
steps.
4. Enter the newly-created InvokeAI folder:
```bash
cd InvokeAI
```
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:
<figure markdown>
| 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 |
</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
```
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`.
```bash
ls -la
```
=== "Windows"
!!! todo " Since it requires admin privileges to create links, we will use the copy command to create your `environment.yml`"
```cmd
copy 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
```
!!! warning "Do not try to run conda on directly on the subdirectory environments file. This won't work. Instead, copy or link it to the top-level directory as shown."
6. Create the conda environment:
```bash
conda env update
```
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).
7. 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
by prepending `(invokeai)`.
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](050_INSTALLING_MODELS.md).
```bash
python scripts/configure_invokeai.py
```
The script `configure_invokeai.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.
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.
9. Run the command-line- or the web- interface:
!!! example ""
!!! warning "Make sure that the conda environment is activated, which should create `(invokeai)` in front of your prompt!"
=== "CLI"
```bash
python scripts/invoke.py
```
=== "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.
10. Render away!
Browse the [features](../features/CLI.md) 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.
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
This distribution is changing rapidly. If you used the `git clone` method
(step 5) to download the InvokeAI directory, then to update to the latest and
greatest version, launch the Anaconda window, enter `InvokeAI` and type:
```bash
git pull
conda env update
python scripts/configure_invokeai.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.
## pip Install
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:
```bash
python -V
```
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`:
```bash
virtualenv invokeai
source invokeai/bin/activate
```
4. Run PIP
```bash
pip --python invokeai install --use-pep517 .
```
---
## Troubleshooting
Here are some common issues and their suggested solutions.
### Conda
#### 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.
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:
```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.
### Create Conda Environment fails on MacOS
If conda create environment fails with lmdb error, this is most likely caused by Clang.
Run brew config to see which Clang is installed on your Mac. If Clang isn't installed, that's causing the error.
Start by installing additional XCode command line tools, followed by brew install llvm.
```bash
xcode-select --install
brew install llvm
```
If brew config has Clang installed, update to the latest llvm and try creating the environment again.
#### `configure_invokeai.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.
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
```
This removes all cached library files, including ones that may have been
corrupted somehow. (This is not supposed to happen, but does anyway).
#### `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)
#### 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 be able to fix this by installing a different torch library. Here are
the magic incantations for Conda and PIP.
!!! todo "For CUDA systems"
- conda
```bash
conda install pytorch torchvision torchaudio pytorch-cuda=11.6 -c pytorch -c nvidia
```
- pip
```bash
pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116
```
!!! todo "For AMD systems"
- conda
```bash
conda activate invokeai
pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/rocm5.2/
```
- 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.

2
invokeai/frontend/dist/assets/index-legacy-eaf1c1d4.js → invokeai/frontend/dist/assets/index-legacy-8f3bb5f8.js vendored
View File

File diff suppressed because one or more lines are too long

78
invokeai/frontend/dist/assets/index.92e1e2e8.js → invokeai/frontend/dist/assets/index.2a9ecaa6.js vendored
View File

File diff suppressed because one or more lines are too long

4
invokeai/frontend/dist/index.html vendored
View File

@ -7,7 +7,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>InvokeAI - A Stable Diffusion Toolkit</title>
<link rel="shortcut icon" type="icon" href="./assets/favicon.0d253ced.ico" />
<script type="module" crossorigin src="./assets/index.92e1e2e8.js"></script>
<script type="module" crossorigin src="./assets/index.2a9ecaa6.js"></script>
<link rel="stylesheet" href="./assets/index.8badc8b4.css">
<script type="module">try{import.meta.url;import("_").catch(()=>1);}catch(e){}window.__vite_is_modern_browser=true;</script>
<script type="module">!function(){if(window.__vite_is_modern_browser)return;console.warn("vite: loading legacy build because dynamic import or import.meta.url is unsupported, syntax error above should be ignored");var e=document.getElementById("vite-legacy-polyfill"),n=document.createElement("script");n.src=e.src,n.onload=function(){System.import(document.getElementById('vite-legacy-entry').getAttribute('data-src'))},document.body.appendChild(n)}();</script>
@ -18,6 +18,6 @@
<script nomodule>!function(){var e=document,t=e.createElement("script");if(!("noModule"in t)&&"onbeforeload"in t){var n=!1;e.addEventListener("beforeload",(function(e){if(e.target===t)n=!0;else if(!e.target.hasAttribute("nomodule")||!n)return;e.preventDefault()}),!0),t.type="module",t.src=".",e.head.appendChild(t),t.remove()}}();</script>
<script nomodule crossorigin id="vite-legacy-polyfill" src="./assets/polyfills-legacy-dde3a68a.js"></script>
<script nomodule crossorigin id="vite-legacy-entry" data-src="./assets/index-legacy-eaf1c1d4.js">System.import(document.getElementById('vite-legacy-entry').getAttribute('data-src'))</script>
<script nomodule crossorigin id="vite-legacy-entry" data-src="./assets/index-legacy-8f3bb5f8.js">System.import(document.getElementById('vite-legacy-entry').getAttribute('data-src'))</script>
</body>
</html>

1
invokeai/frontend/dist/locales/options/en.json vendored
View File

@ -46,6 +46,7 @@
"sendTo": "Send to",
"sendToImg2Img": "Send to Image to Image",
"sendToUnifiedCanvas": "Send To Unified Canvas",
"copyImage": "Copy Image",
"copyImageToLink": "Copy Image To Link",
"downloadImage": "Download Image",
"openInViewer": "Open In Viewer",

1
invokeai/frontend/public/locales/options/en.json
View File

@ -46,6 +46,7 @@
"sendTo": "Send to",
"sendToImg2Img": "Send to Image to Image",
"sendToUnifiedCanvas": "Send To Unified Canvas",
"copyImage": "Copy Image",
"copyImageToLink": "Copy Image To Link",
"downloadImage": "Download Image",
"openInViewer": "Open In Viewer",

24
invokeai/frontend/src/features/gallery/components/CurrentImageButtons.tsx
View File

@ -121,6 +121,22 @@ const CurrentImageButtons = () => {
dispatch(setActiveTab('img2img'));
};
const handleCopyImage = async () => {
if (!currentImage) return;
const blob = await fetch(currentImage.url).then((res) => res.blob());
const data = [new ClipboardItem({ [blob.type]: blob })];
await navigator.clipboard.write(data);
toast({
title: t('toast:imageCopied'),
status: 'success',
duration: 2500,
isClosable: true,
});
};
const handleCopyImageLink = () => {
navigator.clipboard
.writeText(
@ -391,6 +407,14 @@ const CurrentImageButtons = () => {
>
{t('options:sendToUnifiedCanvas')}
</IAIButton>
<IAIButton
size={'sm'}
onClick={handleCopyImage}
leftIcon={<FaCopy />}
>
{t('options:copyImage')}
</IAIButton>
<IAIButton
size={'sm'}
onClick={handleCopyImageLink}

4
ldm/invoke/config/configure_invokeai.py
View File

@ -528,8 +528,8 @@ def update_config_file(successfully_downloaded: dict, opt: dict):
# this check is ignored if opt.config_file is specified - user is assumed to know what they
# are doing if they are passing a custom config file from elsewhere.
if config_file is Default_config_file and not config_file.parent.exists():
configs_src = Path(__file__).parent / "configs"
configs_dest = Path(Globals.root) / "configs"
configs_src = Dataset_path.parent
configs_dest = Default_config_file.parent
shutil.copytree(configs_src, configs_dest, dirs_exist_ok=True)
yaml = new_config_file_contents(successfully_downloaded, config_file)

187
ldm/invoke/merge_diffusers.py
View File

@ -5,6 +5,7 @@ used to merge 2-3 models together and create a new InvokeAI-registered diffusion
Copyright (c) 2023 Lincoln Stein and the InvokeAI Development Team
"""
import argparse
import curses
import os
import sys
from argparse import Namespace
@ -12,6 +13,7 @@ from pathlib import Path
from typing import List, Union
import npyscreen
import warnings
from diffusers import DiffusionPipeline
from omegaconf import OmegaConf
@ -26,7 +28,6 @@ from ldm.invoke.model_manager import ModelManager
DEST_MERGED_MODEL_DIR = "merged_models"
def merge_diffusion_models(
model_ids_or_paths: List[Union[str, Path]],
alpha: float = 0.5,
@ -185,6 +186,8 @@ class mergeModelsForm(npyscreen.FormMultiPageAction):
def __init__(self, parentApp, name):
self.parentApp = parentApp
self.ALLOW_RESIZE=True
self.FIX_MINIMUM_SIZE_WHEN_CREATED=False
super().__init__(parentApp, name)
@property
@ -195,29 +198,94 @@ class mergeModelsForm(npyscreen.FormMultiPageAction):
self.parentApp.setNextForm(None)
def create(self):
window_height,window_width=curses.initscr().getmaxyx()
self.model_names = self.get_model_names()
max_width = max([len(x) for x in self.model_names])
max_width += 6
horizontal_layout = max_width*3 < window_width
self.add_widget_intelligent(
npyscreen.FixedText, name="Select up to three models to merge", value=""
npyscreen.FixedText,
color='CONTROL',
value=f"Select two models to merge and optionally a third.",
editable=False,
)
self.models = self.add_widget_intelligent(
npyscreen.TitleMultiSelect,
name="Select two to three models to merge:",
self.add_widget_intelligent(
npyscreen.FixedText,
color='CONTROL',
value=f"Use up and down arrows to move, <space> to select an item, <tab> and <shift-tab> to move from one field to the next.",
editable=False,
)
self.add_widget_intelligent(
npyscreen.FixedText,
value='MODEL 1',
color='GOOD',
editable=False,
rely=4 if horizontal_layout else None,
)
self.model1 = self.add_widget_intelligent(
npyscreen.SelectOne,
values=self.model_names,
value=None,
max_height=len(self.model_names) + 1,
value=0,
max_height=len(self.model_names),
max_width=max_width,
scroll_exit=True,
rely=5,
)
self.add_widget_intelligent(
npyscreen.FixedText,
value='MODEL 2',
color='GOOD',
editable=False,
relx=max_width+3 if horizontal_layout else None,
rely=4 if horizontal_layout else None,
)
self.model2 = self.add_widget_intelligent(
npyscreen.SelectOne,
name='(2)',
values=self.model_names,
value=1,
max_height=len(self.model_names),
max_width=max_width,
relx=max_width+3 if horizontal_layout else None,
rely=5 if horizontal_layout else None,
scroll_exit=True,
)
self.models.when_value_edited = self.models_changed
self.add_widget_intelligent(
npyscreen.FixedText,
value='MODEL 3',
color='GOOD',
editable=False,
relx=max_width*2+3 if horizontal_layout else None,
rely=4 if horizontal_layout else None,
)
models_plus_none = self.model_names.copy()
models_plus_none.insert(0,'None')
self.model3 = self.add_widget_intelligent(
npyscreen.SelectOne,
name='(3)',
values=models_plus_none,
value=0,
max_height=len(self.model_names)+1,
max_width=max_width,
scroll_exit=True,
relx=max_width*2+3 if horizontal_layout else None,
rely=5 if horizontal_layout else None,
)
for m in [self.model1,self.model2,self.model3]:
m.when_value_edited = self.models_changed
self.merged_model_name = self.add_widget_intelligent(
npyscreen.TitleText,
name="Name for merged model:",
labelColor='CONTROL',
value="",
scroll_exit=True,
)
self.force = self.add_widget_intelligent(
npyscreen.Checkbox,
name="Force merge of incompatible models",
labelColor='CONTROL',
value=False,
scroll_exit=True,
)
@ -226,6 +294,7 @@ class mergeModelsForm(npyscreen.FormMultiPageAction):
name="Merge Method:",
values=self.interpolations,
value=0,
labelColor='CONTROL',
max_height=len(self.interpolations) + 1,
scroll_exit=True,
)
@ -236,47 +305,53 @@ class mergeModelsForm(npyscreen.FormMultiPageAction):
step=0.05,
lowest=0,
value=0.5,
labelColor='CONTROL',
scroll_exit=True,
)
self.models.editing = True
self.model1.editing = True
def models_changed(self):
model_names = self.models.values
selected_models = self.models.value
if len(selected_models) > 3:
npyscreen.notify_confirm(
"Too many models selected for merging. Select two to three."
)
return
elif len(selected_models) > 2:
self.merge_method.values = ["add_difference"]
self.merge_method.value = 0
models = self.model1.values
selected_model1 = self.model1.value[0]
selected_model2 = self.model2.value[0]
selected_model3 = self.model3.value[0]
merged_model_name = f'{models[selected_model1]}+{models[selected_model2]}'
self.merged_model_name.value = merged_model_name
if selected_model3 > 0:
self.merge_method.values=['add_difference'],
self.merged_model_name.value += f'+{models[selected_model3]}'
else:
self.merge_method.values = self.interpolations
self.merged_model_name.value = "+".join(
[model_names[x] for x in selected_models]
)
self.merge_method.values=self.interpolations
self.merge_method.value=0
def on_ok(self):
if self.validate_field_values() and self.check_for_overwrite():
self.parentApp.setNextForm(None)
self.editing = False
self.parentApp.merge_arguments = self.marshall_arguments()
npyscreen.notify("Starting the merge...")
npyscreen.notify('Starting the merge...')
else:
self.editing = True
def on_cancel(self):
sys.exit(0)
def marshall_arguments(self) -> dict:
models = [self.models.values[x] for x in self.models.value]
def marshall_arguments(self)->dict:
model_names = self.model_names
models = [
model_names[self.model1.value[0]],
model_names[self.model2.value[0]],
]
if self.model3.value[0] > 0:
models.append(model_names[self.model3.value[0]-1])
args = dict(
models=models,
alpha=self.alpha.value,
interp=self.interpolations[self.merge_method.value[0]],
force=self.force.value,
merged_model_name=self.merged_model_name.value,
alpha = self.alpha.value,
interp = self.interpolations[self.merge_method.value[0]],
force = self.force.value,
merged_model_name = self.merged_model_name.value,
)
return args
@ -289,15 +364,18 @@ class mergeModelsForm(npyscreen.FormMultiPageAction):
f"The chosen merged model destination, {model_out}, is already in use. Overwrite?"
)
def validate_field_values(self) -> bool:
def validate_field_values(self)->bool:
bad_fields = []
selected_models = self.models.value
if len(selected_models) < 2 or len(selected_models) > 3:
bad_fields.append("Please select two or three models to merge.")
model_names = self.model_names
selected_models = set((model_names[self.model1.value[0]],model_names[self.model2.value[0]]))
if self.model3.value[0] > 0:
selected_models.add(model_names[self.model3.value[0]-1])
if len(selected_models) < 2:
bad_fields.append(f'Please select two or three DIFFERENT models to compare. You selected {selected_models}')
if len(bad_fields) > 0:
message = "The following problems were detected and must be corrected:"
message = 'The following problems were detected and must be corrected:'
for problem in bad_fields:
message += f"\n* {problem}"
message += f'\n* {problem}'
npyscreen.notify_confirm(message)
return False
else:
@ -322,10 +400,9 @@ class Mergeapp(npyscreen.NPSAppManaged):
) # precision doesn't really matter here
def onStart(self):
npyscreen.setTheme(npyscreen.Themes.DefaultTheme)
npyscreen.setTheme(npyscreen.Themes.ElegantTheme)
self.main = self.addForm("MAIN", mergeModelsForm, name="Merge Models Settings")
def run_gui(args: Namespace):
mergeapp = Mergeapp()
mergeapp.run()
@ -338,8 +415,8 @@ def run_gui(args: Namespace):
def run_cli(args: Namespace):
assert args.alpha >= 0 and args.alpha <= 1.0, "alpha must be between 0 and 1"
assert (
len(args.models) >= 1 and len(args.models) <= 3
), "provide 2 or 3 models to merge"
args.models and len(args.models) >= 1 and len(args.models) <= 3
), "Please provide the --models argument to list 2 to 3 models to merge. Use --help for full usage."
if not args.merged_model_name:
args.merged_model_name = "+".join(args.models)
@ -353,6 +430,7 @@ def run_cli(args: Namespace):
), f'A model named "{args.merged_model_name}" already exists. Use --clobber to overwrite.'
merge_diffusion_models_and_commit(**vars(args))
print(f'>> Models merged into new model: "{args.merged_model_name}".')
def main():
@ -365,17 +443,22 @@ def main():
] = cache_dir # because not clear the merge pipeline is honoring cache_dir
args.cache_dir = cache_dir
try:
if args.front_end:
run_gui(args)
else:
run_cli(args)
print(f">> Conversion successful. New model is named {args.merged_model_name}")
except Exception as e:
print(f"** An error occurred while merging the pipelines: {str(e)}")
sys.exit(-1)
except KeyboardInterrupt:
sys.exit(-1)
with warnings.catch_warnings():
warnings.simplefilter('ignore')
try:
if args.front_end:
run_gui(args)
else:
run_cli(args)
print(f'>> Conversion successful.')
except Exception as e:
if str(e).startswith('Not enough space'):
print('** Not enough horizontal space! Try making the window wider, or relaunch with a smaller starting size.')
else:
print(f"** An error occurred while merging the pipelines: {str(e)}")
sys.exit(-1)
except KeyboardInterrupt:
sys.exit(-1)
if __name__ == "__main__":
main()