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 update/docs/remove-requirements-step

Browse Source
This commit is contained in:
Lincoln Stein
2023-02-02 16:14:45 -05:00
committed by GitHub
parent 7ca8abb206 756e50f641
commit fe9b4f4a3c
697 changed files with 2899 additions and 3341 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
docs/CHANGELOG.md
View File

@ -52,12 +52,17 @@ introduces several changes you should know about.
path: models/diffusers/hakurei-haifu-diffusion-1.4
```
2. The format of the models directory has changed to mimic the
HuggingFace cache directory. By default, diffusers models are
now automatically downloaded and retrieved from the directory
`ROOTDIR/models/diffusers`, while other models are stored in
the directory `ROOTDIR/models/hub`. This organization is the
same as that used by HuggingFace for its cache management.
2. In order of precedence, InvokeAI will now use HF_HOME, then
XDG_CACHE_HOME, then finally default to `ROOTDIR/models` to
store HuggingFace diffusers models.
Consequently, the format of the models directory has changed to
mimic the HuggingFace cache directory. When HF_HOME and XDG_HOME
are not set, diffusers models are now automatically downloaded
and retrieved from the directory `ROOTDIR/models/diffusers`,
while other models are stored in the directory
`ROOTDIR/models/hub`. This organization is the same as that used
by HuggingFace for its cache management.
This allows you to share diffusers and ckpt model files easily with
other machine learning applications that use the HuggingFace
@ -66,7 +71,13 @@ introduces several changes you should know about.
cache models in. To tell InvokeAI to use the standard HuggingFace
cache directory, you would set HF_HOME like this (Linux/Mac):
`export HF_HOME=~/.cache/hugging_face`
`export HF_HOME=~/.cache/huggingface`
Both HuggingFace and InvokeAI will fall back to the XDG_CACHE_HOME
environment variable if HF_HOME is not set; this path
takes precedence over `ROOTDIR/models` to allow for the same sharing
with other machine learning applications that use HuggingFace
libraries.
3. If you upgrade to InvokeAI 2.3.* from an earlier version, there
will be a one-time migration from the old models directory format

2
docs/features/CLI.md
View File

@ -136,7 +136,7 @@ mixture of both using any of the accepted command switch formats:
# InvokeAI initialization file
# This is the InvokeAI initialization file, which contains command-line default values.
# Feel free to edit. If anything goes wrong, you can re-initialize this file by deleting
# or renaming it and then running configure_invokeai.py again.
# or renaming it and then running invokeai-configure again.
# The --root option below points to the folder in which InvokeAI stores its models, configs and outputs.
--root="/Users/mauwii/invokeai"

2
docs/features/CONCEPTS.md
View File

@ -51,7 +51,7 @@ You can also combine styles and concepts:
If you used an installer to install InvokeAI, you may have already set a HuggingFace token.
If you skipped this step, you can:
- run the InvokeAI configuration script again (if you used a manual installer): `scripts/configure_invokeai.py`
- run the InvokeAI configuration script again (if you used a manual installer): `invokeai-configure`
- set one of the `HUGGINGFACE_TOKEN` or `HUGGING_FACE_HUB_TOKEN` environment variables to contain your token
Finally, if you already used any HuggingFace library on your computer, you might already have a token

2
docs/features/OUTPAINTING.md
View File

@ -120,7 +120,7 @@ A number of caveats:
(`--iterations`) argument.
3. Your results will be _much_ better if you use the `inpaint-1.5` model
released by runwayML and installed by default by `scripts/configure_invokeai.py`.
released by runwayML and installed by default by `invokeai-configure`.
This model was trained specifically to harmoniously fill in image gaps. The
standard model will work as well, but you may notice color discontinuities at
the border.

6
docs/features/POSTPROCESS.md
View File

@ -28,11 +28,11 @@ should "just work" without further intervention. Simply pass the `--upscale`
the popup in the Web GUI.
**GFPGAN** requires a series of downloadable model files to work. These are
loaded when you run `scripts/configure_invokeai.py`. If GFPAN is failing with an
loaded when you run `invokeai-configure`. If GFPAN is failing with an
error, please run the following from the InvokeAI directory:
```bash
python scripts/configure_invokeai.py
invokeai-configure
```
If you do not run this script in advance, the GFPGAN module will attempt to
@ -106,7 +106,7 @@ This repo also allows you to perform face restoration using
[CodeFormer](https://github.com/sczhou/CodeFormer).
In order to setup CodeFormer to work, you need to download the models like with
GFPGAN. You can do this either by running `configure_invokeai.py` or by manually
GFPGAN. You can do this either by running `invokeai-configure` or by manually
downloading the
[model file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth)
and saving it to `ldm/invoke/restoration/codeformer/weights` folder.

40
docs/features/PROMPTS.md
View File

@ -239,28 +239,24 @@ Generate an image with a given prompt, record the seed of the image, and then
use the `prompt2prompt` syntax to substitute words in the original prompt for
words in a new prompt. This works for `img2img` as well.
- `a ("fluffy cat").swap("smiling dog") eating a hotdog`.
- quotes optional: `a (fluffy cat).swap(smiling dog) eating a hotdog`.
- for single word substitutions parentheses are also optional:
`a cat.swap(dog) eating a hotdog`.
- Supports options `s_start`, `s_end`, `t_start`, `t_end` (each 0-1) loosely
corresponding to bloc97's `prompt_edit_spatial_start/_end` and
`prompt_edit_tokens_start/_end` but with the math swapped to make it easier to
intuitively understand.
- Example usage:`a (cat).swap(dog, s_end=0.3) eating a hotdog` - the `s_end`
argument means that the "spatial" (self-attention) edit will stop having any
effect after 30% (=0.3) of the steps have been done, leaving Stable
Diffusion with 70% of the steps where it is free to decide for itself how to
reshape the cat-form into a dog form.
- The numbers represent a percentage through the step sequence where the edits
should happen. 0 means the start (noisy starting image), 1 is the end (final
image).
- For img2img, the step sequence does not start at 0 but instead at
(1-strength) - so if strength is 0.7, s_start and s_end must both be
greater than 0.3 (1-0.7) to have any effect.
- Convenience option `shape_freedom` (0-1) to specify how much "freedom" Stable
Diffusion should have to change the shape of the subject being swapped.
- `a (cat).swap(dog, shape_freedom=0.5) eating a hotdog`.
For example, consider the prompt `a cat.swap(dog) playing with a ball in the forest`. Normally, because of the word words interact with each other when doing a stable diffusion image generation, these two prompts would generate different compositions:
- `a cat playing with a ball in the forest`
- `a dog playing with a ball in the forest`
| `a cat playing with a ball in the forest` | `a dog playing with a ball in the forest` |
| --- | --- |
| img | img |
- For multiple word swaps, use parentheses: `a (fluffy cat).swap(barking dog) playing with a ball in the forest`.
- To swap a comma, use quotes: `a ("fluffy, grey cat").swap("big, barking dog") playing with a ball in the forest`.
- Supports options `t_start` and `t_end` (each 0-1) loosely corresponding to bloc97's `prompt_edit_tokens_start/_end` but with the math swapped to make it easier to
intuitively understand. `t_start` and `t_end` are used to control on which steps cross-attention control should run. With the default values `t_start=0` and `t_end=1`, cross-attention control is active on every step of image generation. Other values can be used to turn cross-attention control off for part of the image generation process.
- For example, if doing a diffusion with 10 steps for the prompt is `a cat.swap(dog, t_start=0.3, t_end=1.0) playing with a ball in the forest`, the first 3 steps will be run as `a cat playing with a ball in the forest`, while the last 7 steps will run as `a dog playing with a ball in the forest`, but the pixels that represent `dog` will be locked to the pixels that would have represented `cat` if the `cat` prompt had been used instead.
- Conversely, for `a cat.swap(dog, t_start=0, t_end=0.7) playing with a ball in the forest`, the first 7 steps will run as `a dog playing with a ball in the forest` with the pixels that represent `dog` locked to the same pixels that would have represented `cat` if the `cat` prompt was being used instead. The final 3 steps will just run `a cat playing with a ball in the forest`.
> For img2img, the step sequence does not start at 0 but instead at `(1.0-strength)` - so if the img2img `strength` is `0.7`, `t_start` and `t_end` must both be greater than `0.3` (`1.0-0.7`) to have any effect.
Prompt2prompt `.swap()` is not compatible with xformers, which will be temporarily disabled when doing a `.swap()` - so you should expect to use more VRAM and run slower that with xformers enabled.
The `prompt2prompt` code is based off
[bloc97's colab](https://github.com/bloc97/CrossAttentionControl).

30
docs/installation/010_INSTALL_AUTOMATED.md
View File

@ -29,8 +29,9 @@ version of InvokeAI with the option to upgrade to experimental versions later.
2. Check that your system has an up-to-date Python installed. To do this, open
up a command-line window ("Terminal" on Linux and Macintosh, "Command" or
"Powershell" on Windows) and type `python --version`. If Python is
installed, it will print out the version number. If it is version `3.9.1` or
higher, you meet requirements.
installed, it will print out the version number. If it is version `3.9.1` or `3.10.x`, you meet requirements.
!!! warning "At this time we do not recommend Python 3.11"
!!! warning "If you see an older version, or get a command not found error"
@ -39,7 +40,6 @@ version of InvokeAI with the option to upgrade to experimental versions later.
[Version 3.10.9](https://www.python.org/downloads/release/python-3109/),
which has been extensively tested with InvokeAI.
!!! warning "At this time we do not recommend Python 3.11"
_Please select your platform in the section below for platform-specific
setup requirements._
@ -108,12 +108,11 @@ version of InvokeAI with the option to upgrade to experimental versions later.
[latest release](https://github.com/invoke-ai/InvokeAI/releases/latest), and
look for a series of files named:
- InvokeAI-installer-2.X.X-mac.zip
- InvokeAI-installer-2.X.X-windows.zip
- InvokeAI-installer-2.X.X-linux.zip
- InvokeAI-installer-2.X.X.zip
(Where 2.X.X is the current release number).
Download the one that is appropriate for your operating system.
Download the latest release.
4. Unpack the zip file into a convenient directory. This will create a new
directory named "InvokeAI-Installer". This example shows how this would look
@ -177,8 +176,7 @@ version of InvokeAI with the option to upgrade to experimental versions later.
minutes and nothing is happening, you can interrupt the script with ^C. You
may restart it and it will pick up where it left off.
10. After installation completes, the installer will launch a script called
`configure_invokeai.py`, which will guide you through the first-time process
10. After installation completes, the installer will launch the configuration script, which will guide you through the first-time process
of selecting one or more Stable Diffusion model weights files, downloading
and configuring them. We provide a list of popular models that InvokeAI
performs well with. However, you can add more weight files later on using
@ -227,7 +225,7 @@ version of InvokeAI with the option to upgrade to experimental versions later.
`invokeai\invokeai.init`. It contains a variety of examples that you can
follow to add and modify launch options.
!!! warning "The `invokeai` directory contains the `invoke` application, its
!!! warning "The `invokeai` directory contains the `invokeai` application, its
configuration files, the model weight files, and outputs of image generation.
Once InvokeAI is installed, do not move or remove this directory."
@ -253,18 +251,18 @@ will bring InvokeAI up to date with the latest libraries.
### Corrupted configuration file
Everything seems to install ok, but `invoke` complains of a corrupted
Everything seems to install ok, but `invokeai` complains of a corrupted
configuration file and goes back into the configuration process (asking you to
download models, etc), but this doesn't fix the problem.
This issue is often caused by a misconfigured configuration directive in the
`invokeai\invokeai.init` initialization file that contains startup settings. The
easiest way to fix the problem is to move the file out of the way and re-run
`configure_invokeai.py`. Enter the developer's console (option 3 of the launcher
`invokeai-configure`. Enter the developer's console (option 3 of the launcher
script) and run this command:
```cmd
configure_invokeai.py --root=.
invokeai-configure --root=.
```
Note the dot (.) after `--root`. It is part of the command.
@ -289,15 +287,15 @@ hours, and often much sooner.
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 `configure_invokeai` script to download any updated
release and re-run the `invokeai-configure` 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.
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 `configure_invokeai.py`. This happens relatively infrequently. To do
running `invokeai-configure`. This happens relatively infrequently. To do
this, simply open up the developer's console again and type
`python scripts/configure_invokeai.py`.
`invokeai-configure`.
You may also use the `update` script to install any selected version of
InvokeAI. From https://github.com/invoke-ai/InvokeAI, navigate to the zip file

4
docs/installation/020_INSTALL_MANUAL.md
View File

@ -87,8 +87,7 @@ please follow these steps:
`~/invokeai`.
```bash
configure_invokeai \
--root_dir ~/Programs/invokeai
invokeai-configure --root_dir ~/Programs/invokeai
```
The script `invokeai-configure` will interactively guide you through the
@ -198,3 +197,4 @@ works with the PIP method.
code repository entirely.
(Don't move the runtime directory!)

10
docs/installation/050_INSTALLING_MODELS.md
View File

@ -56,7 +56,7 @@ unofficial Stable Diffusion models and where they can be obtained.
There are three ways to install weights files:
1. During InvokeAI installation, the `configure_invokeai.py` script can download
1. During InvokeAI installation, the `invokeai-configure` script can download
them for you.
2. You can use the command-line interface (CLI) to import, configure and modify
@ -65,13 +65,13 @@ There are three ways to install weights files:
3. You can download the files manually and add the appropriate entries to
`models.yaml`.
### Installation via `configure_invokeai.py`
### Installation via `invokeai-configure`
This is the most automatic way. Run `scripts/configure_invokeai.py` from the
This is the most automatic way. Run `invokeai-configure` from the
console. It will ask you to select which models to download and lead you through
the steps of setting up a Hugging Face account if you haven't done so already.
To start, run `python scripts/configure_invokeai.py` from within the InvokeAI:
To start, run `invokeai-configure` from within the InvokeAI:
directory
!!! example ""
@ -244,7 +244,7 @@ arabian-nights-1.0:
| arabian-nights-1.0 | This is the name of the model that you will refer to from within the CLI and the WebGUI when you need to load and use the model. |
| description | Any description that you want to add to the model to remind you what it is. |
| weights | Relative path to the .ckpt weights file for this model. |
| config | This is the confusingly-named configuration file for the model itself. Use `./configs/stable-diffusion/v1-inference.yaml` unless the model happens to need a custom configuration, in which case the place you downloaded it from will tell you what to use instead. For example, the runwayML custom inpainting model requires the file `configs/stable-diffusion/v1-inpainting-inference.yaml`. This is already inclued in the InvokeAI distribution and is configured automatically for you by the `configure_invokeai.py` script. |
| config | This is the confusingly-named configuration file for the model itself. Use `./configs/stable-diffusion/v1-inference.yaml` unless the model happens to need a custom configuration, in which case the place you downloaded it from will tell you what to use instead. For example, the runwayML custom inpainting model requires the file `configs/stable-diffusion/v1-inpainting-inference.yaml`. This is already inclued in the InvokeAI distribution and is configured automatically for you by the `invokeai-configure` script. |
| vae | If you want to add a VAE file to the model, then enter its path here. |
| width, height | This is the width and height of the images used to train the model. Currently they are always 512 and 512. |