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

finished CLI, IMG2IMG and WEB updates

Browse Source
This commit is contained in:
Lincoln Stein
2023-02-08 12:45:56 -05:00
parent 9d69843a9d
commit c6a2ba12e2
6 changed files with 201 additions and 212 deletions
Download Patch File Download Diff File Expand all files Collapse all files

185
docs/features/CLI.md
View File

@ -6,38 +6,51 @@ title: Command-Line Interface
## **Interactive Command Line Interface** ## **Interactive Command Line Interface**
The `invoke.py` script, located in `scripts/`, provides an interactive interface The InvokeAI command line interface (CLI) provides scriptable access
to image generation similar to the "invoke mothership" bot that Stable AI to InvokeAI's features.Some advanced features are only available
provided on its Discord server. through the CLI, though they eventually find their way into the WebUI.
Unlike the `txt2img.py` and `img2img.py` scripts provided in the original The CLI is accessible from the `invoke.sh`/`invoke.bat` launcher by
[CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion) source selecting option (1). Alternatively, it can be launched directly from
code repository, the time-consuming initialization of the AI model the command line by activating the InvokeAI environment and giving the
initialization only happens once. After that image generation from the command:
command-line interface is very fast.
```bash
invokeai
```
After some startup messages, you will be presented with the `invoke> `
prompt. Here you can type prompts to generate images and issue other
commands to load and manipulate generative models. The CLI has a large
number of command-line options that control its behavior. To get a
concise summary of the options, call `invokeai` with the `--help` argument:
```bash
invokeai --help
```
The script uses the readline library to allow for in-line editing, command The script uses the readline library to allow for in-line editing, command
history (++up++ and ++down++), autocompletion, and more. To help keep track of history (++up++ and ++down++), autocompletion, and more. To help keep track of
which prompts generated which images, the script writes a log file of image which prompts generated which images, the script writes a log file of image
names and prompts to the selected output directory. names and prompts to the selected output directory.
In addition, as of version 1.02, it also writes the prompt into the PNG file's Here is a typical session
metadata where it can be retrieved using `scripts/images2prompt.py`
The script is confirmed to work on Linux, Windows and Mac systems.
!!! note
This script runs from the command-line or can be used as a Web application. The Web GUI is
currently rudimentary, but a much better replacement is on its way.
```bash ```bash
(invokeai) ~/stable-diffusion$ python3 ./scripts/invoke.py PS1:C:\Users\fred> invokeai
* Initializing, be patient... * Initializing, be patient...
Loading model from models/ldm/text2img-large/model.ckpt * Initializing, be patient...
(...more initialization messages...) >> Initialization file /home/lstein/invokeai/invokeai.init found. Loading...
>> Internet connectivity is True
* Initialization done! Awaiting your command... >> InvokeAI, version 2.3.0-rc5
>> InvokeAI runtime directory is "/home/lstein/invokeai"
>> GFPGAN Initialized
>> CodeFormer Initialized
>> ESRGAN Initialized
>> Using device_type cuda
>> xformers memory-efficient attention is available and enabled
(...more initialization messages...)
* Initialization done! Awaiting your command (-h for help, 'q' to quit)
invoke> ashley judd riding a camel -n2 -s150 invoke> ashley judd riding a camel -n2 -s150
Outputs: Outputs:
outputs/img-samples/00009.png: "ashley judd riding a camel" -n2 -s150 -S 416354203 outputs/img-samples/00009.png: "ashley judd riding a camel" -n2 -s150 -S 416354203
@ -47,27 +60,15 @@ invoke> "there's a fly in my soup" -n6 -g
outputs/img-samples/00011.png: "there's a fly in my soup" -n6 -g -S 2685670268 outputs/img-samples/00011.png: "there's a fly in my soup" -n6 -g -S 2685670268
seeds for individual rows: [2685670268, 1216708065, 2335773498, 822223658, 714542046, 3395302430] seeds for individual rows: [2685670268, 1216708065, 2335773498, 822223658, 714542046, 3395302430]
invoke> q invoke> q
# this shows how to retrieve the prompt stored in the saved image's metadata
(invokeai) ~/stable-diffusion$ python ./scripts/images2prompt.py outputs/img_samples/*.png
00009.png: "ashley judd riding a camel" -s150 -S 416354203
00010.png: "ashley judd riding a camel" -s150 -S 1362479620
00011.png: "there's a fly in my soup" -n6 -g -S 2685670268
``` ```
![invoke-py-demo](../assets/dream-py-demo.png) ![invoke-py-demo](../assets/dream-py-demo.png)
The `invoke>` prompt's arguments are pretty much identical to those used in the
Discord bot, except you don't need to type `!invoke` (it doesn't hurt if you
do). A significant change is that creation of individual images is now the
default unless `--grid` (`-g`) is given. A full list is given in
[List of prompt arguments](#list-of-prompt-arguments).
## Arguments ## Arguments
The script itself also recognizes a series of command-line switches that will The script recognizes a series of command-line switches that will
change important global defaults, such as the directory for image outputs and change important global defaults, such as the directory for image
the location of the model weight files. outputs and the location of the model weight files.
### List of arguments recognized at the command line ### List of arguments recognized at the command line
@ -82,10 +83,14 @@ overridden on a per-prompt basis (see
| `--outdir <path>` | `-o<path>` | `outputs/img_samples` | Location for generated images. | | `--outdir <path>` | `-o<path>` | `outputs/img_samples` | Location for generated images. |
| `--prompt_as_dir` | `-p` | `False` | Name output directories using the prompt text. | | `--prompt_as_dir` | `-p` | `False` | Name output directories using the prompt text. |
| `--from_file <path>` | | `None` | Read list of prompts from a file. Use `-` to read from standard input | | `--from_file <path>` | | `None` | Read list of prompts from a file. Use `-` to read from standard input |
| `--model <modelname>` | | `stable-diffusion-1.4` | Loads model specified in configs/models.yaml. Currently one of "stable-diffusion-1.4" or "laion400m" | | `--model <modelname>` | | `stable-diffusion-1.5` | Loads the initial model specified in configs/models.yaml. |
| `--full_precision` | `-F` | `False` | Run in slower full-precision mode. Needed for Macintosh M1/M2 hardware and some older video cards. | | `--ckpt_convert ` | | `False` | If provided both .ckpt and .safetensors files will be auto-converted into diffusers format in memory |
| `--autoconvert <path>` | | `None` | On startup, scan the indicated directory for new .ckpt/.safetensor files and automatically convert and import them |
| `--precision` | | `fp16` | Provide `fp32` for full precision mode, `fp16` for half-precision. `fp32` needed for Macintoshes and some NVidia cards. |
| `--png_compression <0-9>` | `-z<0-9>` | `6` | Select level of compression for output files, from 0 (no compression) to 9 (max compression) | | `--png_compression <0-9>` | `-z<0-9>` | `6` | Select level of compression for output files, from 0 (no compression) to 9 (max compression) |
| `--safety-checker` | | `False` | Activate safety checker for NSFW and other potentially disturbing imagery | | `--safety-checker` | | `False` | Activate safety checker for NSFW and other potentially disturbing imagery |
| `--patchmatch`, `--no-patchmatch` | | `--patchmatch` | Load/Don't load the PatchMatch inpainting extension |
| `--xformers`, `--no-xformers` | | `--xformers` | Load/Don't load the Xformers memory-efficient attention module (CUDA only) |
| `--web` | | `False` | Start in web server mode | | `--web` | | `False` | Start in web server mode |
| `--host <ip addr>` | | `localhost` | Which network interface web server should listen on. Set to 0.0.0.0 to listen on any. | | `--host <ip addr>` | | `localhost` | Which network interface web server should listen on. Set to 0.0.0.0 to listen on any. |
| `--port <port>` | | `9090` | Which port web server should listen for requests on. | | `--port <port>` | | `9090` | Which port web server should listen for requests on. |
@ -109,6 +114,7 @@ overridden on a per-prompt basis (see
| Argument | Shortcut | Default | Description | | Argument | Shortcut | Default | Description |
|--------------------|------------|---------------------|--------------| |--------------------|------------|---------------------|--------------|
| `--full_precision` | | `False` | Same as `--precision=fp32`|
| `--weights <path>` | | `None` | Path to weights file; use `--model stable-diffusion-1.4` instead | | `--weights <path>` | | `None` | Path to weights file; use `--model stable-diffusion-1.4` instead |
| `--laion400m` | `-l` | `False` | Use older LAION400m weights; use `--model=laion400m` instead | | `--laion400m` | `-l` | `False` | Use older LAION400m weights; use `--model=laion400m` instead |
@ -336,8 +342,10 @@ useful for debugging the text masking process prior to inpainting with the
### Model selection and importation ### Model selection and importation
The CLI allows you to add new models on the fly, as well as to switch among them The CLI allows you to add new models on the fly, as well as to switch
rapidly without leaving the script. among them rapidly without leaving the script. There are several
different model formats, each described in the [Model Installation
Guide](050_INSTALLING_MODELS.md).
#### `!models` #### `!models`
@ -347,9 +355,9 @@ model is bold-faced
Example: Example:
<pre> <pre>
laion400m not loaded <no description> inpainting-1.5 not loaded Stable Diffusion inpainting model
<b>stable-diffusion-1.4 active Stable Diffusion v1.4</b> <b>stable-diffusion-1.5 active Stable Diffusion v1.5</b>
waifu-diffusion not loaded Waifu Diffusion v1.3 waifu-diffusion not loaded Waifu Diffusion v1.4
</pre> </pre>
#### `!switch <model>` #### `!switch <model>`
@ -361,43 +369,30 @@ Note how the second column of the `!models` table changes to `cached` after a
model is first loaded, and that the long initialization step is not needed when model is first loaded, and that the long initialization step is not needed when
loading a cached model. loading a cached model.
<pre> #### `!import_model <hugging_face_repo_ID>`
invoke> !models
laion400m not loaded <no description>
<b>stable-diffusion-1.4 cached Stable Diffusion v1.4</b>
waifu-diffusion active Waifu Diffusion v1.3
invoke> !switch waifu-diffusion This imports and installs a `diffusers`-style model that is stored on
>> Caching model stable-diffusion-1.4 in system RAM the [HuggingFace Web Site](https://huggingface.co). You can look up
>> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt any [Stable Diffusion diffusers
| LatentDiffusion: Running in eps-prediction mode model](https://huggingface.co/models?library=diffusers) and install it
| DiffusionWrapper has 859.52 M params. with a command like the following:
| Making attention of type 'vanilla' with 512 in_channels
| Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
| Making attention of type 'vanilla' with 512 in_channels
| Using faster float16 precision
>> Model loaded in 18.24s
>> Max VRAM used to load the model: 2.17G
>> Current VRAM usage:2.17G
>> Setting Sampler to k_lms
invoke> !models ```bash
laion400m not loaded <no description> !import_model prompthero/openjourney
stable-diffusion-1.4 cached Stable Diffusion v1.4 ```
<b>waifu-diffusion active Waifu Diffusion v1.3</b>
invoke> !switch stable-diffusion-1.4 #### `!import_model <path/to/diffusers/directory>`
>> Caching model waifu-diffusion in system RAM
>> Retrieving model stable-diffusion-1.4 from system RAM cache
>> Setting Sampler to k_lms
invoke> !models If you have a copy of a `diffusers`-style model saved to disk, you can
laion400m not loaded <no description> import it by passing the path to model's top-level directory.
<b>stable-diffusion-1.4 active Stable Diffusion v1.4</b>
waifu-diffusion cached Waifu Diffusion v1.3
</pre>
#### `!import_model <path/to/model/weights>` #### `!import_model <url>`
For a `.ckpt` or `.safetensors` file, if you have a direct download
URL for the file, you can provide it to `!import_model` and the file
will be downloaded and installed for you.
#### `!import_model <path/to/model/weights.ckpt>`
This command imports a new model weights file into InvokeAI, makes it available This command imports a new model weights file into InvokeAI, makes it available
for image generation within the script, and writes out the configuration for the for image generation within the script, and writes out the configuration for the
@ -417,35 +412,12 @@ below, the bold-faced text shows what the user typed in with the exception of
the width, height and configuration file paths, which were filled in the width, height and configuration file paths, which were filled in
automatically. automatically.
Example: #### `!import_model <path/to/directory_of_models>`
<pre> If you provide the path of a directory that contains one or more
invoke> <b>!import_model models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt</b> `.ckpt` or `.safetensors` files, the CLI will scan the directory and
>> Model import in process. Please enter the values needed to configure this model: interactively offer to import the models it finds there. Also see the
`--autoconvert` command-line option.
Name for this model: <b>waifu-diffusion</b>
Description of this model: <b>Waifu Diffusion v1.3</b>
Configuration file for this model: <b>configs/stable-diffusion/v1-inference.yaml</b>
Default image width: <b>512</b>
Default image height: <b>512</b>
>> New configuration:
waifu-diffusion:
config: configs/stable-diffusion/v1-inference.yaml
description: Waifu Diffusion v1.3
height: 512
weights: models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
width: 512
OK to import [n]? <b>y</b>
>> Caching model stable-diffusion-1.4 in system RAM
>> Loading waifu-diffusion from models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt
| LatentDiffusion: Running in eps-prediction mode
| DiffusionWrapper has 859.52 M params.
| Making attention of type 'vanilla' with 512 in_channels
| Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
| Making attention of type 'vanilla' with 512 in_channels
| Using faster float16 precision
invoke>
</pre>
#### `!edit_model <name_of_model>` #### `!edit_model <name_of_model>`
@ -479,11 +451,6 @@ OK to import [n]? y
... ...
</pre> </pre>
======= invoke> !fix 000017.4829112.gfpgan-00.png --embiggen 3 ...lots of
text... Outputs: [2] outputs/img-samples/000018.2273800735.embiggen-00.png: !fix
"outputs/img-samples/000017.243781548.gfpgan-00.png" -s 50 -S 2273800735 -W 512
-H 512 -C 7.5 -A k_lms --embiggen 3.0 0.75 0.25 ```
### History processing ### History processing
The CLI provides a series of convenient commands for reviewing previous actions, The CLI provides a series of convenient commands for reviewing previous actions,

23
docs/features/IMG2IMG.md
View File

@ -4,13 +4,24 @@ title: Image-to-Image
# :material-image-multiple: Image-to-Image # :material-image-multiple: Image-to-Image
## `img2img` Both the Web and command-line interfaces provide an "img2img" feature
that lets you seed your creations with an initial drawing or
photo. This is a really cool feature that tells stable diffusion to
build the prompt on top of the image you provide, preserving the
original's basic shape and layout.
This script also provides an `img2img` feature that lets you seed your creations See the [WebUI Guide](WEB.md) for a walkthrough of the img2img feature
with an initial drawing or photo. This is a really cool feature that tells in the InvokeAI web server. This document describes how to use img2img
stable diffusion to build the prompt on top of the image you provide, preserving in the command-line tool.
the original's basic shape and layout. To use it, provide the `--init_img`
option as shown here: ## Basic Usage
Launch the command-line client by launching `invoke.sh`/`invoke.bat`
and choosing option (1). Alternative, activate the InvokeAI
environment and issue the command `invokeai`.
Once the `invoke> ` prompt appears, you can start an img2img render by
pointing to a seed file with the `-I` option as shown here:
!!! example "" !!! example ""

51
docs/features/WEB.md
View File

@ -5,11 +5,14 @@ title: InvokeAI Web Server
# :material-web: InvokeAI Web Server # :material-web: InvokeAI Web Server
As of version 2.0.0, this distribution comes with a full-featured web server As of version 2.0.0, this distribution comes with a full-featured web server
(see screenshot). To use it, run the `invoke.py` script by adding the `--web` (see screenshot).
option:
To use it, launch the `invoke.sh`/`invoke.bat` script and select
option (2). Alternatively, with the InvokeAI environment active, run
the `invokeai` script by adding the `--web` option:
```bash ```bash
(invokeai) ~/InvokeAI$ python3 scripts/invoke.py --web invokeai --web
``` ```
You can then connect to the server by pointing your web browser at You can then connect to the server by pointing your web browser at
@ -19,17 +22,23 @@ address of the host you are running it on, or the wildcard `0.0.0.0`. For
example: example:
```bash ```bash
(invokeai) ~/InvokeAI$ python3 scripts/invoke.py --web --host 0.0.0.0 invoke.sh --host 0.0.0.0
``` ```
## Quick guided walkthrough of the WebGUI's features or
While most of the WebGUI's features are intuitive, here is a guided walkthrough ```bash
invokeai --web --host 0.0.0.0
```
## Quick guided walkthrough of the WebUI's features
While most of the WebUI's features are intuitive, here is a guided walkthrough
through its various components. through its various components.
![Invoke Web Server - Major Components](../assets/invoke-web-server-1.png){:width="640px"} ![Invoke Web Server - Major Components](../assets/invoke-web-server-1.png){:width="640px"}
The screenshot above shows the Text to Image tab of the WebGUI. There are three The screenshot above shows the Text to Image tab of the WebUI. There are three
main sections: main sections:
1. A **control panel** on the left, which contains various settings for text to 1. A **control panel** on the left, which contains various settings for text to
@ -63,12 +72,14 @@ From top to bottom, these are:
1. Text to Image - generate images from text 1. Text to Image - generate images from text
2. Image to Image - from an uploaded starting image (drawing or photograph) 2. Image to Image - from an uploaded starting image (drawing or photograph)
generate a new one, modified by the text prompt generate a new one, modified by the text prompt
3. Inpainting (pending) - Interactively erase portions of a starting image and 3. Unified Canvas - Interactively combine multiple images, extend them
have the AI fill in the erased region from a text prompt. with outpainting,and modify interior portions of the image with
4. Outpainting (pending) - Interactively add blank space to the borders of a inpainting, erase portions of a starting image and have the AI fill in
starting image and fill in the background from a text prompt. the erased region from a text prompt.
5. Postprocessing (pending) - Interactively postprocess generated images using a 4. Workflow Management (not yet implemented) - this panel will allow you to create
variety of filters. pipelines of common operations and combine them into workflows.
5. Training (not yet implemented) - this panel will provide an interface to [textual
inversion training](TEXTUAL_INVERSION.md) and fine tuning.
The inpainting, outpainting and postprocessing tabs are currently in The inpainting, outpainting and postprocessing tabs are currently in
development. However, limited versions of their features can already be accessed development. However, limited versions of their features can already be accessed
@ -76,18 +87,18 @@ through the Text to Image and Image to Image tabs.
## Walkthrough ## Walkthrough
The following walkthrough will exercise most (but not all) of the WebGUI's The following walkthrough will exercise most (but not all) of the WebUI's
feature set. feature set.
### Text to Image ### Text to Image
1. Launch the WebGUI using `python scripts/invoke.py --web` and connect to it 1. Launch the WebUI using `python scripts/invoke.py --web` and connect to it
with your browser by accessing `http://localhost:9090`. If the browser and with your browser by accessing `http://localhost:9090`. If the browser and
server are running on different machines on your LAN, add the option server are running on different machines on your LAN, add the option
`--host 0.0.0.0` to the launch command line and connect to the machine `--host 0.0.0.0` to the launch command line and connect to the machine
hosting the web server using its IP address or domain name. hosting the web server using its IP address or domain name.
2. If all goes well, the WebGUI should come up and you'll see a green 2. If all goes well, the WebUI should come up and you'll see a green
`connected` message on the upper right. `connected` message on the upper right.
#### Basics #### Basics
@ -234,7 +245,7 @@ walkthrough.
2. Drag-and-drop the Lincoln-and-Parrot image into the Image panel, or click 2. Drag-and-drop the Lincoln-and-Parrot image into the Image panel, or click
the blank area to get an upload dialog. The image will load into an area the blank area to get an upload dialog. The image will load into an area
marked _Initial Image_. (The WebGUI will also load the most marked _Initial Image_. (The WebUI will also load the most
recently-generated image from the gallery into a section on the left, but recently-generated image from the gallery into a section on the left, but
this image will be replaced in the next step.) this image will be replaced in the next step.)
@ -284,13 +295,17 @@ initial image" icons are located.
![Invoke Web Server - Use as Image Links](../assets/invoke-web-server-9.png){:width="640px"} ![Invoke Web Server - Use as Image Links](../assets/invoke-web-server-9.png){:width="640px"}
### Unified Canvas
See the [Unified Canvas Guide](UNIFIED_CANVAS.md)
## Parting remarks ## Parting remarks
This concludes the walkthrough, but there are several more features that you can This concludes the walkthrough, but there are several more features that you can
explore. Please check out the [Command Line Interface](CLI.md) documentation for explore. Please check out the [Command Line Interface](CLI.md) documentation for
further explanation of the advanced features that were not covered here. further explanation of the advanced features that were not covered here.
The WebGUI is only rapid development. Check back regularly for updates! The WebUI is only rapid development. Check back regularly for updates!
## Reference ## Reference

98
docs/index.md
View File

@ -100,81 +100,61 @@ images in full-precision mode:
- GTX 1650 series cards - GTX 1650 series cards
- GTX 1660 series cards - GTX 1660 series cards
### :fontawesome-solid-memory: Memory ### :fontawesome-solid-memory: Memory and Disk
- At least 12 GB Main Memory RAM. - At least 12 GB Main Memory RAM.
### :fontawesome-regular-hard-drive: Disk
- At least 18 GB of free disk space for the machine learning model, Python, and - At least 18 GB of free disk space for the machine learning model, Python, and
all its dependencies. all its dependencies.
!!! info
Precision is auto configured based on the device. If however you encounter errors like
`expected type Float but found Half` or `not implemented for Half` you can try starting
`invoke.py` with the `--precision=float32` flag:
```bash
(invokeai) ~/InvokeAI$ python scripts/invoke.py --precision=float32
```
## :octicons-package-dependencies-24: Installation ## :octicons-package-dependencies-24: Installation
This fork is supported across Linux, Windows and Macintosh. Linux users can use This fork is supported across Linux, Windows and Macintosh. Linux users can use
either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm either an Nvidia-based card (with CUDA support) or an AMD card (using the ROCm
driver). driver).
### Automated Installation ### [Installation Getting Started Guide](installation)
#### [Automated Installer](installation/010_INSTALL_AUTOMATED.md)
This method is recommended for 1st time users
First time users, please see [Automated #### [Manual Installation](installation/020_INSTALL_MANUAL.md)
Installer](installation/010_INSTALL_AUTOMATED.md) for a walkthrough of This method is recommended for experienced users and developers
getting InvokeAI up and running on your system. #### [Docker Installation](installation/040_INSTALL_DOCKER.md)
This method is recommended for those familiar with running Docker containers
### Manual Installation ### Other Installation Guides
- [PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md)
Power users who are comfortable with the command line can try the - [XFormers](installation/070_INSTALL_XFORMERS.md)
[Manual Installation](installation/020_INSTALL_MANUAL.md) method, which provides - [CUDA and ROCm Drivers](installation/030_INSTALL_CUDA_AND_ROCM.md)
more flexibility. This manual also describes how to start developing - [Installing New Models](installation/050_INSTALLING_MODELS.md)
with InvokeAI.
### Docker Installation
Another installation method is to run a Docker container containing
InvokeAI and its dependencies. This method is recommended for
individuals with experience with Docker containers and understand the
pluses and minuses of a container-based install.
### PyPatchMatch Library Installation
Linux and Mac users who wish to make use of the **PyPatchMatch** inpainting
optimization functions will need to perform a bit of extra work to enable this
module. Instructions can be found at [Installing
PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md).
## :octicons-gift-24: InvokeAI Features ## :octicons-gift-24: InvokeAI Features
- [The InvokeAI Web Interface](features/WEB.md) - ### The InvokeAI Web Interface
[WebGUI hotkey reference guide](features/WEBUIHOTKEYS.md) - - [WebUI overview](features/WEB.md)
[WebGUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md) - [WebUI hotkey reference guide](features/WEBUIHOTKEYS.md)
<!-- seperator --> - [WebUI Unified Canvas for Img2Img, inpainting and outpainting](features/UNIFIED_CANVAS.md)
- [The Command Line Interace](features/CLI.md) - <!-- separator -->
[Image2Image](features/IMG2IMG.md) - [Inpainting](features/INPAINTING.md) - ### The InvokeAI Command Line Interface
[Outpainting](features/OUTPAINTING.md) - - [Command Line Interace Reference Guide](features/CLI.md)
[Adding custom styles and subjects](features/CONCEPTS.md) - <!-- separator -->
[Upscaling and Face Reconstruction](features/POSTPROCESS.md) ### Image Management
<!-- seperator --> - [Image2Image](features/IMG2IMG.md)
- [Generating Variations](features/VARIATIONS.md) - [Inpainting](features/INPAINTING.md)
<!-- seperator --> - [Outpainting](features/OUTPAINTING.md)
- [Prompt Engineering](features/PROMPTS.md) - [Adding custom styles and subjects](features/CONCEPTS.md)
<!-- seperator --> - [Upscaling and Face Reconstruction](features/POSTPROCESS.md)
- [Embiggen upscaling](features/EMBIGGEN.md)
- [Other Features](features/OTHER.md)
<!-- separator -->
### Model Management
- [Installing](installation/050_INSTALLING_MODELS.md)
- [Model Merging](features/MODEL_MERGING.md) - [Model Merging](features/MODEL_MERGING.md)
- [Style/Subject Concepts and Embeddings](features/CONCEPTS.md)
- [Textual Inversion](features/TEXTUAL_INVERSION.md)
- [Not Safe for Work (NSFW) Checker](features/NSFW.md)
<!-- seperator --> <!-- seperator -->
- Miscellaneous ### Prompt Engineering
- [NSFW Checker](features/NSFW.md) - [Prompt Syntax](features/PROMPTS.md)
- [Embiggen upscaling](features/EMBIGGEN.md) - [Generating Variations](features/VARIATIONS.md)
- [Other](features/OTHER.md)
## :octicons-log-16: Latest Changes ## :octicons-log-16: Latest Changes

38
docs/installation/010_INSTALL_AUTOMATED.md
View File

@ -14,7 +14,7 @@ experimental versions later.
## Walk through ## Walk through
1. Make sure that your system meets the [hardware 1. <a name="hardware_requirements">**Hardware Requirements**: </a>Make sure that your system meets the [hardware
requirements](../index.md#hardware-requirements) and has the requirements](../index.md#hardware-requirements) and has the
appropriate GPU drivers installed. For a system with an NVIDIA appropriate GPU drivers installed. For a system with an NVIDIA
card installed, you will need to install the CUDA driver, while card installed, you will need to install the CUDA driver, while
@ -36,22 +36,22 @@ experimental versions later.
NOTE for Linux users: if your temporary directory is mounted NOTE for Linux users: if your temporary directory is mounted
as a `tmpfs`, ensure it has sufficient space. as a `tmpfs`, ensure it has sufficient space.
2. Check that your system has an up-to-date Python installed. To do 2. <a name="software_requirements">**Software Requirements**: </a>Check that your system has an up-to-date Python installed. To do
this, open up a command-line window ("Terminal" on Linux and this, open up a command-line window ("Terminal" on Linux and
Macintosh, "Command" or "Powershell" on Windows) and type `python Macintosh, "Command" or "Powershell" on Windows) and type `python
--version`. If Python is installed, it will print out the version --version`. If Python is installed, it will print out the version
number. If it is version `3.9.1` or `3.10.x`, you meet number. If it is version `3.9.1` or `3.10.x`, you meet
requirements. 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" !!! warning "What to do if you have an unsupported version"
Go to [Python Downloads](https://www.python.org/downloads/) and
download the appropriate installer package for your platform. We recommend
[Version 3.10.9](https://www.python.org/downloads/release/python-3109/),
which has been extensively tested with InvokeAI.
Go to [Python Downloads](https://www.python.org/downloads/)
and download the appropriate installer package for your
platform. We recommend [Version
3.10.9](https://www.python.org/downloads/release/python-3109/),
which has been extensively tested with InvokeAI. At this time
we do not recommend Python 3.11.
_Please select your platform in the section below for platform-specific _Please select your platform in the section below for platform-specific
setup requirements._ setup requirements._
@ -120,7 +120,7 @@ experimental versions later.
install. If you already have them installed, you will instead see some install. If you already have them installed, you will instead see some
output in the Terminal advising you that the tools are already installed. More information can be found at [FreeCode Camp](https://www.freecodecamp.org/news/install-xcode-command-line-tools/) output in the Terminal advising you that the tools are already installed. More information can be found at [FreeCode Camp](https://www.freecodecamp.org/news/install-xcode-command-line-tools/)
3. The InvokeAI installer is distributed as a ZIP files. Go to the 3. **Download the Installer**: The InvokeAI installer is distributed as a ZIP files. Go to the
[latest release](https://github.com/invoke-ai/InvokeAI/releases/latest), [latest release](https://github.com/invoke-ai/InvokeAI/releases/latest),
and look for a file named: and look for a file named:
@ -129,7 +129,7 @@ experimental versions later.
where "2.X.X" is the latest released version. The file is located where "2.X.X" is the latest released version. The file is located
at the very bottom of the release page, under **Assets**. at the very bottom of the release page, under **Assets**.
4. Unpack the zip file into a convenient directory. This will create a new 4. **Unpack the installer**: Unpack the zip file into a convenient directory. This will create a new
directory named "InvokeAI-Installer". When unpacked, the directory directory named "InvokeAI-Installer". When unpacked, the directory
will look like this: will look like this:
@ -137,7 +137,7 @@ experimental versions later.
![zipfile-screenshot](../assets/installer-walkthrough/unpacked-zipfile.png) ![zipfile-screenshot](../assets/installer-walkthrough/unpacked-zipfile.png)
</figure> </figure>
5. If you are using a desktop GUI, double-click the installer file 5. **Launch the installer script from the desktop**: If you are using a desktop GUI, double-click the installer file
appropriate for your platform. It will be named `install.bat` on appropriate for your platform. It will be named `install.bat` on
Windows systems and `install.sh` on Linux and Macintosh Windows systems and `install.sh` on Linux and Macintosh
systems. Be aware that your system's file browser may suppress the systems. Be aware that your system's file browser may suppress the
@ -146,14 +146,14 @@ experimental versions later.
On Windows systems if you get an "Untrusted Publisher" warning. On Windows systems if you get an "Untrusted Publisher" warning.
Click on "More Info" and then select "Run Anyway." You trust us, right? Click on "More Info" and then select "Run Anyway." You trust us, right?
6. Alternatively, from the command line, run the shell script or .bat file: 6. **[Alternative] Launch the installer script from the command line**: Alternatively, from the command line, run the shell script or .bat file:
```cmd ```cmd
C:\Documents\Linco> cd InvokeAI-Installer C:\Documents\Linco> cd InvokeAI-Installer
C:\Documents\Linco\invokeAI> install.bat C:\Documents\Linco\invokeAI> install.bat
``` ```
7. The script will ask you to choose where to install InvokeAI. Select a 7. **Select the location to install InvokeAI**: The script will ask you to choose where to install InvokeAI. Select a
directory with at least 18G of free space for a full install. InvokeAI and directory with at least 18G of free space for a full install. InvokeAI and
all its support files will be installed into a new directory named all its support files will be installed into a new directory named
`invokeai` located at the location you specify. `invokeai` located at the location you specify.
@ -171,7 +171,7 @@ experimental versions later.
Type part of the path (e.g. "C:\Users") and press ++tab++ repeatedly Type part of the path (e.g. "C:\Users") and press ++tab++ repeatedly
to suggest completions. to suggest completions.
8. The installer will autodetect your platform and will request you to 8. **Select your GPU**: The installer will autodetect your platform and will request you to
confirm the type of GPU your graphics card has. On Linux systems, confirm the type of GPU your graphics card has. On Linux systems,
you will have the choice of CUDA (NVidia cards), ROCm (AMD cards), you will have the choice of CUDA (NVidia cards), ROCm (AMD cards),
or CPU (no graphics acceleration). On Windows, you'll have the or CPU (no graphics acceleration). On Windows, you'll have the
@ -186,7 +186,7 @@ experimental versions later.
</figure> </figure>
9. Sit back and let the install script work. It will install the third-party 9. **Watch it go!**: Sit back and let the install script work. It will install the third-party
libraries needed by InvokeAI and the application itself. libraries needed by InvokeAI and the application itself.
Be aware that some of the library download and install steps take a long Be aware that some of the library download and install steps take a long
@ -197,7 +197,7 @@ experimental versions later.
minutes and nothing is happening, you can interrupt the script with ^C. You 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. may restart it and it will pick up where it left off.
10. After installation completes, the installer will launch the 10. **Post-install Configuration**: After installation completes, the installer will launch the
configuration script, which will guide you through the first-time configuration script, which will guide you through the first-time
process of selecting one or more Stable Diffusion model weights process of selecting one or more Stable Diffusion model weights
files, downloading and configuring them. We provide a list of files, downloading and configuring them. We provide a list of
@ -215,7 +215,7 @@ experimental versions later.
prompted) and configure InvokeAI to use the previously-downloaded files. The prompted) and configure InvokeAI to use the previously-downloaded files. The
process for this is described in [Installing Models](050_INSTALLING_MODELS.md). process for this is described in [Installing Models](050_INSTALLING_MODELS.md).
11. The script will now exit and you'll be ready to generate some images. Look 11. **Running InvokeAI for the first time**: The script will now exit and you'll be ready to generate some images. Look
for the directory `invokeai` installed in the location you chose at the for the directory `invokeai` installed in the location you chose at the
beginning of the install session. Look for a shell script named `invoke.sh` beginning of the install session. Look for a shell script named `invoke.sh`
(Linux/Mac) or `invoke.bat` (Windows). Launch the script by double-clicking (Linux/Mac) or `invoke.bat` (Windows). Launch the script by double-clicking
@ -236,7 +236,7 @@ experimental versions later.
http://localhost:9090. Click on this link to open up a browser http://localhost:9090. Click on this link to open up a browser
and start exploring InvokeAI's features. and start exploring InvokeAI's features.
12. You can launch InvokeAI with several different command-line arguments that 12. **InvokeAI Options**: You can launch InvokeAI with several different command-line arguments that
customize its behavior. For example, you can change the location of the customize its behavior. For example, you can change the location of the
image output directory, or select your favorite sampler. See the image output directory, or select your favorite sampler. See the
[Command-Line Interface](../features/CLI.md) for a full list of the options. [Command-Line Interface](../features/CLI.md) for a full list of the options.

18
docs/installation/index.md
View File

@ -3,7 +3,17 @@ title: Overview
--- ---
We offer several ways to install InvokeAI, each one suited to your We offer several ways to install InvokeAI, each one suited to your
experience and preferences. experience and preferences. We suggest that everyone start by
reviewing the
[hardware](010_INSTALL_AUTOMATED.md#hardware_requirements) and
[software](010_INSTALL_AUTOMATED.md#software_requirements)
requirements, as they are the same across each install method. Then
pick the install method most suitable to your level of experience and
needs.
See the [troubleshooting
section](010_INSTALL_AUTOMATED.md#troubleshooting) of the automated
install guide for frequently-encountered installation issues.
1. [Automated Installer](010_INSTALL_AUTOMATED.md) 1. [Automated Installer](010_INSTALL_AUTOMATED.md)
@ -33,3 +43,9 @@ experience and preferences.
InvokeAI and its dependencies. This method is recommended for InvokeAI and its dependencies. This method is recommended for
individuals with experience with Docker containers and understand individuals with experience with Docker containers and understand
the pluses and minuses of a container-based install. the pluses and minuses of a container-based install.
4. Other Installation Guides
- [PyPatchMatch](installation/060_INSTALL_PATCHMATCH.md)
- [XFormers](installation/070_INSTALL_XFORMERS.md)
- [CUDA and ROCm Drivers](installation/030_INSTALL_CUDA_AND_ROCM.md)
- [Installing New Models](installation/050_INSTALLING_MODELS.md)