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

updated LICENSE files and added information about watermarking

Browse Source
This commit is contained in:
Lincoln Stein
2023-07-26 17:27:33 -04:00
parent 6a3a776f4e
commit 049645d66e
7 changed files with 351 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/features/CONFIGURATION.md
View File

@ -65,7 +65,6 @@ InvokeAI:
esrgan: true
internet_available: true
log_tokenization: false
nsfw_checker: false
patchmatch: true
restore: true
...
@ -138,7 +137,7 @@ command-line options by giving the `--help` argument:
(.venv) > invokeai-web --help
usage: InvokeAI [-h] [--host HOST] [--port PORT] [--allow_origins [ALLOW_ORIGINS ...]] [--allow_credentials | --no-allow_credentials] [--allow_methods [ALLOW_METHODS ...]]
[--allow_headers [ALLOW_HEADERS ...]] [--esrgan | --no-esrgan] [--internet_available | --no-internet_available] [--log_tokenization | --no-log_tokenization]
[--nsfw_checker | --no-nsfw_checker] [--invisible_watermark | --no-invisible_watermark] [--patchmatch | --no-patchmatch] [--restore | --no-restore]
[--patchmatch | --no-patchmatch] [--restore | --no-restore]
[--always_use_cpu | --no-always_use_cpu] [--free_gpu_mem | --no-free_gpu_mem] [--max_loaded_models MAX_LOADED_MODELS] [--max_cache_size MAX_CACHE_SIZE]
[--max_vram_cache_size MAX_VRAM_CACHE_SIZE] [--gpu_mem_reserved GPU_MEM_RESERVED] [--precision {auto,float16,float32,autocast}]
[--sequential_guidance | --no-sequential_guidance] [--xformers_enabled | --no-xformers_enabled] [--tiled_decode | --no-tiled_decode] [--root ROOT]
@ -175,8 +174,6 @@ These configuration settings allow you to enable and disable various InvokeAI fe
| `esrgan` | `true` | Activate the ESRGAN upscaling options|
| `internet_available` | `true` | When a resource is not available locally, try to fetch it via the internet |
| `log_tokenization` | `false` | Before each text2image generation, print a color-coded representation of the prompt to the console; this can help understand why a prompt is not working as expected |
| `nsfw_checker` | `true` | Activate the NSFW checker to blur out risque images |
| `invisible_watermark` | `true` | Write an invisible watermark 'InvokeAI' into generated images for use by AI image detectors |
| `patchmatch` | `true` | Activate the "patchmatch" algorithm for improved inpainting |
| `restore` | `true` | Activate the facial restoration features (DEPRECATED; restoration features will be removed in 3.0.0) |

69
docs/features/NSFW.md → docs/features/WATERMARK+NSFW.md
View File

@ -1,12 +1,40 @@
---
title: The NSFW Checker
title: Watermarking, NSFW Image Checking
---
# :material-image-off: NSFW Checker
# :material-image-off: Invisible Watermark and the NSFW Checker
## Watermarking
InvokeAI does not apply watermarking to images by default. However,
many computer scientists working in the field of generative AI worry
that a flood of computer-generated imagery will contaminate the image
data sets needed to train future generations of generative models.
InvokeAI offers an optional watermarking mode that writes a small bit
of text, **InvokeAI**, into each image that it generates using an
"invisible" watermarking library that spreads the information
throughout the image in a way that is not perceptible to the human
eye. If you are planning to share your generated images on
internet-accessible services, we encourage you to activate the
invisible watermark mode in order to help preserve the digital image
environment.
The downside of watermarking is that it increases the size of the
image moderately, and has been reported by some individuals to degrade
image quality. Your mileage may vary.
To read the watermark in an image, activate the InvokeAI virtual
environment (called the "developer's console" in the launcher) and run
the command:
```
invisible-watermark -a decode -t bytes -m dwtDct -l 64 /path/to/image.png
```
## The NSFW ("Safety") Checker
The Stable Diffusion image generation models will produce sexual
Stable Diffusion 1.5-based image generation models will produce sexual
imagery if deliberately prompted, and will occasionally produce such
images when this is not intended. Such images are colloquially known
as "Not Safe for Work" (NSFW). This behavior is due to the nature of
@ -18,35 +46,17 @@ jurisdictions it may be illegal to publicly distribute such imagery,
including mounting a publicly-available server that provides
unfiltered images to the public. Furthermore, the [Stable Diffusion
weights
License](https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE-ModelWeights.txt)
forbids the model from being used to "exploit any of the
License](https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE-SD1+SD2.txt),
and the [Stable Diffusion XL
License][https://github.com/invoke-ai/InvokeAI/blob/main/LICENSE-SDXL.txt]
both forbid the models from being used to "exploit any of the
vulnerabilities of a specific group of persons."
For these reasons Stable Diffusion offers a "safety checker," a
machine learning model trained to recognize potentially disturbing
imagery. When a potentially NSFW image is detected, the checker will
blur the image and paste a warning icon on top. The checker can be
turned on and off on the command line using `--nsfw_checker` and
`--no-nsfw_checker`.
At installation time, InvokeAI will ask whether the checker should be
activated by default (neither argument given on the command line). The
response is stored in the InvokeAI initialization file
(`invokeai.yaml` in the InvokeAI root directory). You can change the
default at any time by opening this file in a text editor and
changing the line `nsfw_checker:` from true to false or vice-versa:
```
...
Features:
esrgan: true
internet_available: true
log_tokenization: false
nsfw_checker: true
patchmatch: true
restore: true
```
turned on and off in the Web interface under Settings.
## Caveats
@ -84,10 +94,3 @@ are encouraged to turn **off** intermediate image rendering when you
are using the checker. Future versions of InvokeAI will apply
additional blurring to intermediate images when the checker is active.
### Watermarking
InvokeAI does not apply any sort of watermark to images it
generates. However, it does write metadata into the PNG data area,
including the prompt used to generate the image and relevant parameter
settings. These fields can be examined using the `sd-metadata.py`
script that comes with the InvokeAI package.

2
docs/index.md
View File

@ -148,7 +148,7 @@ images in full-precision mode:
- [Model Merging](features/MODEL_MERGING.md)
- [ControlNet Models](features/CONTROLNET.md)
- [Style/Subject Concepts and Embeddings](features/CONCEPTS.md)
- [Not Safe for Work (NSFW) Checker](features/NSFW.md)
- [Watermarking and the Not Safe for Work (NSFW) Checker](features/WATERMARK+NSFW.md)
<!-- seperator -->
### Prompt Engineering
- [Prompt Syntax](features/PROMPTS.md)

39
docs/installation/010_INSTALL_AUTOMATED.md
View File

@ -215,17 +215,6 @@ experimental versions later.
Generally the defaults are fine, and you can come back to this screen at
any time to tweak your system. Here are the options you can adjust:
- ***Output directory for images***
This is the path to a directory in which InvokeAI will store all its
generated images.
- ***NSFW checker***
If checked, InvokeAI will test images for potential sexual content
and blur them out if found. Note that the NSFW checker consumes
an additional 0.6 GB of VRAM on top of the 2-3 GB of VRAM used
by most image models. If you have a low VRAM GPU (4-6 GB), you
can reduce out of memory errors by disabling the checker.
- ***HuggingFace Access Token***
InvokeAI has the ability to download embedded styles and subjects
from the HuggingFace Concept Library on-demand. However, some of
@ -257,20 +246,30 @@ experimental versions later.
and graphics cards. The "autocast" option is deprecated and
shouldn't be used unless you are asked to by a member of the team.
- ***Number of models to cache in CPU memory***
- **Size of the RAM cache used for fast model switching***
This allows you to keep models in memory and switch rapidly among
them rather than having them load from disk each time. This slider
controls how many models to keep loaded at once. Each
model will use 2-4 GB of RAM, so use this cautiously
controls how many models to keep loaded at once. A typical SD-1 or SD-2 model
uses 2-3 GB of memory. A typical SDXL model uses 6-7 GB. Providing more
RAM will allow more models to be co-resident.
- ***Directory containing embedding/textual inversion files***
This is the directory in which you can place custom embedding
files (.pt or .bin). During startup, this directory will be
scanned and InvokeAI will print out the text terms that
are available to trigger the embeddings.
- ***Output directory for images***
This is the path to a directory in which InvokeAI will store all its
generated images.
- ***Autoimport Folder***
This is the directory in which you can place models you have
downloaded and wish to load into InvokeAI. You can place a variety
of models in this directory, including diffusers folders, .ckpt files,
.safetensors files, as well as LoRAs, ControlNet and Textual Inversion
files (both folder and file versions). To help organize this folder,
you can create several levels of subfolders and drop your models into
whichever ones you want.
- ***Autoimport FolderLICENSE***
At the bottom of the screen you will see a checkbox for accepting
the CreativeML Responsible AI License. You need to accept the license
the CreativeML Responsible AI Licenses. You need to accept the license
in order to download Stable Diffusion models from the next screen.
_You can come back to the startup options form_ as many times as you like.