updated LICENSE files and added information about watermarking

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

290
LICENSE-SDXL.txt Normal file
View File

@ -0,0 +1,290 @@
Copyright (c) 2023 Stability AI
CreativeML Open RAIL++-M License dated July 26, 2023
Section I: PREAMBLE
Multimodal generative models are being widely adopted and used, and
have the potential to transform the way artists, among other
individuals, conceive and benefit from AI or ML technologies as a tool
for content creation.
Notwithstanding the current and potential benefits that these
artifacts can bring to society at large, there are also concerns about
potential misuses of them, either due to their technical limitations
or ethical considerations.
In short, this license strives for both the open and responsible
downstream use of the accompanying model. When it comes to the open
character, we took inspiration from open source permissive licenses
regarding the grant of IP rights. Referring to the downstream
responsible use, we added use-based restrictions not permitting the
use of the model in very specific scenarios, in order for the licensor
to be able to enforce the license in case potential misuses of the
Model may occur. At the same time, we strive to promote open and
responsible research on generative models for art and content
generation.
Even though downstream derivative versions of the model could be
released under different licensing terms, the latter will always have
to include - at minimum - the same use-based restrictions as the ones
in the original license (this license). We believe in the intersection
between open and responsible AI development; thus, this agreement aims
to strike a balance between both in order to enable responsible
open-science in the field of AI.
This CreativeML Open RAIL++-M License governs the use of the model
(and its derivatives) and is informed by the model card associated
with the model.
NOW THEREFORE, You and Licensor agree as follows:
Definitions
"License" means the terms and conditions for use, reproduction, and
Distribution as defined in this document.
"Data" means a collection of information and/or content extracted from
the dataset used with the Model, including to train, pretrain, or
otherwise evaluate the Model. The Data is not licensed under this
License.
"Output" means the results of operating a Model as embodied in
informational content resulting therefrom.
"Model" means any accompanying machine-learning based assemblies
(including checkpoints), consisting of learnt weights, parameters
(including optimizer states), corresponding to the model architecture
as embodied in the Complementary Material, that have been trained or
tuned, in whole or in part on the Data, using the Complementary
Material.
"Derivatives of the Model" means all modifications to the Model, works
based on the Model, or any other model which is created or initialized
by transfer of patterns of the weights, parameters, activations or
output of the Model, to the other model, in order to cause the other
model to perform similarly to the Model, including - but not limited
to - distillation methods entailing the use of intermediate data
representations or methods based on the generation of synthetic data
by the Model for training the other model.
"Complementary Material" means the accompanying source code and
scripts used to define, run, load, benchmark or evaluate the Model,
and used to prepare data for training or evaluation, if any. This
includes any accompanying documentation, tutorials, examples, etc, if
any.
"Distribution" means any transmission, reproduction, publication or
other sharing of the Model or Derivatives of the Model to a third
party, including providing the Model as a hosted service made
available by electronic or other remote means - e.g. API-based or web
access.
"Licensor" means the copyright owner or entity authorized by the
copyright owner that is granting the License, including the persons or
entities that may have rights in the Model and/or distributing the
Model.
"You" (or "Your") means an individual or Legal Entity exercising
permissions granted by this License and/or making use of the Model for
whichever purpose and in any field of use, including usage of the
Model in an end-use application - e.g. chatbot, translator, image
generator.
"Third Parties" means individuals or legal entities that are not under
common control with Licensor or You.
"Contribution" means any work of authorship, including the original
version of the Model and any modifications or additions to that Model
or Derivatives of the Model thereof, that is intentionally submitted
to Licensor for inclusion in the Model by the copyright owner or by an
individual or Legal Entity authorized to submit on behalf of the
copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent to
the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control
systems, and issue tracking systems that are managed by, or on behalf
of, the Licensor for the purpose of discussing and improving the
Model, but excluding communication that is conspicuously marked or
otherwise designated in writing by the copyright owner as "Not a
Contribution."
"Contributor" means Licensor and any individual or Legal Entity on
behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Model.
Section II: INTELLECTUAL PROPERTY RIGHTS
Both copyright and patent grants apply to the Model, Derivatives of
the Model and Complementary Material. The Model and Derivatives of the
Model are subject to additional terms as described in
Section III.
Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare, publicly display, publicly
perform, sublicense, and distribute the Complementary Material, the
Model, and Derivatives of the Model.
Grant of Patent License. Subject to the terms and conditions of this
License and where and as applicable, each Contributor hereby grants to
You a perpetual, worldwide, non-exclusive, no-charge, royalty-free,
irrevocable (except as stated in this paragraph) patent license to
make, have made, use, offer to sell, sell, import, and otherwise
transfer the Model and the Complementary Material, where such license
applies only to those patent claims licensable by such Contributor
that are necessarily infringed by their Contribution(s) alone or by
combination of their Contribution(s) with the Model to which such
Contribution(s) was submitted. If You institute patent litigation
against any entity (including a cross-claim or counterclaim in a
lawsuit) alleging that the Model and/or Complementary Material or a
Contribution incorporated within the Model and/or Complementary
Material constitutes direct or contributory patent infringement, then
any patent licenses granted to You under this License for the Model
and/or Work shall terminate as of the date such litigation is asserted
or filed.
Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
Distribution and Redistribution. You may host for Third Party remote
access purposes (e.g. software-as-a-service), reproduce and distribute
copies of the Model or Derivatives of the Model thereof in any medium,
with or without modifications, provided that You meet the following
conditions: Use-based restrictions as referenced in paragraph 5 MUST
be included as an enforceable provision by You in any type of legal
agreement (e.g. a license) governing the use and/or distribution of
the Model or Derivatives of the Model, and You shall give notice to
subsequent users You Distribute to, that the Model or Derivatives of
the Model are subject to paragraph 5. This provision does not apply to
the use of Complementary Material. You must give any Third Party
recipients of the Model or Derivatives of the Model a copy of this
License; You must cause any modified files to carry prominent notices
stating that You changed the files; You must retain all copyright,
patent, trademark, and attribution notices excluding those notices
that do not pertain to any part of the Model, Derivatives of the
Model. You may add Your own copyright statement to Your modifications
and may provide additional or different license terms and conditions -
respecting paragraph 4.a. - for use, reproduction, or Distribution of
Your modifications, or for any such Derivatives of the Model as a
whole, provided Your use, reproduction, and Distribution of the Model
otherwise complies with the conditions stated in this License.
Use-based restrictions. The restrictions set forth in Attachment A are
considered Use-based restrictions. Therefore You cannot use the Model
and the Derivatives of the Model for the specified restricted
uses. You may use the Model subject to this License, including only
for lawful purposes and in accordance with the License. Use may
include creating any content with, finetuning, updating, running,
training, evaluating and/or reparametrizing the Model. You shall
require all of Your users who use the Model or a Derivative of the
Model to comply with the terms of this paragraph (paragraph 5).
The Output You Generate. Except as set forth herein, Licensor claims
no rights in the Output You generate using the Model. You are
accountable for the Output you generate and its subsequent uses. No
use of the output can contravene any provision as stated in the
License.
Section IV: OTHER PROVISIONS
Updates and Runtime Restrictions. To the maximum extent permitted by
law, Licensor reserves the right to restrict (remotely or otherwise)
usage of the Model in violation of this License.
Trademarks and related. Nothing in this License permits You to make
use of Licensors trademarks, trade names, logos or to otherwise
suggest endorsement or misrepresent the relationship between the
parties; and any rights not expressly granted herein are reserved by
the Licensors.
Disclaimer of Warranty. Unless required by applicable law or agreed to
in writing, Licensor provides the Model and the Complementary Material
(and each Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Model, Derivatives of
the Model, and the Complementary Material and assume any risks
associated with Your exercise of permissions under this License.
Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise, unless
required by applicable law (such as deliberate and grossly negligent
acts) or agreed to in writing, shall any Contributor be liable to You
for damages, including any direct, indirect, special, incidental, or
consequential damages of any character arising as a result of this
License or out of the use or inability to use the Model and the
Complementary Material (including but not limited to damages for loss
of goodwill, work stoppage, computer failure or malfunction, or any
and all other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
Accepting Warranty or Additional Liability. While redistributing the
Model, Derivatives of the Model and the Complementary Material
thereof, You may choose to offer, and charge a fee for, acceptance of
support, warranty, indemnity, or other liability obligations and/or
rights consistent with this License. However, in accepting such
obligations, You may act only on Your own behalf and on Your sole
responsibility, not on behalf of any other Contributor, and only if
You agree to indemnify, defend, and hold each Contributor harmless for
any liability incurred by, or claims asserted against, such
Contributor by reason of your accepting any such warranty or
additional liability.
If any provision of this License is held to be invalid, illegal or
unenforceable, the remaining provisions shall be unaffected thereby
and remain valid as if such provision had not been set forth herein.
END OF TERMS AND CONDITIONS
Attachment A
Use Restrictions
You agree not to use the Model or Derivatives of the Model:
* In any way that violates any applicable national, federal, state,
local or international law or regulation;
* For the purpose of exploiting, harming or attempting to exploit or
harm minors in any way;
* To generate or disseminate verifiably false information and/or
content with the purpose of harming others;
* To generate or disseminate personal identifiable information that
can be used to harm an individual;
* To defame, disparage or otherwise harass others;
* For fully automated decision making that adversely impacts an
individuals legal rights or otherwise creates or modifies a
binding, enforceable obligation;
* For any use intended to or which has the effect of discriminating
against or harming individuals or groups based on online or offline
social behavior or known or predicted personal or personality
characteristics;
* To exploit any of the vulnerabilities of a specific group of persons
based on their age, social, physical or mental characteristics, in
order to materially distort the behavior of a person pertaining to
that group in a manner that causes or is likely to cause that person
or another person physical or psychological harm;
* For any use intended to or which has the effect of discriminating
against individuals or groups based on legally protected
characteristics or categories;
* To provide medical advice and medical results interpretation;
* To generate or disseminate information for the purpose to be used
for administration of justice, law enforcement, immigration or
asylum processes, such as predicting an individual will commit
fraud/crime commitment (e.g. by text profiling, drawing causal
relationships between assertions made in documents, indiscriminate
and arbitrarily-targeted use).

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) |

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.

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)

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.

View File

@ -412,8 +412,9 @@ Use cursor arrows to make a checkbox selection, and space to toggle.
)
self.nextrely -= 1
label = """BY DOWNLOADING THE STABLE DIFFUSION WEIGHT FILES, YOU AGREE TO HAVE READ
AND ACCEPTED THE CREATIVEML RESPONSIBLE AI LICENSE LOCATED AT
https://huggingface.co/spaces/CompVis/stable-diffusion-license
AND ACCEPTED THE CREATIVEML RESPONSIBLE AI LICENSES LOCATED AT
https://huggingface.co/spaces/CompVis/stable-diffusion-license and
https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md
"""
for i in textwrap.wrap(label,width=window_width-6):
self.add_widget_intelligent(
@ -424,7 +425,7 @@ https://huggingface.co/spaces/CompVis/stable-diffusion-license
)
self.license_acceptance = self.add_widget_intelligent(
npyscreen.Checkbox,
name="I accept the CreativeML Responsible AI License",
name="I accept the CreativeML Responsible AI Licenses",
value=not first_time,
relx=2,
scroll_exit=True,