OreX/forge-builds
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

initial commit

Browse Source
This commit is contained in:
Bacruru Sakaguchi
2025-10-21 13:37:07 +07:00
commit 9cd16e276a
1574 changed files with 2675557 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1085
CHANGELOG.md Executable file
View File

File diff suppressed because it is too large Load Diff

7
CITATION.cff Executable file
View File

@@ -0,0 +1,7 @@
cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- given-names: AUTOMATIC1111
title: "Stable Diffusion Web UI"
date-released: 2022-08-22
url: "https://github.com/AUTOMATIC1111/stable-diffusion-webui"

1
CODEOWNERS Executable file
View File

@@ -0,0 +1 @@
* @lllyasviel

688
LICENSE.txt Executable file
View File

@@ -0,0 +1,688 @@
GNU AFFERO GENERAL PUBLIC LICENSE
Version 3, 19 November 2007
Copyright (c) 2023 AUTOMATIC1111
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
Developers that use our General Public Licenses protect your rights
with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU Affero General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a "Source" link that leads users to an archive
of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
<https://www.gnu.org/licenses/>.
---------------------------------Facebook BNB-------------------------------
MIT License
Copyright (c) Facebook, Inc. and its affiliates.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

7
NEWS.md Executable file
View File

@@ -0,0 +1,7 @@
About Gradio 5: will try to upgrade to Gradio 5 at about 2025 March. If failed, then will try again on about 2025 June. relatively positive that we can have Gradio5 before next summer.
2024 Oct 28: A new branch `sd35` is contributed by [#2183](https://github.com/lllyasviel/stable-diffusion-webui-forge/pull/2183) . I will take a look at quants and sampling and transformer's clip-g vs that clip-g rewrite before merging to main ... (Oct 29: okay maybe medium also need to take a look later)
About Flux ControlNet (sync [here](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/932)): The rewrite of ControlNet Intergrated will ~start at about Sep 29~ (delayed) ~start at about Oct 15~ (delayed) ~start at about Oct 30~ (delayed) start at about Nov 20. (When this note is announced, the main targets include some diffusers formatted Flux ControlNets and some community implementation of Union ControlNets. However, this may be extended if stronger models come out after this note.)
2024 Sep 7: New sampler `Flux Realistic` is available now! Recommended scheduler is "simple".

213
README.md Executable file
View File

@@ -0,0 +1,213 @@
# Stable Diffusion WebUI Forge
Stable Diffusion WebUI Forge is a platform on top of [Stable Diffusion WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui) (based on [Gradio](https://www.gradio.app/) <a href='https://github.com/gradio-app/gradio'><img src='https://img.shields.io/github/stars/gradio-app/gradio'></a>) to make development easier, optimize resource management, speed up inference, and study experimental features.
The name "Forge" is inspired from "Minecraft Forge". This project is aimed at becoming SD WebUI's Forge.
Forge is currently based on SD-WebUI 1.10.1 at [this commit](https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/82a973c04367123ae98bd9abdf80d9eda9b910e2). (Because original SD-WebUI is almost static now, Forge will sync with original WebUI every 90 days, or when important fixes.)
News are moved to this link: [Click here to see the News section](https://github.com/lllyasviel/stable-diffusion-webui-forge/blob/main/NEWS.md)
# Quick List
[Gradio 4 UI Must Read (TLDR: You need to use RIGHT MOUSE BUTTON to move canvas!)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/853)
[Flux Tutorial (BitsandBytes Models, NF4, "GPU Weight", "Offload Location", "Offload Method", etc)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/981)
[Flux Tutorial 2 (Seperated Full Models, GGUF, Technically Correct Comparison between GGUF and NF4, etc)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1050)
[Forge Extension List and Extension Replacement List (Temporary)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1754)
[How to make LoRAs more precise on low-bit models; How to Skip" Patching LoRAs"; How to only load LoRA one time rather than each generation; How to report LoRAs that do not work](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1038)
[Report Flux Performance Problems (TLDR: DO NOT set "GPU Weight" too high! Lower "GPU Weight" solves 99% problems!)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1181)
[How to solve "Connection errored out" / "Press anykey to continue ..." / etc](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1474)
[(Save Flux BitsandBytes UNet/Checkpoint)](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1224#discussioncomment-10384104)
[LayerDiffuse Transparent Image Editing](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/854)
[Tell us what is missing in ControlNet Integrated](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/932)
[(Policy) Soft Advertisement Removal Policy](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/1286)
(Flux BNB NF4 / GGUF Q8_0/Q5_0/Q5_1/Q4_0/Q4_1 are all natively supported with GPU weight slider and Quene/Async Swap toggle and swap location toggle. All Flux BNB NF4 / GGUF Q8_0/Q5_0/Q4_0 have LoRA support.)
# Installing Forge
**Just use this one-click installation package (with git and python included).**
[>>> Click Here to Download One-Click Package (CUDA 12.1 + Pytorch 2.3.1) <<<](https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/download/latest/webui_forge_cu121_torch231.7z)
Some other CUDA/Torch Versions:
[Forge with CUDA 12.1 + Pytorch 2.3.1](https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/download/latest/webui_forge_cu121_torch231.7z) <- **Recommended**
[Forge with CUDA 12.4 + Pytorch 2.4](https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/download/latest/webui_forge_cu124_torch24.7z) <- **Fastest**, but MSVC may be broken, xformers may not work
[Forge with CUDA 12.1 + Pytorch 2.1](https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/download/latest/webui_forge_cu121_torch21.7z) <- the previously used old environments
After you download, you uncompress, use `update.bat` to update, and use `run.bat` to run.
Note that running `update.bat` is important, otherwise you may be using a previous version with potential bugs unfixed.
![image](https://github.com/lllyasviel/stable-diffusion-webui-forge/assets/19834515/c49bd60d-82bd-4086-9859-88d472582b94)
### Advanced Install
If you are proficient in Git and you want to install Forge as another branch of SD-WebUI, please see [here](https://github.com/continue-revolution/sd-webui-animatediff/blob/forge/master/docs/how-to-use.md#you-have-a1111-and-you-know-git). In this way, you can reuse all SD checkpoints and all extensions you installed previously in your OG SD-WebUI, but you should know what you are doing.
If you know what you are doing, you can also install Forge using same method as SD-WebUI. (Install Git, Python, Git Clone the forge repo `https://github.com/lllyasviel/stable-diffusion-webui-forge.git` and then run webui-user.bat).
### Previous Versions
You can download previous versions [here](https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/849).
# Forge Status
Based on manual test one-by-one:
| Component | Status | Last Test |
|-----------------------------------------------------|---------------------------------------------|--------------|
| Basic Diffusion | Normal | 2024 Aug 26 |
| GPU Memory Management System | Normal | 2024 Aug 26 |
| LoRAs | Normal | 2024 Aug 26 |
| All Preprocessors | Normal | 2024 Aug 26 |
| All ControlNets | Normal | 2024 Aug 26 |
| All IP-Adapters | Normal | 2024 Aug 26 |
| All Instant-IDs | Normal | 2024 July 27 |
| All Reference-only Methods | Normal | 2024 July 27 |
| All Integrated Extensions | Normal | 2024 July 27 |
| Popular Extensions (Adetailer, etc) | Normal | 2024 July 27 |
| Gradio 4 UIs | Normal | 2024 July 27 |
| Gradio 4 Forge Canvas | Normal | 2024 Aug 26 |
| LoRA/Checkpoint Selection UI for Gradio 4 | Normal | 2024 July 27 |
| Photopea/OpenposeEditor/etc for ControlNet | Normal | 2024 July 27 |
| Wacom 128 level touch pressure support for Canvas | Normal | 2024 July 15 |
| Microsoft Surface touch pressure support for Canvas | Broken, pending fix | 2024 July 29 |
| ControlNets (Union) | Not implemented yet, pending implementation | 2024 Aug 26 |
| ControlNets (Flux) | Not implemented yet, pending implementation | 2024 Aug 26 |
| API endpoints (txt2img, img2img, etc) | Normal, but pending improved Flux support | 2024 Aug 29 |
| OFT LoRAs | Broken, pending fix | 2024 Sep 9 |
Feel free to open issue if anything is broken and I will take a look every several days. If I do not update this "Forge Status" then it means I cannot reproduce any problem. In that case, fresh re-install should help most.
# UnetPatcher
Below are self-supported **single file** of all codes to implement FreeU V2.
See also `extension-builtin/sd_forge_freeu/scripts/forge_freeu.py`:
```python
import torch
import gradio as gr
from modules import scripts
def Fourier_filter(x, threshold, scale):
# FFT
x_freq = torch.fft.fftn(x.float(), dim=(-2, -1))
x_freq = torch.fft.fftshift(x_freq, dim=(-2, -1))
B, C, H, W = x_freq.shape
mask = torch.ones((B, C, H, W), device=x.device)
crow, ccol = H // 2, W // 2
mask[..., crow - threshold:crow + threshold, ccol - threshold:ccol + threshold] = scale
x_freq = x_freq * mask
# IFFT
x_freq = torch.fft.ifftshift(x_freq, dim=(-2, -1))
x_filtered = torch.fft.ifftn(x_freq, dim=(-2, -1)).real
return x_filtered.to(x.dtype)
def patch_freeu_v2(unet_patcher, b1, b2, s1, s2):
model_channels = unet_patcher.model.diffusion_model.config["model_channels"]
scale_dict = {model_channels * 4: (b1, s1), model_channels * 2: (b2, s2)}
on_cpu_devices = {}
def output_block_patch(h, hsp, transformer_options):
scale = scale_dict.get(h.shape[1], None)
if scale is not None:
hidden_mean = h.mean(1).unsqueeze(1)
B = hidden_mean.shape[0]
hidden_max, _ = torch.max(hidden_mean.view(B, -1), dim=-1, keepdim=True)
hidden_min, _ = torch.min(hidden_mean.view(B, -1), dim=-1, keepdim=True)
hidden_mean = (hidden_mean - hidden_min.unsqueeze(2).unsqueeze(3)) / (hidden_max - hidden_min).unsqueeze(2).unsqueeze(3)
h[:, :h.shape[1] // 2] = h[:, :h.shape[1] // 2] * ((scale[0] - 1) * hidden_mean + 1)
if hsp.device not in on_cpu_devices:
try:
hsp = Fourier_filter(hsp, threshold=1, scale=scale[1])
except:
print("Device", hsp.device, "does not support the torch.fft.")
on_cpu_devices[hsp.device] = True
hsp = Fourier_filter(hsp.cpu(), threshold=1, scale=scale[1]).to(hsp.device)
else:
hsp = Fourier_filter(hsp.cpu(), threshold=1, scale=scale[1]).to(hsp.device)
return h, hsp
m = unet_patcher.clone()
m.set_model_output_block_patch(output_block_patch)
return m
class FreeUForForge(scripts.Script):
sorting_priority = 12 # It will be the 12th item on UI.
def title(self):
return "FreeU Integrated"
def show(self, is_img2img):
# make this extension visible in both txt2img and img2img tab.
return scripts.AlwaysVisible
def ui(self, *args, **kwargs):
with gr.Accordion(open=False, label=self.title()):
freeu_enabled = gr.Checkbox(label='Enabled', value=False)
freeu_b1 = gr.Slider(label='B1', minimum=0, maximum=2, step=0.01, value=1.01)
freeu_b2 = gr.Slider(label='B2', minimum=0, maximum=2, step=0.01, value=1.02)
freeu_s1 = gr.Slider(label='S1', minimum=0, maximum=4, step=0.01, value=0.99)
freeu_s2 = gr.Slider(label='S2', minimum=0, maximum=4, step=0.01, value=0.95)
return freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2
def process_before_every_sampling(self, p, *script_args, **kwargs):
# This will be called before every sampling.
# If you use highres fix, this will be called twice.
freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2 = script_args
if not freeu_enabled:
return
unet = p.sd_model.forge_objects.unet
unet = patch_freeu_v2(unet, freeu_b1, freeu_b2, freeu_s1, freeu_s2)
p.sd_model.forge_objects.unet = unet
# Below codes will add some logs to the texts below the image outputs on UI.
# The extra_generation_params does not influence results.
p.extra_generation_params.update(dict(
freeu_enabled=freeu_enabled,
freeu_b1=freeu_b1,
freeu_b2=freeu_b2,
freeu_s1=freeu_s1,
freeu_s2=freeu_s2,
))
return
```
See also [Forge's Unet Implementation](https://github.com/lllyasviel/stable-diffusion-webui-forge/blob/main/backend/nn/unet.py).
# Under Construction
WebUI Forge is now under some constructions, and docs / UI / functionality may change with updates.

5
_typos.toml Executable file
View File

@@ -0,0 +1,5 @@
[default.extend-words]
# Part of "RGBa" (Pillow's pre-multiplied alpha RGB mode)
Ba = "Ba"
# HSA is something AMD uses for their GPUs
HSA = "HSA"

1
backend/README.md Executable file
View File

@@ -0,0 +1 @@
# WIP Backend for Forge

67
backend/args.py Executable file
View File

@@ -0,0 +1,67 @@
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("--gpu-device-id", type=int, default=None, metavar="DEVICE_ID")
fp_group = parser.add_mutually_exclusive_group()
fp_group.add_argument("--all-in-fp32", action="store_true")
fp_group.add_argument("--all-in-fp16", action="store_true")
fpunet_group = parser.add_mutually_exclusive_group()
fpunet_group.add_argument("--unet-in-bf16", action="store_true")
fpunet_group.add_argument("--unet-in-fp16", action="store_true")
fpunet_group.add_argument("--unet-in-fp8-e4m3fn", action="store_true")
fpunet_group.add_argument("--unet-in-fp8-e5m2", action="store_true")
fpvae_group = parser.add_mutually_exclusive_group()
fpvae_group.add_argument("--vae-in-fp16", action="store_true")
fpvae_group.add_argument("--vae-in-fp32", action="store_true")
fpvae_group.add_argument("--vae-in-bf16", action="store_true")
parser.add_argument("--vae-in-cpu", action="store_true")
fpte_group = parser.add_mutually_exclusive_group()
fpte_group.add_argument("--clip-in-fp8-e4m3fn", action="store_true")
fpte_group.add_argument("--clip-in-fp8-e5m2", action="store_true")
fpte_group.add_argument("--clip-in-fp16", action="store_true")
fpte_group.add_argument("--clip-in-fp32", action="store_true")
attn_group = parser.add_mutually_exclusive_group()
attn_group.add_argument("--attention-split", action="store_true")
attn_group.add_argument("--attention-quad", action="store_true")
attn_group.add_argument("--attention-pytorch", action="store_true")
upcast = parser.add_mutually_exclusive_group()
upcast.add_argument("--force-upcast-attention", action="store_true")
upcast.add_argument("--disable-attention-upcast", action="store_true")
parser.add_argument("--disable-xformers", action="store_true")
parser.add_argument("--directml", type=int, nargs="?", metavar="DIRECTML_DEVICE", const=-1)
parser.add_argument("--disable-ipex-hijack", action="store_true")
vram_group = parser.add_mutually_exclusive_group()
vram_group.add_argument("--always-gpu", action="store_true")
vram_group.add_argument("--always-high-vram", action="store_true")
vram_group.add_argument("--always-normal-vram", action="store_true")
vram_group.add_argument("--always-low-vram", action="store_true")
vram_group.add_argument("--always-no-vram", action="store_true")
vram_group.add_argument("--always-cpu", action="store_true")
parser.add_argument("--always-offload-from-vram", action="store_true")
parser.add_argument("--pytorch-deterministic", action="store_true")
parser.add_argument("--cuda-malloc", action="store_true")
parser.add_argument("--cuda-stream", action="store_true")
parser.add_argument("--pin-shared-memory", action="store_true")
parser.add_argument("--disable-gpu-warning", action="store_true")
args = parser.parse_known_args()[0]
# Some dynamic args that may be changed by webui rather than cmd flags.
dynamic_args = dict(
embedding_dir='./embeddings',
emphasis_name='original'
)

501
backend/attention.py Executable file
View File

@@ -0,0 +1,501 @@
import math
import torch
import einops
from backend.args import args
from backend import memory_management
from backend.misc.sub_quadratic_attention import efficient_dot_product_attention
BROKEN_XFORMERS = False
if memory_management.xformers_enabled():
import xformers
import xformers.ops
try:
x_vers = xformers.__version__
BROKEN_XFORMERS = x_vers.startswith("0.0.2") and not x_vers.startswith("0.0.20")
except:
pass
FORCE_UPCAST_ATTENTION_DTYPE = memory_management.force_upcast_attention_dtype()
def get_attn_precision(attn_precision=torch.float32):
if args.disable_attention_upcast:
return None
if FORCE_UPCAST_ATTENTION_DTYPE is not None:
return FORCE_UPCAST_ATTENTION_DTYPE
return attn_precision
def exists(val):
return val is not None
def attention_basic(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
attn_precision = get_attn_precision(attn_precision)
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
scale = dim_head ** -0.5
h = heads
if skip_reshape:
q, k, v = map(
lambda t: t.reshape(b * heads, -1, dim_head),
(q, k, v),
)
else:
q, k, v = map(
lambda t: t.unsqueeze(3)
.reshape(b, -1, heads, dim_head)
.permute(0, 2, 1, 3)
.reshape(b * heads, -1, dim_head)
.contiguous(),
(q, k, v),
)
if attn_precision == torch.float32:
sim = torch.einsum('b i d, b j d -> b i j', q.float(), k.float()) * scale
else:
sim = torch.einsum('b i d, b j d -> b i j', q, k) * scale
del q, k
if exists(mask):
if mask.dtype == torch.bool:
mask = einops.rearrange(mask, 'b ... -> b (...)')
max_neg_value = -torch.finfo(sim.dtype).max
mask = einops.repeat(mask, 'b j -> (b h) () j', h=h)
sim.masked_fill_(~mask, max_neg_value)
else:
if len(mask.shape) == 2:
bs = 1
else:
bs = mask.shape[0]
mask = mask.reshape(bs, -1, mask.shape[-2], mask.shape[-1]).expand(b, heads, -1, -1).reshape(-1, mask.shape[-2], mask.shape[-1])
sim.add_(mask)
sim = sim.softmax(dim=-1)
out = torch.einsum('b i j, b j d -> b i d', sim.to(v.dtype), v)
out = (
out.unsqueeze(0)
.reshape(b, heads, -1, dim_head)
.permute(0, 2, 1, 3)
.reshape(b, -1, heads * dim_head)
)
return out
def attention_sub_quad(query, key, value, heads, mask=None, attn_precision=None, skip_reshape=False):
attn_precision = get_attn_precision(attn_precision)
if skip_reshape:
b, _, _, dim_head = query.shape
else:
b, _, dim_head = query.shape
dim_head //= heads
scale = dim_head ** -0.5
if skip_reshape:
query = query.reshape(b * heads, -1, dim_head)
value = value.reshape(b * heads, -1, dim_head)
key = key.reshape(b * heads, -1, dim_head).movedim(1, 2)
else:
query = query.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head)
value = value.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 1, 3).reshape(b * heads, -1, dim_head)
key = key.unsqueeze(3).reshape(b, -1, heads, dim_head).permute(0, 2, 3, 1).reshape(b * heads, dim_head, -1)
dtype = query.dtype
upcast_attention = attn_precision == torch.float32 and query.dtype != torch.float32
if upcast_attention:
bytes_per_token = torch.finfo(torch.float32).bits // 8
else:
bytes_per_token = torch.finfo(query.dtype).bits // 8
batch_x_heads, q_tokens, _ = query.shape
_, _, k_tokens = key.shape
qk_matmul_size_bytes = batch_x_heads * bytes_per_token * q_tokens * k_tokens
mem_free_total, mem_free_torch = memory_management.get_free_memory(query.device, True)
kv_chunk_size_min = None
kv_chunk_size = None
query_chunk_size = None
for x in [4096, 2048, 1024, 512, 256]:
count = mem_free_total / (batch_x_heads * bytes_per_token * x * 4.0)
if count >= k_tokens:
kv_chunk_size = k_tokens
query_chunk_size = x
break
if query_chunk_size is None:
query_chunk_size = 512
if mask is not None:
if len(mask.shape) == 2:
bs = 1
else:
bs = mask.shape[0]
mask = mask.reshape(bs, -1, mask.shape[-2], mask.shape[-1]).expand(b, heads, -1, -1).reshape(-1, mask.shape[-2], mask.shape[-1])
hidden_states = efficient_dot_product_attention(
query,
key,
value,
query_chunk_size=query_chunk_size,
kv_chunk_size=kv_chunk_size,
kv_chunk_size_min=kv_chunk_size_min,
use_checkpoint=False,
upcast_attention=upcast_attention,
mask=mask,
)
hidden_states = hidden_states.to(dtype)
hidden_states = hidden_states.unflatten(0, (-1, heads)).transpose(1, 2).flatten(start_dim=2)
return hidden_states
def attention_split(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
attn_precision = get_attn_precision(attn_precision)
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
scale = dim_head ** -0.5
h = heads
if skip_reshape:
q, k, v = map(
lambda t: t.reshape(b * heads, -1, dim_head),
(q, k, v),
)
else:
q, k, v = map(
lambda t: t.unsqueeze(3)
.reshape(b, -1, heads, dim_head)
.permute(0, 2, 1, 3)
.reshape(b * heads, -1, dim_head)
.contiguous(),
(q, k, v),
)
r1 = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype)
mem_free_total = memory_management.get_free_memory(q.device)
if attn_precision == torch.float32:
element_size = 4
upcast = True
else:
element_size = q.element_size()
upcast = False
gb = 1024 ** 3
tensor_size = q.shape[0] * q.shape[1] * k.shape[1] * element_size
modifier = 3
mem_required = tensor_size * modifier
steps = 1
if mem_required > mem_free_total:
steps = 2 ** (math.ceil(math.log(mem_required / mem_free_total, 2)))
# print(f"Expected tensor size:{tensor_size/gb:0.1f}GB, cuda free:{mem_free_cuda/gb:0.1f}GB "
# f"torch free:{mem_free_torch/gb:0.1f} total:{mem_free_total/gb:0.1f} steps:{steps}")
if steps > 64:
max_res = math.floor(math.sqrt(math.sqrt(mem_free_total / 2.5)) / 8) * 64
raise RuntimeError(f'Not enough memory, use lower resolution (max approx. {max_res}x{max_res}). '
f'Need: {mem_required / 64 / gb:0.1f}GB free, Have:{mem_free_total / gb:0.1f}GB free')
if mask is not None:
if len(mask.shape) == 2:
bs = 1
else:
bs = mask.shape[0]
mask = mask.reshape(bs, -1, mask.shape[-2], mask.shape[-1]).expand(b, heads, -1, -1).reshape(-1, mask.shape[-2], mask.shape[-1])
# print("steps", steps, mem_required, mem_free_total, modifier, q.element_size(), tensor_size)
first_op_done = False
cleared_cache = False
while True:
try:
slice_size = q.shape[1] // steps if (q.shape[1] % steps) == 0 else q.shape[1]
for i in range(0, q.shape[1], slice_size):
end = i + slice_size
if upcast:
with torch.autocast(enabled=False, device_type='cuda'):
s1 = torch.einsum('b i d, b j d -> b i j', q[:, i:end].float(), k.float()) * scale
else:
s1 = torch.einsum('b i d, b j d -> b i j', q[:, i:end], k) * scale
if mask is not None:
if len(mask.shape) == 2:
s1 += mask[i:end]
else:
s1 += mask[:, i:end]
s2 = s1.softmax(dim=-1).to(v.dtype)
del s1
first_op_done = True
r1[:, i:end] = torch.einsum('b i j, b j d -> b i d', s2, v)
del s2
break
except memory_management.OOM_EXCEPTION as e:
if first_op_done == False:
memory_management.soft_empty_cache(True)
if cleared_cache == False:
cleared_cache = True
print("out of memory error, emptying cache and trying again")
continue
steps *= 2
if steps > 64:
raise e
print("out of memory error, increasing steps and trying again {}".format(steps))
else:
raise e
del q, k, v
r1 = (
r1.unsqueeze(0)
.reshape(b, heads, -1, dim_head)
.permute(0, 2, 1, 3)
.reshape(b, -1, heads * dim_head)
)
return r1
def attention_xformers(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
if BROKEN_XFORMERS and b * heads > 65535:
return attention_pytorch(q, k, v, heads, mask, skip_reshape=skip_reshape)
if skip_reshape:
q, k, v = map(
lambda t: t.reshape(b * heads, -1, dim_head),
(q, k, v),
)
else:
q, k, v = map(
lambda t: t.reshape(b, -1, heads, dim_head),
(q, k, v),
)
if mask is not None:
pad = 8 - q.shape[1] % 8
mask_out = torch.empty([q.shape[0], q.shape[1], q.shape[1] + pad], dtype=q.dtype, device=q.device)
mask_out[:, :, :mask.shape[-1]] = mask
mask = mask_out[:, :, :mask.shape[-1]]
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=mask)
if skip_reshape:
out = (
out.unsqueeze(0)
.reshape(b, heads, -1, dim_head)
.permute(0, 2, 1, 3)
.reshape(b, -1, heads * dim_head)
)
else:
out = (
out.reshape(b, -1, heads * dim_head)
)
return out
def attention_pytorch(q, k, v, heads, mask=None, attn_precision=None, skip_reshape=False):
if skip_reshape:
b, _, _, dim_head = q.shape
else:
b, _, dim_head = q.shape
dim_head //= heads
q, k, v = map(
lambda t: t.view(b, -1, heads, dim_head).transpose(1, 2),
(q, k, v),
)
out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False)
out = (
out.transpose(1, 2).reshape(b, -1, heads * dim_head)
)
return out
def slice_attention_single_head_spatial(q, k, v):
r1 = torch.zeros_like(k, device=q.device)
scale = (int(q.shape[-1]) ** (-0.5))
mem_free_total = memory_management.get_free_memory(q.device)
gb = 1024 ** 3
tensor_size = q.shape[0] * q.shape[1] * k.shape[2] * q.element_size()
modifier = 3 if q.element_size() == 2 else 2.5
mem_required = tensor_size * modifier
steps = 1
if mem_required > mem_free_total:
steps = 2 ** (math.ceil(math.log(mem_required / mem_free_total, 2)))
while True:
try:
slice_size = q.shape[1] // steps if (q.shape[1] % steps) == 0 else q.shape[1]
for i in range(0, q.shape[1], slice_size):
end = i + slice_size
s1 = torch.bmm(q[:, i:end], k) * scale
s2 = torch.nn.functional.softmax(s1, dim=2).permute(0, 2, 1)
del s1
r1[:, :, i:end] = torch.bmm(v, s2)
del s2
break
except memory_management.OOM_EXCEPTION as e:
memory_management.soft_empty_cache(True)
steps *= 2
if steps > 128:
raise e
print("out of memory error, increasing steps and trying again {}".format(steps))
return r1
def normal_attention_single_head_spatial(q, k, v):
# compute attention
b, c, h, w = q.shape
q = q.reshape(b, c, h * w)
q = q.permute(0, 2, 1) # b,hw,c
k = k.reshape(b, c, h * w) # b,c,hw
v = v.reshape(b, c, h * w)
r1 = slice_attention_single_head_spatial(q, k, v)
h_ = r1.reshape(b, c, h, w)
del r1
return h_
def xformers_attention_single_head_spatial(q, k, v):
# compute attention
B, C, H, W = q.shape
q, k, v = map(
lambda t: t.view(B, C, -1).transpose(1, 2).contiguous(),
(q, k, v),
)
try:
out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None)
out = out.transpose(1, 2).reshape(B, C, H, W)
except NotImplementedError as e:
out = slice_attention_single_head_spatial(q.view(B, -1, C), k.view(B, -1, C).transpose(1, 2),
v.view(B, -1, C).transpose(1, 2)).reshape(B, C, H, W)
return out
def pytorch_attention_single_head_spatial(q, k, v):
# compute attention
B, C, H, W = q.shape
q, k, v = map(
lambda t: t.view(B, 1, C, -1).transpose(2, 3).contiguous(),
(q, k, v),
)
try:
out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=0.0, is_causal=False)
out = out.transpose(2, 3).reshape(B, C, H, W)
except memory_management.OOM_EXCEPTION as e:
print("scaled_dot_product_attention OOMed: switched to slice attention")
out = slice_attention_single_head_spatial(q.view(B, -1, C), k.view(B, -1, C).transpose(1, 2),
v.view(B, -1, C).transpose(1, 2)).reshape(B, C, H, W)
return out
if memory_management.xformers_enabled():
print("Using xformers cross attention")
attention_function = attention_xformers
elif memory_management.pytorch_attention_enabled():
print("Using pytorch cross attention")
attention_function = attention_pytorch
elif args.attention_split:
print("Using split optimization for cross attention")
attention_function = attention_split
else:
print("Using sub quadratic optimization for cross attention")
attention_function = attention_sub_quad
if memory_management.xformers_enabled_vae():
print("Using xformers attention for VAE")
attention_function_single_head_spatial = xformers_attention_single_head_spatial
elif memory_management.pytorch_attention_enabled():
print("Using pytorch attention for VAE")
attention_function_single_head_spatial = pytorch_attention_single_head_spatial
else:
print("Using split attention for VAE")
attention_function_single_head_spatial = normal_attention_single_head_spatial
class AttentionProcessorForge:
def __call__(self, attn, hidden_states, encoder_hidden_states, attention_mask=None, temb=None, *args, **kwargs):
residual = hidden_states
if attn.spatial_norm is not None:
hidden_states = attn.spatial_norm(hidden_states, temb)
input_ndim = hidden_states.ndim
if input_ndim == 4:
batch_size, channel, height, width = hidden_states.shape
hidden_states = hidden_states.view(batch_size, channel, height * width).transpose(1, 2)
batch_size, sequence_length, _ = (
hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
)
if attention_mask is not None:
attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length, batch_size)
attention_mask = attention_mask.view(batch_size, attn.heads, -1, attention_mask.shape[-1])
if attn.group_norm is not None:
hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(1, 2)
query = attn.to_q(hidden_states)
if encoder_hidden_states is None:
encoder_hidden_states = hidden_states
elif attn.norm_cross:
encoder_hidden_states = attn.norm_encoder_hidden_states(encoder_hidden_states)
key = attn.to_k(encoder_hidden_states)
value = attn.to_v(encoder_hidden_states)
hidden_states = attention_function(query, key, value, heads=attn.heads, mask=attention_mask)
hidden_states = attn.to_out[0](hidden_states)
hidden_states = attn.to_out[1](hidden_states)
if input_ndim == 4:
hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
if attn.residual_connection:
hidden_states = hidden_states + residual
hidden_states = hidden_states / attn.rescale_output_factor
return hidden_states

87
backend/diffusion_engine/base.py Executable file
View File

@@ -0,0 +1,87 @@
import torch
import safetensors.torch as sf
from backend import utils
class ForgeObjects:
def __init__(self, unet, clip, vae, clipvision):
self.unet = unet
self.clip = clip
self.vae = vae
self.clipvision = clipvision
def shallow_copy(self):
return ForgeObjects(
self.unet,
self.clip,
self.vae,
self.clipvision
)
class ForgeDiffusionEngine:
matched_guesses = []
def __init__(self, estimated_config, huggingface_components):
self.model_config = estimated_config
self.is_inpaint = estimated_config.inpaint_model()
self.forge_objects = None
self.forge_objects_original = None
self.forge_objects_after_applying_lora = None
self.current_lora_hash = str([])
self.fix_for_webui_backward_compatibility()
def set_clip_skip(self, clip_skip):
pass
def get_first_stage_encoding(self, x):
return x # legacy code, do not change
def get_learned_conditioning(self, prompt: list[str]):
pass
def encode_first_stage(self, x):
pass
def decode_first_stage(self, x):
pass
def get_prompt_lengths_on_ui(self, prompt):
return 0, 75
def is_webui_legacy_model(self):
return self.is_sd1 or self.is_sd2 or self.is_sdxl or self.is_sd3
def fix_for_webui_backward_compatibility(self):
self.tiling_enabled = False
self.first_stage_model = None
self.cond_stage_model = None
self.use_distilled_cfg_scale = False
self.is_sd1 = False
self.is_sd2 = False
self.is_sdxl = False
self.is_sd3 = False
return
def save_unet(self, filename):
sd = utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model)
sf.save_file(sd, filename)
return filename
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='text_encoders.')
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='vae.')
)
sf.save_file(sd, filename)
return filename

114
backend/diffusion_engine/flux.py Executable file
View File

@@ -0,0 +1,114 @@
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.text_processing.t5_engine import T5TextProcessingEngine
from backend.args import dynamic_args
from backend.modules.k_prediction import PredictionFlux
from backend import memory_management
class Flux(ForgeDiffusionEngine):
matched_guesses = [model_list.Flux, model_list.FluxSchnell]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
self.is_inpaint = False
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder'],
't5xxl': huggingface_components['text_encoder_2']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer'],
't5xxl': huggingface_components['tokenizer_2']
}
)
vae = VAE(model=huggingface_components['vae'])
if 'schnell' in estimated_config.huggingface_repo.lower():
k_predictor = PredictionFlux(
mu=1.0
)
else:
k_predictor = PredictionFlux(
seq_len=4096,
base_seq_len=256,
max_seq_len=4096,
base_shift=0.5,
max_shift=1.15,
)
self.use_distilled_cfg_scale = True
unet = UnetPatcher.from_model(
model=huggingface_components['transformer'],
diffusers_scheduler=None,
k_predictor=k_predictor,
config=estimated_config
)
self.text_processing_engine_l = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=768,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=True,
final_layer_norm=True,
)
self.text_processing_engine_t5 = T5TextProcessingEngine(
text_encoder=clip.cond_stage_model.t5xxl,
tokenizer=clip.tokenizer.t5xxl,
emphasis_name=dynamic_args['emphasis_name'],
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
def set_clip_skip(self, clip_skip):
self.text_processing_engine_l.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond_l, pooled_l = self.text_processing_engine_l(prompt)
cond_t5 = self.text_processing_engine_t5(prompt)
cond = dict(crossattn=cond_t5, vector=pooled_l)
if self.use_distilled_cfg_scale:
distilled_cfg_scale = getattr(prompt, 'distilled_cfg_scale', 3.5) or 3.5
cond['guidance'] = torch.FloatTensor([distilled_cfg_scale] * len(prompt))
print(f'Distilled CFG Scale: {distilled_cfg_scale}')
else:
print('Distilled CFG Scale will be ignored for Schnell')
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
token_count = len(self.text_processing_engine_t5.tokenize([prompt])[0])
return token_count, max(255, token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)

100
backend/diffusion_engine/sd15.py Executable file
View File

@@ -0,0 +1,100 @@
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
import safetensors.torch as sf
from backend import utils
class StableDiffusion(ForgeDiffusionEngine):
matched_guesses = [model_list.SD15]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer']
}
)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['unet'],
diffusers_scheduler=huggingface_components['scheduler'],
config=estimated_config
)
self.text_processing_engine = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=768,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=False,
final_layer_norm=True,
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sd1 = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond = self.text_processing_engine(prompt)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
_, token_count = self.text_processing_engine.process_texts([prompt])
return token_count, self.text_processing_engine.get_target_prompt_token_count(token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
model_list.SD15.process_clip_state_dict_for_saving(self,
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='')
)
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='first_stage_model.')
)
sf.save_file(sd, filename)
return filename

100
backend/diffusion_engine/sd20.py Executable file
View File

@@ -0,0 +1,100 @@
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
import safetensors.torch as sf
from backend import utils
class StableDiffusion2(ForgeDiffusionEngine):
matched_guesses = [model_list.SD20]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
clip = CLIP(
model_dict={
'clip_h': huggingface_components['text_encoder']
},
tokenizer_dict={
'clip_h': huggingface_components['tokenizer']
}
)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['unet'],
diffusers_scheduler=huggingface_components['scheduler'],
config=estimated_config
)
self.text_processing_engine = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_h,
tokenizer=clip.tokenizer.clip_h,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_h',
embedding_expected_shape=1024,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=False,
final_layer_norm=True,
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sd2 = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond = self.text_processing_engine(prompt)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
_, token_count = self.text_processing_engine.process_texts([prompt])
return token_count, self.text_processing_engine.get_target_prompt_token_count(token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
model_list.SD20.process_clip_state_dict_for_saving(self,
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='')
)
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='first_stage_model.')
)
sf.save_file(sd, filename)
return filename

149
backend/diffusion_engine/sd35.py Executable file
View File

@@ -0,0 +1,149 @@
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.text_processing.t5_engine import T5TextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
from backend.modules.k_prediction import PredictionDiscreteFlow
from modules.shared import opts
## patch SD3 Class in huggingface_guess.model_list
def SD3_clip_target(self, state_dict={}):
return {'clip_l': 'text_encoder', 'clip_g': 'text_encoder_2', 't5xxl': 'text_encoder_3'}
model_list.SD3.unet_target = 'transformer'
model_list.SD3.clip_target = SD3_clip_target
## end patch
class StableDiffusion3(ForgeDiffusionEngine):
matched_guesses = [model_list.SD3]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
self.is_inpaint = False
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder'],
'clip_g': huggingface_components['text_encoder_2'],
't5xxl' : huggingface_components['text_encoder_3']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer'],
'clip_g': huggingface_components['tokenizer_2'],
't5xxl' : huggingface_components['tokenizer_3']
}
)
k_predictor = PredictionDiscreteFlow(shift=3.0)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['transformer'],
diffusers_scheduler= None,
k_predictor=k_predictor,
config=estimated_config
)
self.text_processing_engine_l = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=768,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=True,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=True,
final_layer_norm=False,
)
self.text_processing_engine_g = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_g,
tokenizer=clip.tokenizer.clip_g,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_g',
embedding_expected_shape=1280,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=True,
minimal_clip_skip=1,
clip_skip=1,
return_pooled=True,
final_layer_norm=False,
)
self.text_processing_engine_t5 = T5TextProcessingEngine(
text_encoder=clip.cond_stage_model.t5xxl,
tokenizer=clip.tokenizer.t5xxl,
emphasis_name=dynamic_args['emphasis_name'],
)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sd3 = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine_l.clip_skip = clip_skip
self.text_processing_engine_g.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond_g, g_pooled = self.text_processing_engine_g(prompt)
cond_l, l_pooled = self.text_processing_engine_l(prompt)
if opts.sd3_enable_t5:
cond_t5 = self.text_processing_engine_t5(prompt)
else:
cond_t5 = torch.zeros([len(prompt), 256, 4096]).to(cond_l.device)
is_negative_prompt = getattr(prompt, 'is_negative_prompt', False)
force_zero_negative_prompt = is_negative_prompt and all(x == '' for x in prompt)
if force_zero_negative_prompt:
l_pooled = torch.zeros_like(l_pooled)
g_pooled = torch.zeros_like(g_pooled)
cond_l = torch.zeros_like(cond_l)
cond_g = torch.zeros_like(cond_g)
cond_t5 = torch.zeros_like(cond_t5)
cond_lg = torch.cat([cond_l, cond_g], dim=-1)
cond_lg = torch.nn.functional.pad(cond_lg, (0, 4096 - cond_lg.shape[-1]))
cond = dict(
crossattn=torch.cat([cond_lg, cond_t5], dim=-2),
vector=torch.cat([l_pooled, g_pooled], dim=-1),
)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
token_count = len(self.text_processing_engine_t5.tokenize([prompt])[0])
return token_count, max(255, token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)

272
backend/diffusion_engine/sdxl.py Executable file
View File

@@ -0,0 +1,272 @@
import torch
from huggingface_guess import model_list
from backend.diffusion_engine.base import ForgeDiffusionEngine, ForgeObjects
from backend.patcher.clip import CLIP
from backend.patcher.vae import VAE
from backend.patcher.unet import UnetPatcher
from backend.text_processing.classic_engine import ClassicTextProcessingEngine
from backend.args import dynamic_args
from backend import memory_management
from backend.nn.unet import Timestep
import safetensors.torch as sf
from backend import utils
from modules.shared import opts
class StableDiffusionXL(ForgeDiffusionEngine):
matched_guesses = [model_list.SDXL]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
clip = CLIP(
model_dict={
'clip_l': huggingface_components['text_encoder'],
'clip_g': huggingface_components['text_encoder_2']
},
tokenizer_dict={
'clip_l': huggingface_components['tokenizer'],
'clip_g': huggingface_components['tokenizer_2']
}
)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['unet'],
diffusers_scheduler=huggingface_components['scheduler'],
config=estimated_config
)
self.text_processing_engine_l = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_l,
tokenizer=clip.tokenizer.clip_l,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_l',
embedding_expected_shape=2048,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=False,
minimal_clip_skip=2,
clip_skip=2,
return_pooled=False,
final_layer_norm=False,
)
self.text_processing_engine_g = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_g,
tokenizer=clip.tokenizer.clip_g,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_g',
embedding_expected_shape=2048,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=True,
minimal_clip_skip=2,
clip_skip=2,
return_pooled=True,
final_layer_norm=False,
)
self.embedder = Timestep(256)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sdxl = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine_l.clip_skip = clip_skip
self.text_processing_engine_g.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond_l = self.text_processing_engine_l(prompt)
cond_g, clip_pooled = self.text_processing_engine_g(prompt)
width = getattr(prompt, 'width', 1024) or 1024
height = getattr(prompt, 'height', 1024) or 1024
is_negative_prompt = getattr(prompt, 'is_negative_prompt', False)
crop_w = opts.sdxl_crop_left
crop_h = opts.sdxl_crop_top
target_width = width
target_height = height
out = [
self.embedder(torch.Tensor([height])), self.embedder(torch.Tensor([width])),
self.embedder(torch.Tensor([crop_h])), self.embedder(torch.Tensor([crop_w])),
self.embedder(torch.Tensor([target_height])), self.embedder(torch.Tensor([target_width]))
]
flat = torch.flatten(torch.cat(out)).unsqueeze(dim=0).repeat(clip_pooled.shape[0], 1).to(clip_pooled)
force_zero_negative_prompt = is_negative_prompt and all(x == '' for x in prompt)
if force_zero_negative_prompt:
clip_pooled = torch.zeros_like(clip_pooled)
cond_l = torch.zeros_like(cond_l)
cond_g = torch.zeros_like(cond_g)
cond = dict(
crossattn=torch.cat([cond_l, cond_g], dim=2),
vector=torch.cat([clip_pooled, flat], dim=1),
)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
_, token_count = self.text_processing_engine_l.process_texts([prompt])
return token_count, self.text_processing_engine_l.get_target_prompt_token_count(token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
model_list.SDXL.process_clip_state_dict_for_saving(self,
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='')
)
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='first_stage_model.')
)
sf.save_file(sd, filename)
return filename
class StableDiffusionXLRefiner(ForgeDiffusionEngine):
matched_guesses = [model_list.SDXLRefiner]
def __init__(self, estimated_config, huggingface_components):
super().__init__(estimated_config, huggingface_components)
clip = CLIP(
model_dict={
'clip_g': huggingface_components['text_encoder']
},
tokenizer_dict={
'clip_g': huggingface_components['tokenizer'],
}
)
vae = VAE(model=huggingface_components['vae'])
unet = UnetPatcher.from_model(
model=huggingface_components['unet'],
diffusers_scheduler=huggingface_components['scheduler'],
config=estimated_config
)
self.text_processing_engine_g = ClassicTextProcessingEngine(
text_encoder=clip.cond_stage_model.clip_g,
tokenizer=clip.tokenizer.clip_g,
embedding_dir=dynamic_args['embedding_dir'],
embedding_key='clip_g',
embedding_expected_shape=2048,
emphasis_name=dynamic_args['emphasis_name'],
text_projection=True,
minimal_clip_skip=2,
clip_skip=2,
return_pooled=True,
final_layer_norm=False,
)
self.embedder = Timestep(256)
self.forge_objects = ForgeObjects(unet=unet, clip=clip, vae=vae, clipvision=None)
self.forge_objects_original = self.forge_objects.shallow_copy()
self.forge_objects_after_applying_lora = self.forge_objects.shallow_copy()
# WebUI Legacy
self.is_sdxl = True
def set_clip_skip(self, clip_skip):
self.text_processing_engine_g.clip_skip = clip_skip
@torch.inference_mode()
def get_learned_conditioning(self, prompt: list[str]):
memory_management.load_model_gpu(self.forge_objects.clip.patcher)
cond_g, clip_pooled = self.text_processing_engine_g(prompt)
width = getattr(prompt, 'width', 1024) or 1024
height = getattr(prompt, 'height', 1024) or 1024
is_negative_prompt = getattr(prompt, 'is_negative_prompt', False)
crop_w = opts.sdxl_crop_left
crop_h = opts.sdxl_crop_top
aesthetic = opts.sdxl_refiner_low_aesthetic_score if is_negative_prompt else opts.sdxl_refiner_high_aesthetic_score
out = [
self.embedder(torch.Tensor([height])), self.embedder(torch.Tensor([width])),
self.embedder(torch.Tensor([crop_h])), self.embedder(torch.Tensor([crop_w])),
self.embedder(torch.Tensor([aesthetic]))
]
flat = torch.flatten(torch.cat(out)).unsqueeze(dim=0).repeat(clip_pooled.shape[0], 1).to(clip_pooled)
force_zero_negative_prompt = is_negative_prompt and all(x == '' for x in prompt)
if force_zero_negative_prompt:
clip_pooled = torch.zeros_like(clip_pooled)
cond_g = torch.zeros_like(cond_g)
cond = dict(
crossattn=cond_g,
vector=torch.cat([clip_pooled, flat], dim=1),
)
return cond
@torch.inference_mode()
def get_prompt_lengths_on_ui(self, prompt):
_, token_count = self.text_processing_engine_g.process_texts([prompt])
return token_count, self.text_processing_engine_g.get_target_prompt_token_count(token_count)
@torch.inference_mode()
def encode_first_stage(self, x):
sample = self.forge_objects.vae.encode(x.movedim(1, -1) * 0.5 + 0.5)
sample = self.forge_objects.vae.first_stage_model.process_in(sample)
return sample.to(x)
@torch.inference_mode()
def decode_first_stage(self, x):
sample = self.forge_objects.vae.first_stage_model.process_out(x)
sample = self.forge_objects.vae.decode(sample).movedim(-1, 1) * 2.0 - 1.0
return sample.to(x)
def save_checkpoint(self, filename):
sd = {}
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.unet.model.diffusion_model, prefix='model.diffusion_model.')
)
sd.update(
model_list.SDXLRefiner.process_clip_state_dict_for_saving(self,
utils.get_state_dict_after_quant(self.forge_objects.clip.cond_stage_model, prefix='')
)
)
sd.update(
utils.get_state_dict_after_quant(self.forge_objects.vae.first_stage_model, prefix='first_stage_model.')
)
sf.save_file(sd, filename)
return filename

25
backend/huggingface/Kwai-Kolors/Kolors/model_index.json Executable file
View File

@@ -0,0 +1,25 @@
{
"_class_name": "StableDiffusionXLPipeline",
"_diffusers_version": "0.18.0.dev0",
"force_zeros_for_empty_prompt": true,
"scheduler": [
"diffusers",
"EulerDiscreteScheduler"
],
"text_encoder": [
"kolors",
"ChatGLMModel"
],
"tokenizer": [
"kolors",
"ChatGLMTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

22
backend/huggingface/Kwai-Kolors/Kolors/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,22 @@
{
"_class_name": "EulerDiscreteScheduler",
"_diffusers_version": "0.18.0.dev0",
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"beta_end": 0.014,
"clip_sample": false,
"clip_sample_range": 1.0,
"dynamic_thresholding_ratio": 0.995,
"interpolation_type": "linear",
"num_train_timesteps": 1100,
"prediction_type": "epsilon",
"rescale_betas_zero_snr": false,
"sample_max_value": 1.0,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"thresholding": false,
"timestep_spacing": "leading",
"trained_betas": null,
"use_karras_sigmas": false
}

42
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/config.json Executable file
View File

@@ -0,0 +1,42 @@
{
"_name_or_path": "THUDM/chatglm3-6b-base",
"model_type": "chatglm",
"architectures": [
"ChatGLMModel"
],
"auto_map": {
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
"AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
},
"add_bias_linear": false,
"add_qkv_bias": true,
"apply_query_key_layer_scaling": true,
"apply_residual_connection_post_layernorm": false,
"attention_dropout": 0.0,
"attention_softmax_in_fp32": true,
"bias_dropout_fusion": true,
"ffn_hidden_size": 13696,
"fp32_residual_connection": false,
"hidden_dropout": 0.0,
"hidden_size": 4096,
"kv_channels": 128,
"layernorm_epsilon": 1e-05,
"multi_query_attention": true,
"multi_query_group_num": 2,
"num_attention_heads": 32,
"num_layers": 28,
"original_rope": true,
"padded_vocab_size": 65024,
"post_layer_norm": true,
"rmsnorm": true,
"seq_length": 32768,
"use_cache": true,
"torch_dtype": "float16",
"transformers_version": "4.30.2",
"tie_word_embeddings": false,
"eos_token_id": 2,
"pad_token_id": 0
}

207
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/pytorch_model.bin.index.json Executable file
View File

@@ -0,0 +1,207 @@
{
"metadata": {
"total_size": 12487168064
},
"weight_map": {
"transformer.embedding.word_embeddings.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.final_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.10.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.11.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.12.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.13.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.14.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.15.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.16.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.self_attention.dense.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.self_attention.query_key_value.bias": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.17.self_attention.query_key_value.weight": "pytorch_model-00004-of-00007.bin",
"transformer.encoder.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.18.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.19.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.20.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.self_attention.dense.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.self_attention.query_key_value.bias": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.21.self_attention.query_key_value.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
"transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.22.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.23.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.24.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.25.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.self_attention.dense.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.self_attention.query_key_value.bias": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.26.self_attention.query_key_value.weight": "pytorch_model-00006-of-00007.bin",
"transformer.encoder.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.self_attention.dense.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.self_attention.query_key_value.bias": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.27.self_attention.query_key_value.weight": "pytorch_model-00007-of-00007.bin",
"transformer.encoder.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.self_attention.dense.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00007.bin",
"transformer.encoder.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.5.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.6.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.self_attention.dense.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.self_attention.query_key_value.bias": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
"transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.self_attention.dense.weight": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.self_attention.query_key_value.bias": "pytorch_model-00003-of-00007.bin",
"transformer.encoder.layers.9.self_attention.query_key_value.weight": "pytorch_model-00003-of-00007.bin",
"transformer.output_layer.weight": "pytorch_model-00007-of-00007.bin",
"transformer.rotary_pos_emb.inv_freq": "pytorch_model-00001-of-00007.bin"
}
}

12
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/tokenizer_config.json Executable file
View File

@@ -0,0 +1,12 @@
{
"name_or_path": "THUDM/chatglm3-6b-base",
"remove_space": false,
"do_lower_case": false,
"tokenizer_class": "ChatGLMTokenizer",
"auto_map": {
"AutoTokenizer": [
"tokenization_chatglm.ChatGLMTokenizer",
null
]
}
}

BIN
backend/huggingface/Kwai-Kolors/Kolors/text_encoder/vocab.txt Executable file
View File

Binary file not shown.

12
backend/huggingface/Kwai-Kolors/Kolors/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,12 @@
{
"name_or_path": "THUDM/chatglm3-6b-base",
"remove_space": false,
"do_lower_case": false,
"tokenizer_class": "ChatGLMTokenizer",
"auto_map": {
"AutoTokenizer": [
"tokenization_chatglm.ChatGLMTokenizer",
null
]
}
}

BIN
backend/huggingface/Kwai-Kolors/Kolors/tokenizer/vocab.txt Executable file
View File

Binary file not shown.

72
backend/huggingface/Kwai-Kolors/Kolors/unet/config.json Executable file
View File

@@ -0,0 +1,72 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.27.0.dev0",
"act_fn": "silu",
"addition_embed_type": "text_time",
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": 256,
"attention_head_dim": [
5,
10,
20
],
"attention_type": "default",
"block_out_channels": [
320,
640,
1280
],
"center_input_sample": false,
"class_embed_type": null,
"class_embeddings_concat": false,
"conv_in_kernel": 3,
"conv_out_kernel": 3,
"cross_attention_dim": 2048,
"cross_attention_norm": null,
"down_block_types": [
"DownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D"
],
"downsample_padding": 1,
"dropout": 0.0,
"dual_cross_attention": false,
"encoder_hid_dim": 4096,
"encoder_hid_dim_type": "text_proj",
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_only_cross_attention": null,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"out_channels": 4,
"projection_class_embeddings_input_dim": 5632,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"reverse_transformer_layers_per_block": null,
"sample_size": 128,
"time_cond_proj_dim": null,
"time_embedding_act_fn": null,
"time_embedding_dim": null,
"time_embedding_type": "positional",
"timestep_post_act": null,
"transformer_layers_per_block": [
1,
2,
10
],
"up_block_types": [
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"UpBlock2D"
],
"upcast_attention": false,
"use_linear_projection": true
}

31
backend/huggingface/Kwai-Kolors/Kolors/vae/config.json Executable file
View File

@@ -0,0 +1,31 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.18.0.dev0",
"_name_or_path": "./vae",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.13025,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}

41
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/model_index.json Executable file
View File

@@ -0,0 +1,41 @@
{
"_class_name": "HunyuanDiTPipeline",
"_diffusers_version": "0.29.0.dev0",
"feature_extractor": [
null,
null
],
"requires_safety_checker": true,
"safety_checker": [
null,
null
],
"scheduler": [
"diffusers",
"DDPMScheduler"
],
"text_encoder": [
"transformers",
"BertModel"
],
"text_encoder_2": [
"transformers",
"T5EncoderModel"
],
"tokenizer": [
"transformers",
"BertTokenizer"
],
"tokenizer_2": [
"transformers",
"T5Tokenizer"
],
"transformer": [
"diffusers",
"HunyuanDiT2DModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

21
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,21 @@
{
"_class_name": "DDPMScheduler",
"_diffusers_version": "0.29.0.dev0",
"beta_end": 0.03,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"clip_sample_range": 1.0,
"dynamic_thresholding_ratio": 0.995,
"num_train_timesteps": 1000,
"prediction_type": "v_prediction",
"rescale_betas_zero_snr": false,
"sample_max_value": 1.0,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"thresholding": false,
"timestep_spacing": "leading",
"trained_betas": null,
"variance_type": "fixed_small"
}

33
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder/config.json Executable file
View File

@@ -0,0 +1,33 @@
{
"architectures": [
"BertModel"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"directionality": "bidi",
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"output_past": true,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.41.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 47020
}

32
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder_2/config.json Executable file
View File

@@ -0,0 +1,32 @@
{
"architectures": [
"T5EncoderModel"
],
"classifier_dropout": 0.0,
"d_ff": 5120,
"d_kv": 64,
"d_model": 2048,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 24,
"num_heads": 32,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"tokenizer_class": "T5Tokenizer",
"torch_dtype": "float32",
"transformers_version": "4.41.1",
"use_cache": true,
"vocab_size": 250112
}

226
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/text_encoder_2/model.safetensors.index.json Executable file
View File

@@ -0,0 +1,226 @@
{
"metadata": {
"total_size": 6679834624
},
"weight_map": {
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
"shared.weight": "model-00001-of-00002.safetensors"
}
}

37
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/special_tokens_map.json Executable file
View File

@@ -0,0 +1,37 @@
{
"cls_token": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"sep_token": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

57
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,57 @@
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 77,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}

47020
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer/vocab.txt Executable file
View File

File diff suppressed because it is too large Load Diff

23
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer_2/special_tokens_map.json Executable file
View File

@@ -0,0 +1,23 @@
{
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

39
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/tokenizer_2/tokenizer_config.json Executable file
View File

@@ -0,0 +1,39 @@
{
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 0,
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}

20
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/transformer/config.json Executable file
View File

@@ -0,0 +1,20 @@
{
"_class_name": "HunyuanDiT2DModel",
"_diffusers_version": "0.29.0.dev0",
"activation_fn": "gelu-approximate",
"attention_head_dim": 88,
"cross_attention_dim": 1024,
"cross_attention_dim_t5": 2048,
"hidden_size": 1408,
"in_channels": 4,
"learn_sigma": true,
"mlp_ratio": 4.3637,
"norm_type": "layer_norm",
"num_attention_heads": 16,
"num_layers": 40,
"patch_size": 2,
"pooled_projection_dim": 1024,
"sample_size": 128,
"text_len": 77,
"text_len_t5": 256
}

33
backend/huggingface/Tencent-Hunyuan/HunyuanDiT-Diffusers/vae/config.json Executable file
View File

@@ -0,0 +1,33 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.29.0.dev0",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": false,
"in_channels": 3,
"latent_channels": 4,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 512,
"scaling_factor": 0.13025,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}

32
backend/huggingface/black-forest-labs/FLUX.1-dev/model_index.json Executable file
View File

@@ -0,0 +1,32 @@
{
"_class_name": "FluxPipeline",
"_diffusers_version": "0.30.0.dev0",
"scheduler": [
"diffusers",
"FlowMatchEulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"T5EncoderModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"T5TokenizerFast"
],
"transformer": [
"diffusers",
"FluxTransformer2DModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

11
backend/huggingface/black-forest-labs/FLUX.1-dev/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,11 @@
{
"_class_name": "FlowMatchEulerDiscreteScheduler",
"_diffusers_version": "0.30.0.dev0",
"base_image_seq_len": 256,
"base_shift": 0.5,
"max_image_seq_len": 4096,
"max_shift": 1.15,
"num_train_timesteps": 1000,
"shift": 3.0,
"use_dynamic_shifting": true
}

25
backend/huggingface/black-forest-labs/FLUX.1-dev/text_encoder/config.json Executable file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "openai/clip-vit-large-patch14",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.3",
"vocab_size": 49408
}

22
backend/huggingface/black-forest-labs/FLUX.1-dev/text_encoder_2/config.json Executable file
View File

@@ -0,0 +1,22 @@
{
"d_ff": 10240,
"d_kv": 64,
"d_model": 4096,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"dense_act_fn": "gelu_pytorch_tanh",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 24,
"num_heads": 64,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"vocab_size": 32128
}

226
backend/huggingface/black-forest-labs/FLUX.1-dev/text_encoder_2/model.safetensors.index.json Executable file
View File

@@ -0,0 +1,226 @@
{
"metadata": {
"total_size": 9524621312
},
"weight_map": {
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
"shared.weight": "model-00001-of-00002.safetensors"
}
}

48895
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/special_tokens_map.json Executable file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

30
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

49410
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

125
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer_2/special_tokens_map.json Executable file
View File

@@ -0,0 +1,125 @@
{
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

129428
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer_2/tokenizer.json Executable file
View File

File diff suppressed because one or more lines are too long

939
backend/huggingface/black-forest-labs/FLUX.1-dev/tokenizer_2/tokenizer_config.json Executable file
View File

@@ -0,0 +1,939 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<extra_id_99>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<extra_id_98>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "<extra_id_97>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "<extra_id_96>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32004": {
"content": "<extra_id_95>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32005": {
"content": "<extra_id_94>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32006": {
"content": "<extra_id_93>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32007": {
"content": "<extra_id_92>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32008": {
"content": "<extra_id_91>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32009": {
"content": "<extra_id_90>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32010": {
"content": "<extra_id_89>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32011": {
"content": "<extra_id_88>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32012": {
"content": "<extra_id_87>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32013": {
"content": "<extra_id_86>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32014": {
"content": "<extra_id_85>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32015": {
"content": "<extra_id_84>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32016": {
"content": "<extra_id_83>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32017": {
"content": "<extra_id_82>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32018": {
"content": "<extra_id_81>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32019": {
"content": "<extra_id_80>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32020": {
"content": "<extra_id_79>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32021": {
"content": "<extra_id_78>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32022": {
"content": "<extra_id_77>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32023": {
"content": "<extra_id_76>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32024": {
"content": "<extra_id_75>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32025": {
"content": "<extra_id_74>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32026": {
"content": "<extra_id_73>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32027": {
"content": "<extra_id_72>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32028": {
"content": "<extra_id_71>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32029": {
"content": "<extra_id_70>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32030": {
"content": "<extra_id_69>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32031": {
"content": "<extra_id_68>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32032": {
"content": "<extra_id_67>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32033": {
"content": "<extra_id_66>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32034": {
"content": "<extra_id_65>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32035": {
"content": "<extra_id_64>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32036": {
"content": "<extra_id_63>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32037": {
"content": "<extra_id_62>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32038": {
"content": "<extra_id_61>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32039": {
"content": "<extra_id_60>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32040": {
"content": "<extra_id_59>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32041": {
"content": "<extra_id_58>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32042": {
"content": "<extra_id_57>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32043": {
"content": "<extra_id_56>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32044": {
"content": "<extra_id_55>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32045": {
"content": "<extra_id_54>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32046": {
"content": "<extra_id_53>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32047": {
"content": "<extra_id_52>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32048": {
"content": "<extra_id_51>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32049": {
"content": "<extra_id_50>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32050": {
"content": "<extra_id_49>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32051": {
"content": "<extra_id_48>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32052": {
"content": "<extra_id_47>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32053": {
"content": "<extra_id_46>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32054": {
"content": "<extra_id_45>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32055": {
"content": "<extra_id_44>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32056": {
"content": "<extra_id_43>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32057": {
"content": "<extra_id_42>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32058": {
"content": "<extra_id_41>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32059": {
"content": "<extra_id_40>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32060": {
"content": "<extra_id_39>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32061": {
"content": "<extra_id_38>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32062": {
"content": "<extra_id_37>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32063": {
"content": "<extra_id_36>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32064": {
"content": "<extra_id_35>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32065": {
"content": "<extra_id_34>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32066": {
"content": "<extra_id_33>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32067": {
"content": "<extra_id_32>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32068": {
"content": "<extra_id_31>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32069": {
"content": "<extra_id_30>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32070": {
"content": "<extra_id_29>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32071": {
"content": "<extra_id_28>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32072": {
"content": "<extra_id_27>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32073": {
"content": "<extra_id_26>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32074": {
"content": "<extra_id_25>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32075": {
"content": "<extra_id_24>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32076": {
"content": "<extra_id_23>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32077": {
"content": "<extra_id_22>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32078": {
"content": "<extra_id_21>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32079": {
"content": "<extra_id_20>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32080": {
"content": "<extra_id_19>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32081": {
"content": "<extra_id_18>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32082": {
"content": "<extra_id_17>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32083": {
"content": "<extra_id_16>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32084": {
"content": "<extra_id_15>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32085": {
"content": "<extra_id_14>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32086": {
"content": "<extra_id_13>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32087": {
"content": "<extra_id_12>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32088": {
"content": "<extra_id_11>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32089": {
"content": "<extra_id_10>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32090": {
"content": "<extra_id_9>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32091": {
"content": "<extra_id_8>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32092": {
"content": "<extra_id_7>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32093": {
"content": "<extra_id_6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32094": {
"content": "<extra_id_5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32095": {
"content": "<extra_id_4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32096": {
"content": "<extra_id_3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32097": {
"content": "<extra_id_2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32098": {
"content": "<extra_id_1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32099": {
"content": "<extra_id_0>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 100,
"legacy": false,
"model_max_length": 512,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}

14
backend/huggingface/black-forest-labs/FLUX.1-dev/transformer/config.json Executable file
View File

@@ -0,0 +1,14 @@
{
"_class_name": "FluxTransformer2DModel",
"_diffusers_version": "0.30.0.dev0",
"_name_or_path": "../checkpoints/flux-dev/transformer",
"attention_head_dim": 128,
"guidance_embeds": true,
"in_channels": 64,
"joint_attention_dim": 4096,
"num_attention_heads": 24,
"num_layers": 19,
"num_single_layers": 38,
"patch_size": 1,
"pooled_projection_dim": 768
}

1167
backend/huggingface/black-forest-labs/FLUX.1-dev/transformer/diffusion_pytorch_model.safetensors.index.json Executable file
View File

File diff suppressed because it is too large Load Diff

38
backend/huggingface/black-forest-labs/FLUX.1-dev/vae/config.json Executable file
View File

@@ -0,0 +1,38 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.30.0.dev0",
"_name_or_path": "../checkpoints/flux-dev",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}

32
backend/huggingface/black-forest-labs/FLUX.1-schnell/model_index.json Executable file
View File

@@ -0,0 +1,32 @@
{
"_class_name": "FluxPipeline",
"_diffusers_version": "0.30.0.dev0",
"scheduler": [
"diffusers",
"FlowMatchEulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"T5EncoderModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"T5TokenizerFast"
],
"transformer": [
"diffusers",
"FluxTransformer2DModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

11
backend/huggingface/black-forest-labs/FLUX.1-schnell/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,11 @@
{
"_class_name": "FlowMatchEulerDiscreteScheduler",
"_diffusers_version": "0.30.0.dev0",
"base_image_seq_len": 256,
"base_shift": 0.5,
"max_image_seq_len": 4096,
"max_shift": 1.15,
"num_train_timesteps": 1000,
"shift": 1.0,
"use_dynamic_shifting": false
}

25
backend/huggingface/black-forest-labs/FLUX.1-schnell/text_encoder/config.json Executable file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "openai/clip-vit-large-patch14",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.3",
"vocab_size": 49408
}

22
backend/huggingface/black-forest-labs/FLUX.1-schnell/text_encoder_2/config.json Executable file
View File

@@ -0,0 +1,22 @@
{
"d_ff": 10240,
"d_kv": 64,
"d_model": 4096,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"dense_act_fn": "gelu_pytorch_tanh",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 24,
"num_heads": 64,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"vocab_size": 32128
}

226
backend/huggingface/black-forest-labs/FLUX.1-schnell/text_encoder_2/model.safetensors.index.json Executable file
View File

@@ -0,0 +1,226 @@
{
"metadata": {
"total_size": 9524621312
},
"weight_map": {
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
"encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
"encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
"encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
"shared.weight": "model-00001-of-00002.safetensors"
}
}

48895
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/special_tokens_map.json Executable file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

30
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

49410
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

125
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer_2/special_tokens_map.json Executable file
View File

@@ -0,0 +1,125 @@
{
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

129428
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer_2/tokenizer.json Executable file
View File

File diff suppressed because one or more lines are too long

939
backend/huggingface/black-forest-labs/FLUX.1-schnell/tokenizer_2/tokenizer_config.json Executable file
View File

@@ -0,0 +1,939 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<extra_id_99>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<extra_id_98>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "<extra_id_97>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "<extra_id_96>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32004": {
"content": "<extra_id_95>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32005": {
"content": "<extra_id_94>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32006": {
"content": "<extra_id_93>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32007": {
"content": "<extra_id_92>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32008": {
"content": "<extra_id_91>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32009": {
"content": "<extra_id_90>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32010": {
"content": "<extra_id_89>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32011": {
"content": "<extra_id_88>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32012": {
"content": "<extra_id_87>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32013": {
"content": "<extra_id_86>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32014": {
"content": "<extra_id_85>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32015": {
"content": "<extra_id_84>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32016": {
"content": "<extra_id_83>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32017": {
"content": "<extra_id_82>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32018": {
"content": "<extra_id_81>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32019": {
"content": "<extra_id_80>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32020": {
"content": "<extra_id_79>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32021": {
"content": "<extra_id_78>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32022": {
"content": "<extra_id_77>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32023": {
"content": "<extra_id_76>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32024": {
"content": "<extra_id_75>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32025": {
"content": "<extra_id_74>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32026": {
"content": "<extra_id_73>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32027": {
"content": "<extra_id_72>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32028": {
"content": "<extra_id_71>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32029": {
"content": "<extra_id_70>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32030": {
"content": "<extra_id_69>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32031": {
"content": "<extra_id_68>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32032": {
"content": "<extra_id_67>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32033": {
"content": "<extra_id_66>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32034": {
"content": "<extra_id_65>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32035": {
"content": "<extra_id_64>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32036": {
"content": "<extra_id_63>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32037": {
"content": "<extra_id_62>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32038": {
"content": "<extra_id_61>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32039": {
"content": "<extra_id_60>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32040": {
"content": "<extra_id_59>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32041": {
"content": "<extra_id_58>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32042": {
"content": "<extra_id_57>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32043": {
"content": "<extra_id_56>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32044": {
"content": "<extra_id_55>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32045": {
"content": "<extra_id_54>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32046": {
"content": "<extra_id_53>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32047": {
"content": "<extra_id_52>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32048": {
"content": "<extra_id_51>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32049": {
"content": "<extra_id_50>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32050": {
"content": "<extra_id_49>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32051": {
"content": "<extra_id_48>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32052": {
"content": "<extra_id_47>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32053": {
"content": "<extra_id_46>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32054": {
"content": "<extra_id_45>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32055": {
"content": "<extra_id_44>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32056": {
"content": "<extra_id_43>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32057": {
"content": "<extra_id_42>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32058": {
"content": "<extra_id_41>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32059": {
"content": "<extra_id_40>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32060": {
"content": "<extra_id_39>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32061": {
"content": "<extra_id_38>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32062": {
"content": "<extra_id_37>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32063": {
"content": "<extra_id_36>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32064": {
"content": "<extra_id_35>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32065": {
"content": "<extra_id_34>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32066": {
"content": "<extra_id_33>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32067": {
"content": "<extra_id_32>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32068": {
"content": "<extra_id_31>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32069": {
"content": "<extra_id_30>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32070": {
"content": "<extra_id_29>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32071": {
"content": "<extra_id_28>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32072": {
"content": "<extra_id_27>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32073": {
"content": "<extra_id_26>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32074": {
"content": "<extra_id_25>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32075": {
"content": "<extra_id_24>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32076": {
"content": "<extra_id_23>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32077": {
"content": "<extra_id_22>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32078": {
"content": "<extra_id_21>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32079": {
"content": "<extra_id_20>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32080": {
"content": "<extra_id_19>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32081": {
"content": "<extra_id_18>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32082": {
"content": "<extra_id_17>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32083": {
"content": "<extra_id_16>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32084": {
"content": "<extra_id_15>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32085": {
"content": "<extra_id_14>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32086": {
"content": "<extra_id_13>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32087": {
"content": "<extra_id_12>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32088": {
"content": "<extra_id_11>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32089": {
"content": "<extra_id_10>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32090": {
"content": "<extra_id_9>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32091": {
"content": "<extra_id_8>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32092": {
"content": "<extra_id_7>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32093": {
"content": "<extra_id_6>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32094": {
"content": "<extra_id_5>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32095": {
"content": "<extra_id_4>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32096": {
"content": "<extra_id_3>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32097": {
"content": "<extra_id_2>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32098": {
"content": "<extra_id_1>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32099": {
"content": "<extra_id_0>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 100,
"legacy": false,
"model_max_length": 512,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}

13
backend/huggingface/black-forest-labs/FLUX.1-schnell/transformer/config.json Executable file
View File

@@ -0,0 +1,13 @@
{
"_class_name": "FluxTransformer2DModel",
"_diffusers_version": "0.30.0.dev0",
"attention_head_dim": 128,
"guidance_embeds": false,
"in_channels": 64,
"joint_attention_dim": 4096,
"num_attention_heads": 24,
"num_layers": 19,
"num_single_layers": 38,
"patch_size": 1,
"pooled_projection_dim": 768
}

1163
backend/huggingface/black-forest-labs/FLUX.1-schnell/transformer/diffusion_pytorch_model.safetensors.index.json Executable file
View File

File diff suppressed because it is too large Load Diff

38
backend/huggingface/black-forest-labs/FLUX.1-schnell/vae/config.json Executable file
View File

@@ -0,0 +1,38 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.30.0.dev0",
"_name_or_path": "../checkpoints/flux-dev",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 16,
"latents_mean": null,
"latents_std": null,
"layers_per_block": 2,
"mid_block_add_attention": true,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"scaling_factor": 0.3611,
"shift_factor": 0.1159,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"use_post_quant_conv": false,
"use_quant_conv": false
}

35
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/model_index.json Executable file
View File

@@ -0,0 +1,35 @@
{
"_class_name": "StableDiffusionXLInpaintPipeline",
"_diffusers_version": "0.21.0.dev0",
"_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
"force_zeros_for_empty_prompt": true,
"requires_aesthetics_score": false,
"scheduler": [
"diffusers",
"EulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"CLIPTextModelWithProjection"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

18
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,18 @@
{
"_class_name": "EulerDiscreteScheduler",
"_diffusers_version": "0.21.0.dev0",
"beta_end": 0.012,
"beta_schedule": "scaled_linear",
"beta_start": 0.00085,
"clip_sample": false,
"interpolation_type": "linear",
"num_train_timesteps": 1000,
"prediction_type": "epsilon",
"sample_max_value": 1.0,
"set_alpha_to_one": false,
"skip_prk_steps": true,
"steps_offset": 1,
"timestep_spacing": "leading",
"trained_betas": null,
"use_karras_sigmas": false
}

25
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/text_encoder/config.json Executable file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/text_encoder",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "float16",
"transformers_version": "4.29.2",
"vocab_size": 49408
}

25
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/text_encoder_2/config.json Executable file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "/home/suraj_huggingface_co/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/bf714989e22c57ddc1c453bf74dab4521acb81d8/text_encoder_2",
"architectures": [
"CLIPTextModelWithProjection"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_size": 1280,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 5120,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"pad_token_id": 1,
"projection_dim": 1280,
"torch_dtype": "float16",
"transformers_version": "4.29.2",
"vocab_size": 49408
}

48895
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/special_tokens_map.json Executable file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "<|endoftext|>",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

33
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,33 @@
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

49410
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

48895
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/special_tokens_map.json Executable file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "!",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

33
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/tokenizer_config.json Executable file
View File

@@ -0,0 +1,33 @@
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"model_max_length": 77,
"pad_token": "!",
"tokenizer_class": "CLIPTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

49410
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tokenizer_2/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

78
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/unet/config.json Executable file
View File

@@ -0,0 +1,78 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.21.0.dev0",
"_name_or_path": "valhalla/sdxl-inpaint-ema",
"act_fn": "silu",
"addition_embed_type": "text_time",
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": 256,
"attention_head_dim": [
5,
10,
20
],
"attention_type": "default",
"block_out_channels": [
320,
640,
1280
],
"center_input_sample": false,
"class_embed_type": null,
"class_embeddings_concat": false,
"conv_in_kernel": 3,
"conv_out_kernel": 3,
"cross_attention_dim": 2048,
"cross_attention_norm": null,
"decay": 0.9999,
"down_block_types": [
"DownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D"
],
"downsample_padding": 1,
"dual_cross_attention": false,
"encoder_hid_dim": null,
"encoder_hid_dim_type": null,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 9,
"inv_gamma": 1.0,
"layers_per_block": 2,
"mid_block_only_cross_attention": null,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"min_decay": 0.0,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"optimization_step": 37000,
"out_channels": 4,
"power": 0.6666666666666666,
"projection_class_embeddings_input_dim": 2816,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"sample_size": 128,
"time_cond_proj_dim": null,
"time_embedding_act_fn": null,
"time_embedding_dim": null,
"time_embedding_type": "positional",
"timestep_post_act": null,
"transformer_layers_per_block": [
1,
2,
10
],
"up_block_types": [
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"UpBlock2D"
],
"upcast_attention": null,
"update_after_step": 0,
"use_ema_warmup": false,
"use_linear_projection": true
}

32
backend/huggingface/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/vae/config.json Executable file
View File

@@ -0,0 +1,32 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.21.0.dev0",
"_name_or_path": "madebyollin/sdxl-vae-fp16-fix",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": false,
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 512,
"scaling_factor": 0.13025,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
]
}

42
backend/huggingface/lllyasviel/control_v11p_sd15_canny/config.json Executable file
View File

@@ -0,0 +1,42 @@
{
"_class_name": "ControlNetModel",
"_diffusers_version": "0.16.0.dev0",
"_name_or_path": "/home/patrick/controlnet_v1_1/control_v11p_sd15_canny",
"act_fn": "silu",
"attention_head_dim": 8,
"block_out_channels": [
320,
640,
1280,
1280
],
"class_embed_type": null,
"conditioning_embedding_out_channels": [
16,
32,
96,
256
],
"controlnet_conditioning_channel_order": "rgb",
"cross_attention_dim": 768,
"down_block_types": [
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D"
],
"downsample_padding": 1,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_scale_factor": 1,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_class_embeds": null,
"only_cross_attention": false,
"projection_class_embeddings_input_dim": null,
"resnet_time_scale_shift": "default",
"upcast_attention": false,
"use_linear_projection": false
}

41
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/model_index.json Executable file
View File

@@ -0,0 +1,41 @@
{
"_class_name": "StableDiffusionXLPipeline",
"_diffusers_version": "0.27.0.dev0",
"feature_extractor": [
null,
null
],
"force_zeros_for_empty_prompt": true,
"image_encoder": [
null,
null
],
"scheduler": [
"diffusers",
"EDMDPMSolverMultistepScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"text_encoder_2": [
"transformers",
"CLIPTextModelWithProjection"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"tokenizer_2": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

19
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/scheduler/scheduler_config.json Executable file
View File

@@ -0,0 +1,19 @@
{
"_class_name": "EDMDPMSolverMultistepScheduler",
"_diffusers_version": "0.27.0.dev0",
"algorithm_type": "dpmsolver++",
"dynamic_thresholding_ratio": 0.995,
"euler_at_final": false,
"final_sigmas_type": "zero",
"lower_order_final": true,
"num_train_timesteps": 1000,
"prediction_type": "epsilon",
"rho": 7.0,
"sample_max_value": 1.0,
"sigma_data": 0.5,
"sigma_max": 80.0,
"sigma_min": 0.002,
"solver_order": 2,
"solver_type": "midpoint",
"thresholding": false
}

24
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/text_encoder/config.json Executable file
View File

@@ -0,0 +1,24 @@
{
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"vocab_size": 49408
}

24
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/text_encoder_2/config.json Executable file
View File

@@ -0,0 +1,24 @@
{
"architectures": [
"CLIPTextModelWithProjection"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_size": 1280,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 5120,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 20,
"num_hidden_layers": 32,
"pad_token_id": 1,
"projection_dim": 1280,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"vocab_size": 49408
}

48895
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

30
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/special_tokens_map.json Executable file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

30
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/tokenizer_config.json Executable file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "<|endoftext|>",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

49410
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

48895
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/merges.txt Executable file
View File

File diff suppressed because it is too large Load Diff

24
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/special_tokens_map.json Executable file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "!",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

38
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/tokenizer_config.json Executable file
View File

@@ -0,0 +1,38 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "!",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"49406": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"49407": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": true,
"do_lower_case": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 77,
"pad_token": "!",
"tokenizer_class": "CLIPTokenizer",
"unk_token": "<|endoftext|>"
}

49410
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/tokenizer_2/vocab.json Executable file
View File

File diff suppressed because it is too large Load Diff

72
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/unet/config.json Executable file
View File

@@ -0,0 +1,72 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.27.0.dev0",
"act_fn": "silu",
"addition_embed_type": "text_time",
"addition_embed_type_num_heads": 64,
"addition_time_embed_dim": 256,
"attention_head_dim": [
5,
10,
20
],
"attention_type": "default",
"block_out_channels": [
320,
640,
1280
],
"center_input_sample": false,
"class_embed_type": null,
"class_embeddings_concat": false,
"conv_in_kernel": 3,
"conv_out_kernel": 3,
"cross_attention_dim": 2048,
"cross_attention_norm": null,
"down_block_types": [
"DownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D"
],
"downsample_padding": 1,
"dropout": 0.0,
"dual_cross_attention": false,
"encoder_hid_dim": null,
"encoder_hid_dim_type": null,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 4,
"layers_per_block": 2,
"mid_block_only_cross_attention": null,
"mid_block_scale_factor": 1,
"mid_block_type": "UNetMidBlock2DCrossAttn",
"norm_eps": 1e-05,
"norm_num_groups": 32,
"num_attention_heads": null,
"num_class_embeds": null,
"only_cross_attention": false,
"out_channels": 4,
"projection_class_embeddings_input_dim": 2816,
"resnet_out_scale_factor": 1.0,
"resnet_skip_time_act": false,
"resnet_time_scale_shift": "default",
"reverse_transformer_layers_per_block": null,
"sample_size": 128,
"time_cond_proj_dim": null,
"time_embedding_act_fn": null,
"time_embedding_dim": null,
"time_embedding_type": "positional",
"timestep_post_act": null,
"transformer_layers_per_block": [
1,
2,
10
],
"up_block_types": [
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"UpBlock2D"
],
"upcast_attention": false,
"use_linear_projection": true
}

43
backend/huggingface/playgroundai/playground-v2.5-1024px-aesthetic/vae/config.json Executable file
View File

@@ -0,0 +1,43 @@
{
"_class_name": "AutoencoderKL",
"_diffusers_version": "0.27.0.dev0",
"act_fn": "silu",
"block_out_channels": [
128,
256,
512,
512
],
"down_block_types": [
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D",
"DownEncoderBlock2D"
],
"force_upcast": true,
"in_channels": 3,
"latent_channels": 4,
"layers_per_block": 2,
"norm_num_groups": 32,
"out_channels": 3,
"sample_size": 1024,
"up_block_types": [
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D",
"UpDecoderBlock2D"
],
"latents_mean": [
-1.6574,
1.886,
-1.383,
2.5155
],
"latents_std": [
8.4927,
5.9022,
6.5498,
5.2299
],
"scaling_factor": 0.5
}

36
backend/huggingface/runwayml/stable-diffusion-inpainting/config.json Executable file
View File

@@ -0,0 +1,36 @@
{
"_class_name": "UNet2DConditionModel",
"_diffusers_version": "0.6.0.dev0",
"act_fn": "silu",
"attention_head_dim": 8,
"block_out_channels": [
320,
640,
1280,
1280
],
"center_input_sample": false,
"cross_attention_dim": 768,
"down_block_types": [
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D"
],
"downsample_padding": 1,
"flip_sin_to_cos": true,
"freq_shift": 0,
"in_channels": 9,
"layers_per_block": 2,
"mid_block_scale_factor": 1,
"norm_eps": 1e-05,
"norm_num_groups": 32,
"out_channels": 4,
"sample_size": 64,
"up_block_types": [
"UpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D",
"CrossAttnUpBlock2D"
]
}

20
backend/huggingface/runwayml/stable-diffusion-inpainting/feature_extractor/preprocessor_config.json Executable file
View File

@@ -0,0 +1,20 @@
{
"crop_size": 224,
"do_center_crop": true,
"do_convert_rgb": true,
"do_normalize": true,
"do_resize": true,
"feature_extractor_type": "CLIPFeatureExtractor",
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"resample": 3,
"size": 224
}

32
backend/huggingface/runwayml/stable-diffusion-inpainting/model_index.json Executable file
View File

@@ -0,0 +1,32 @@
{
"_class_name": "StableDiffusionInpaintPipeline",
"_diffusers_version": "0.6.0",
"feature_extractor": [
"transformers",
"CLIPImageProcessor"
],
"safety_checker": [
"stable_diffusion",
"StableDiffusionSafetyChecker"
],
"scheduler": [
"diffusers",
"DDIMScheduler"
],
"text_encoder": [
"transformers",
"CLIPTextModel"
],
"tokenizer": [
"transformers",
"CLIPTokenizer"
],
"unet": [
"diffusers",
"UNet2DConditionModel"
],
"vae": [
"diffusers",
"AutoencoderKL"
]
}

Some files were not shown because too many files have changed in this diff Show More