Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,10 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Auto detect text files and perform LF normalization
+* text=auto
+media/avgpcperformancedemo.gif filter=lfs diff=lfs merge=lfs -text
+media/deepwarebench.gif filter=lfs diff=lfs merge=lfs -text
+media/demo.gif filter=lfs diff=lfs merge=lfs -text
+media/live_show.gif filter=lfs diff=lfs merge=lfs -text
+media/ludwig.gif filter=lfs diff=lfs merge=lfs -text
+media/meme.gif filter=lfs diff=lfs merge=lfs -text
+media/movie.gif filter=lfs diff=lfs merge=lfs -text
+media/streamers.gif filter=lfs diff=lfs merge=lfs -text

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,26 @@
+***[Remove this]The issue would be closed without notice and be considered spam if the template is not followed.***
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**Error Message**
+
+`<The error message in terminal>`
+
+**Desktop (please complete the following information):**
+ - OS: [e.g. Windows]
+ - Version [e.g. 22]
+ - GPU
+ - CPU
+
+**Additional context**
+Add any other context about the problem here.
+
+**Confirmation (Mandatory)**
+- [ ] I have followed the template
+- [ ] This is not a query about how to increase performance
+- [ ] I have checked the issues page, and this is not a duplicate
+

.gitignore

@@ -0,0 +1,27 @@
+__pycache__/
+*.py[cod]
+*$py.class
+*.pyc
+.idea
+.todo
+*.log
+*.backup
+tf_env/
+*.png
+*.mp4
+*.mkv
+
+.tmp/
+temp/
+.venv/
+venv/
+env/
+workflow/
+gfpgan/
+models/inswapper_128.onnx
+models/GFPGANv1.4.pth
+*.onnx
+models/DMDNet.pth
+faceswap/
+.vscode/
+switch_states.json

CONTRIBUTING.md

@@ -0,0 +1,38 @@
+# Collaboration Guidelines and Codebase Quality Standards
+
+To ensure smooth collaboration and maintain the high quality of our codebase, please adhere to the following guidelines:
+
+## Branching Strategy
+
+*   **`premain`**:
+    *   Always push your changes to the `premain` branch initially.
+    *   This safeguards the `main` branch from unintentional disruptions.
+    *   All tests will be performed on the `premain` branch.
+    *   Changes will only be merged into `main` after several hours or days of rigorous testing.
+*   **`experimental`**:
+    *   For large or potentially disruptive changes, use the `experimental` branch.
+    *   This allows for thorough discussion and review before considering a merge into `main`.
+
+## Pre-Pull Request Checklist
+
+Before creating a Pull Request (PR), ensure you have completed the following tests:
+
+### Functionality
+
+*   **Realtime Faceswap**:
+    *   Test with face enhancer **enabled** and **disabled**.
+*   **Map Faces**:
+    *   Test with both options (**enabled** and **disabled**).
+*   **Camera Listing**:
+    *   Verify that all cameras are listed accurately.
+
+### Stability
+
+*   **Realtime FPS**:
+    *   Confirm that there is no drop in real-time frames per second (FPS).
+*   **Boot Time**:
+    *   Changes should not negatively impact the boot time of either the application or the real-time faceswap feature.
+*   **GPU Overloading**:
+    *   Test for a minimum of 15 minutes to guarantee no GPU overloading, which could lead to crashes.
+*   **App Performance**:
+    *   The application should remain responsive and not exhibit any lag.

LICENSE

@@ -0,0 +1,661 @@
+                    GNU AFFERO GENERAL PUBLIC LICENSE
+                       Version 3, 19 November 2007
+
+ 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/>.

README.md

@@ -1,12 +1,388 @@
----
-title: Dlcmuz
-emoji: 📉
-colorFrom: green
-colorTo: pink
-sdk: gradio
-sdk_version: 5.29.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<h1 align="center">Deep-Live-Cam</h1>
+
+<p align="center">
+  Real-time face swap and video deepfake with a single click and only a single image.
+</p>
+
+<p align="center">
+<a href="https://trendshift.io/repositories/11395" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11395" alt="hacksider%2FDeep-Live-Cam | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</p>
+
+<p align="center">
+  <img src="media/demo.gif" alt="Demo GIF" width="800">
+</p>
+
+##  Disclaimer
+
+This deepfake software is designed to be a productive tool for the AI-generated media industry. It can assist artists in animating custom characters, creating engaging content, and even using models for clothing design.
+
+We are aware of the potential for unethical applications and are committed to preventative measures. A built-in check prevents the program from processing inappropriate media (nudity, graphic content, sensitive material like war footage, etc.). We will continue to develop this project responsibly, adhering to the law and ethics. We may shut down the project or add watermarks if legally required.
+
+- Ethical Use: Users are expected to use this software responsibly and legally. If using a real person's face, obtain their consent and clearly label any output as a deepfake when sharing online.
+
+- Content Restrictions: The software includes built-in checks to prevent processing inappropriate media, such as nudity, graphic content, or sensitive material.
+
+- Legal Compliance: We adhere to all relevant laws and ethical guidelines. If legally required, we may shut down the project or add watermarks to the output.
+
+- User Responsibility: We are not responsible for end-user actions. Users must ensure their use of the software aligns with ethical standards and legal requirements.
+
+By using this software, you agree to these terms and commit to using it in a manner that respects the rights and dignity of others.
+
+Users are expected to use this software responsibly and legally. If using a real person's face, obtain their consent and clearly label any output as a deepfake when sharing online. We are not responsible for end-user actions.
+
+## Exclusive v2.0 Quick Start - Pre-built (Windows)
+
+  <a href="https://deeplivecam.net/index.php/quickstart"> <img src="media/Download.png" width="285" height="77" />
+
+##### This is the fastest build you can get if you have a discrete NVIDIA or AMD GPU.
+ 
+###### These Pre-builts are perfect for non-technical users or those who don't have time to, or can't manually install all the requirements. Just a heads-up: this is an open-source project, so you can also install it manually. This will be 60 days ahead on the open source version.
+
+## TLDR; Live Deepfake in just 3 Clicks
+![easysteps](https://github.com/user-attachments/assets/af825228-852c-411b-b787-ffd9aac72fc6)
+1. Select a face
+2. Select which camera to use
+3. Press live!
+
+## Features & Uses - Everything is in real-time
+
+### Mouth Mask
+
+**Retain your original mouth for accurate movement using Mouth Mask**
+
+<p align="center">
+  <img src="media/ludwig.gif" alt="resizable-gif">
+</p>
+
+### Face Mapping
+
+**Use different faces on multiple subjects simultaneously**
+
+<p align="center">
+  <img src="media/streamers.gif" alt="face_mapping_source">
+</p>
+
+### Your Movie, Your Face
+
+**Watch movies with any face in real-time**
+
+<p align="center">
+  <img src="media/movie.gif" alt="movie">
+</p>
+
+### Live Show
+
+**Run Live shows and performances**
+
+<p align="center">
+  <img src="media/live_show.gif" alt="show">
+</p>
+
+### Memes
+
+**Create Your Most Viral Meme Yet**
+
+<p align="center">
+  <img src="media/meme.gif" alt="show" width="450"> 
+  <br>
+  <sub>Created using Many Faces feature in Deep-Live-Cam</sub>
+</p>
+
+### Omegle
+
+**Surprise people on Omegle**
+
+<p align="center">
+  <video src="https://github.com/user-attachments/assets/2e9b9b82-fa04-4b70-9f56-b1f68e7672d0" width="450" controls></video>
+</p>
+
+## Installation (Manual)
+
+**Please be aware that the installation requires technical skills and is not for beginners. Consider downloading the prebuilt version.**
+
+<details>
+<summary>Click to see the process</summary>
+
+### Installation
+
+This is more likely to work on your computer but will be slower as it utilizes the CPU.
+
+**1. Set up Your Platform**
+
+-   Python (3.10 recommended)
+-   pip
+-   git
+-   [ffmpeg](https://www.youtube.com/watch?v=OlNWCpFdVMA) - ```iex (irm ffmpeg.tc.ht)```
+-   [Visual Studio 2022 Runtimes (Windows)](https://visualstudio.microsoft.com/visual-cpp-build-tools/)
+
+**2. Clone the Repository**
+
+```bash
+git clone https://github.com/hacksider/Deep-Live-Cam.git
+cd Deep-Live-Cam
+```
+
+**3. Download the Models**
+
+1. [GFPGANv1.4](https://huggingface.co/hacksider/deep-live-cam/resolve/main/GFPGANv1.4.pth)
+2. [inswapper\_128\_fp16.onnx](https://huggingface.co/hacksider/deep-live-cam/resolve/main/inswapper_128_fp16.onnx)
+
+Place these files in the "**models**" folder.
+
+**4. Install Dependencies**
+
+We highly recommend using a `venv` to avoid issues.
+
+
+For Windows:
+```bash
+python -m venv venv
+venv\Scripts\activate
+pip install -r requirements.txt
+```
+For Linux:
+```bash
+# Ensure you use the installed Python 3.10
+python3 -m venv venv
+source venv/bin/activate
+pip install -r requirements.txt
+```
+
+**For macOS:**
+
+Apple Silicon (M1/M2/M3) requires specific setup:
+
+```bash
+# Install Python 3.10 (specific version is important)
+brew install [email protected]
+
+# Install tkinter package (required for the GUI)
+brew install [email protected]
+
+# Create and activate virtual environment with Python 3.10
+python3.10 -m venv venv
+source venv/bin/activate
+
+# Install dependencies
+pip install -r requirements.txt
+```
+
+** In case something goes wrong and you need to reinstall the virtual environment **
+
+```bash
+# Deactivate the virtual environment
+rm -rf venv
+
+# Reinstall the virtual environment
+python -m venv venv
+source venv/bin/activate
+
+# install the dependencies again
+pip install -r requirements.txt
+```
+
+**Run:** If you don't have a GPU, you can run Deep-Live-Cam using `python run.py`. Note that initial execution will download models (~300MB).
+
+### GPU Acceleration
+
+**CUDA Execution Provider (Nvidia)**
+
+1. Install [CUDA Toolkit 11.8.0](https://developer.nvidia.com/cuda-11-8-0-download-archive)
+2. Install dependencies:
+
+```bash
+pip uninstall onnxruntime onnxruntime-gpu
+pip install onnxruntime-gpu==1.16.3
+```
+
+3. Usage:
+
+```bash
+python run.py --execution-provider cuda
+```
+
+**CoreML Execution Provider (Apple Silicon)**
+
+Apple Silicon (M1/M2/M3) specific installation:
+
+1. Make sure you've completed the macOS setup above using Python 3.10.
+2. Install dependencies:
+
+```bash
+pip uninstall onnxruntime onnxruntime-silicon
+pip install onnxruntime-silicon==1.13.1
+```
+
+3. Usage (important: specify Python 3.10):
+
+```bash
+python3.10 run.py --execution-provider coreml
+```
+
+**Important Notes for macOS:**
+- You **must** use Python 3.10, not newer versions like 3.11 or 3.13
+- Always run with `python3.10` command not just `python` if you have multiple Python versions installed
+- If you get error about `_tkinter` missing, reinstall the tkinter package: `brew reinstall [email protected]`
+- If you get model loading errors, check that your models are in the correct folder
+- If you encounter conflicts with other Python versions, consider uninstalling them:
+  ```bash
+  # List all installed Python versions
+  brew list | grep python
+  
+  # Uninstall conflicting versions if needed
+  brew uninstall --ignore-dependencies [email protected] [email protected]
+  
+  # Keep only Python 3.10
+  brew cleanup
+  ```
+
+**CoreML Execution Provider (Apple Legacy)**
+
+1. Install dependencies:
+
+```bash
+pip uninstall onnxruntime onnxruntime-coreml
+pip install onnxruntime-coreml==1.13.1
+```
+
+2. Usage:
+
+```bash
+python run.py --execution-provider coreml
+```
+
+**DirectML Execution Provider (Windows)**
+
+1. Install dependencies:
+
+```bash
+pip uninstall onnxruntime onnxruntime-directml
+pip install onnxruntime-directml==1.15.1
+```
+
+2. Usage:
+
+```bash
+python run.py --execution-provider directml
+```
+
+**OpenVINO™ Execution Provider (Intel)**
+
+1. Install dependencies:
+
+```bash
+pip uninstall onnxruntime onnxruntime-openvino
+pip install onnxruntime-openvino==1.15.0
+```
+
+2. Usage:
+
+```bash
+python run.py --execution-provider openvino
+```
+</details>
+
+## Usage
+
+**1. Image/Video Mode**
+
+-   Execute `python run.py`.
+-   Choose a source face image and a target image/video.
+-   Click "Start".
+-   The output will be saved in a directory named after the target video.
+
+**2. Webcam Mode**
+
+-   Execute `python run.py`.
+-   Select a source face image.
+-   Click "Live".
+-   Wait for the preview to appear (10-30 seconds).
+-   Use a screen capture tool like OBS to stream.
+-   To change the face, select a new source image.
+
+## Tips and Tricks
+
+Check out these helpful guides to get the most out of Deep-Live-Cam:
+
+- [Unlocking the Secrets to the Perfect Deepfake Image](https://deeplivecam.net/index.php/blog/tips-and-tricks/unlocking-the-secrets-to-the-perfect-deepfake-image) - Learn how to create the best deepfake with full head coverage
+- [Video Call with DeepLiveCam](https://deeplivecam.net/index.php/blog/tips-and-tricks/video-call-with-deeplivecam) - Make your meetings livelier by using DeepLiveCam with OBS and meeting software
+- [Have a Special Guest!](https://deeplivecam.net/index.php/blog/tips-and-tricks/have-a-special-guest) - Tutorial on how to use face mapping to add special guests to your stream
+- [Watch Deepfake Movies in Realtime](https://deeplivecam.net/index.php/blog/tips-and-tricks/watch-deepfake-movies-in-realtime) - See yourself star in any video without processing the video
+- [Better Quality without Sacrificing Speed](https://deeplivecam.net/index.php/blog/tips-and-tricks/better-quality-without-sacrificing-speed) - Tips for achieving better results without impacting performance
+- [Instant Vtuber!](https://deeplivecam.net/index.php/blog/tips-and-tricks/instant-vtuber) - Create a new persona/vtuber easily using Metahuman Creator
+
+Visit our [official blog](https://deeplivecam.net/index.php/blog/tips-and-tricks) for more tips and tutorials.
+
+## Command Line Arguments (Unmaintained)
+
+```
+options:
+  -h, --help                                               show this help message and exit
+  -s SOURCE_PATH, --source SOURCE_PATH                     select a source image
+  -t TARGET_PATH, --target TARGET_PATH                     select a target image or video
+  -o OUTPUT_PATH, --output OUTPUT_PATH                     select output file or directory
+  --frame-processor FRAME_PROCESSOR [FRAME_PROCESSOR ...]  frame processors (choices: face_swapper, face_enhancer, ...)
+  --keep-fps                                               keep original fps
+  --keep-audio                                             keep original audio
+  --keep-frames                                            keep temporary frames
+  --many-faces                                             process every face
+  --map-faces                                              map source target faces
+  --mouth-mask                                             mask the mouth region
+  --video-encoder {libx264,libx265,libvpx-vp9}             adjust output video encoder
+  --video-quality [0-51]                                   adjust output video quality
+  --live-mirror                                            the live camera display as you see it in the front-facing camera frame
+  --live-resizable                                         the live camera frame is resizable
+  --max-memory MAX_MEMORY                                  maximum amount of RAM in GB
+  --execution-provider {cpu} [{cpu} ...]                   available execution provider (choices: cpu, ...)
+  --execution-threads EXECUTION_THREADS                    number of execution threads
+  -v, --version                                            show program's version number and exit
+```
+
+Looking for a CLI mode? Using the -s/--source argument will make the run program in cli mode.
+
+## Press
+
+**We are always open to criticism and are ready to improve, that's why we didn't cherry-pick anything.**
+
+ - [*"Deep-Live-Cam goes viral, allowing anyone to become a digital doppelganger"*](https://arstechnica.com/information-technology/2024/08/new-ai-tool-enables-real-time-face-swapping-on-webcams-raising-fraud-concerns/) - Ars Technica
+ - [*"Thanks Deep Live Cam, shapeshifters are among us now"*](https://dataconomy.com/2024/08/15/what-is-deep-live-cam-github-deepfake/) - Dataconomy
+ - [*"This free AI tool lets you become anyone during video-calls"*](https://www.newsbytesapp.com/news/science/deep-live-cam-ai-impersonation-tool-goes-viral/story) - NewsBytes
+ - [*"OK, this viral AI live stream software is truly terrifying"*](https://www.creativebloq.com/ai/ok-this-viral-ai-live-stream-software-is-truly-terrifying) - Creative Bloq
+ - [*"Deepfake AI Tool Lets You Become Anyone in a Video Call With Single Photo"*](https://petapixel.com/2024/08/14/deep-live-cam-deepfake-ai-tool-lets-you-become-anyone-in-a-video-call-with-single-photo-mark-zuckerberg-jd-vance-elon-musk/) - PetaPixel
+ - [*"Deep-Live-Cam Uses AI to Transform Your Face in Real-Time, Celebrities Included"*](https://www.techeblog.com/deep-live-cam-ai-transform-face/) - TechEBlog
+ - [*"An AI tool that "makes you look like anyone" during a video call is going viral online"*](https://telegrafi.com/en/a-tool-that-makes-you-look-like-anyone-during-a-video-call-is-going-viral-on-the-Internet/) - Telegrafi
+ - [*"This Deepfake Tool Turning Images Into Livestreams is Topping the GitHub Charts"*](https://decrypt.co/244565/this-deepfake-tool-turning-images-into-livestreams-is-topping-the-github-charts) - Emerge
+ - [*"New Real-Time Face-Swapping AI Allows Anyone to Mimic Famous Faces"*](https://www.digitalmusicnews.com/2024/08/15/face-swapping-ai-real-time-mimic/) - Digital Music News
+ - [*"This real-time webcam deepfake tool raises alarms about the future of identity theft"*](https://www.diyphotography.net/this-real-time-webcam-deepfake-tool-raises-alarms-about-the-future-of-identity-theft/) - DIYPhotography
+ - [*"That's Crazy, Oh God. That's Fucking Freaky Dude... That's So Wild Dude"*](https://www.youtube.com/watch?time_continue=1074&v=py4Tc-Y8BcY) - SomeOrdinaryGamers
+ - [*"Alright look look look, now look chat, we can do any face we want to look like chat"*](https://www.youtube.com/live/mFsCe7AIxq8?feature=shared&t=2686) - IShowSpeed
+
+## Credits
+
+-   [ffmpeg](https://ffmpeg.org/): for making video-related operations easy
+-   [deepinsight](https://github.com/deepinsight): for their [insightface](https://github.com/deepinsight/insightface) project which provided a well-made library and models. Please be reminded that the [use of the model is for non-commercial research purposes only](https://github.com/deepinsight/insightface?tab=readme-ov-file#license).
+-   [havok2-htwo](https://github.com/havok2-htwo): for sharing the code for webcam
+-   [GosuDRM](https://github.com/GosuDRM): for the open version of roop
+-   [pereiraroland26](https://github.com/pereiraroland26): Multiple faces support
+-   [vic4key](https://github.com/vic4key): For supporting/contributing to this project
+-   [kier007](https://github.com/kier007): for improving the user experience
+-   [qitianai](https://github.com/qitianai): for multi-lingual support
+-   and [all developers](https://github.com/hacksider/Deep-Live-Cam/graphs/contributors) behind libraries used in this project.
+-   Footnote: Please be informed that the base author of the code is [s0md3v](https://github.com/s0md3v/roop)
+-   All the wonderful users who helped make this project go viral by starring the repo ❤️
+
+[![Stargazers](https://reporoster.com/stars/hacksider/Deep-Live-Cam)](https://github.com/hacksider/Deep-Live-Cam/stargazers)
+
+## Contributions
+
+![Alt](https://repobeats.axiom.co/api/embed/fec8e29c45dfdb9c5916f3a7830e1249308d20e1.svg "Repobeats analytics image")
+
+## Stars to the Moon 🚀
+
+<a href="https://star-history.com/#hacksider/deep-live-cam&Date">
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=hacksider/deep-live-cam&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=hacksider/deep-live-cam&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=hacksider/deep-live-cam&type=Date" />
+ </picture>
+</a>

locales/zh.json

@@ -0,0 +1,46 @@
+{
+    "Source x Target Mapper": "Source x Target Mapper",
+    "select an source image": "选择一个源图像",
+    "Preview": "预览",
+    "select an target image or video": "选择一个目标图像或视频",
+    "save image output file": "保存图像输出文件",
+    "save video output file": "保存视频输出文件",
+    "select an target image": "选择一个目标图像",
+    "source": "源",
+    "Select a target": "选择一个目标",
+    "Select a face": "选择一张脸",
+    "Keep audio": "保留音频",
+    "Face Enhancer": "面纹增强器",
+    "Many faces": "多脸",
+    "Show FPS": "显示帧率",
+    "Keep fps": "保持帧率",
+    "Keep frames": "保持帧数",
+    "Fix Blueish Cam": "修复偏蓝的摄像头",
+    "Mouth Mask": "口罩",
+    "Show Mouth Mask Box": "显示口罩盒",
+    "Start": "开始",
+    "Live": "直播",
+    "Destroy": "结束",
+    "Map faces": "识别人脸",
+    "Processing...": "处理中...",
+    "Processing succeed!": "处理成功!",
+    "Processing ignored!": "处理被忽略!",
+    "Failed to start camera": "启动相机失败",
+    "Please complete pop-up or close it.": "请先完成弹出窗口或者关闭它",
+    "Getting unique faces": "获取独特面部",
+    "Please select a source image first": "请先选择一个源图像",
+    "No faces found in target": "目标图像中没有人脸",
+    "Add": "添加",
+    "Clear": "清除",
+    "Submit": "确认",
+    "Select source image": "请选取源图像",
+    "Select target image": "请选取目标图像",
+    "Please provide mapping!": "请提供映射",
+    "Atleast 1 source with target is required!": "至少需要一个来源图像与目标图像相关！",
+    "At least 1 source with target is required!": "至少需要一个来源图像与目标图像相关！",
+    "Face could not be detected in last upload!": "最近上传的图像中没有检测到人脸!",
+    "Select Camera:": "选择摄像头",
+    "All mappings cleared!": "所有映射均已清除!",
+    "Mappings successfully submitted!": "成功提交映射！",
+    "Source x Target Mapper is already open.": "源 x 目标映射器已打开。"
+}

models/instructions.txt

@@ -0,0 +1,4 @@
+just put the models in this folder -
+
+https://huggingface.co/hacksider/deep-live-cam/resolve/main/inswapper_128_fp16.onnx?download=true
+https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth

modules/capturer.py

@@ -0,0 +1,32 @@
+from typing import Any
+import cv2
+import modules.globals  # Import the globals to check the color correction toggle
+
+
+def get_video_frame(video_path: str, frame_number: int = 0) -> Any:
+    capture = cv2.VideoCapture(video_path)
+
+    # Set MJPEG format to ensure correct color space handling
+    capture.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*'MJPG'))
+    
+    # Only force RGB conversion if color correction is enabled
+    if modules.globals.color_correction:
+        capture.set(cv2.CAP_PROP_CONVERT_RGB, 1)
+    
+    frame_total = capture.get(cv2.CAP_PROP_FRAME_COUNT)
+    capture.set(cv2.CAP_PROP_POS_FRAMES, min(frame_total, frame_number - 1))
+    has_frame, frame = capture.read()
+
+    if has_frame and modules.globals.color_correction:
+        # Convert the frame color if necessary
+        frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+
+    capture.release()
+    return frame if has_frame else None
+
+
+def get_video_frame_total(video_path: str) -> int:
+    capture = cv2.VideoCapture(video_path)
+    video_frame_total = int(capture.get(cv2.CAP_PROP_FRAME_COUNT))
+    capture.release()
+    return video_frame_total

modules/cluster_analysis.py

@@ -0,0 +1,32 @@
+import numpy as np
+from sklearn.cluster import KMeans
+from sklearn.metrics import silhouette_score
+from typing import Any
+
+
+def find_cluster_centroids(embeddings, max_k=10) -> Any:
+    inertia = []
+    cluster_centroids = []
+    K = range(1, max_k+1)
+
+    for k in K:
+        kmeans = KMeans(n_clusters=k, random_state=0)
+        kmeans.fit(embeddings)
+        inertia.append(kmeans.inertia_)
+        cluster_centroids.append({"k": k, "centroids": kmeans.cluster_centers_})
+
+    diffs = [inertia[i] - inertia[i+1] for i in range(len(inertia)-1)]
+    optimal_centroids = cluster_centroids[diffs.index(max(diffs)) + 1]['centroids']
+
+    return optimal_centroids
+
+def find_closest_centroid(centroids: list, normed_face_embedding) -> list:
+    try:
+        centroids = np.array(centroids)
+        normed_face_embedding = np.array(normed_face_embedding)
+        similarities = np.dot(centroids, normed_face_embedding)
+        closest_centroid_index = np.argmax(similarities)
+        
+        return closest_centroid_index, centroids[closest_centroid_index]
+    except ValueError:
+        return None

modules/core.py

@@ -0,0 +1,259 @@
+import os
+import sys
+# single thread doubles cuda performance - needs to be set before torch import
+if any(arg.startswith('--execution-provider') for arg in sys.argv):
+    os.environ['OMP_NUM_THREADS'] = '1'
+# reduce tensorflow log level
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
+import warnings
+from typing import List
+import platform
+import signal
+import shutil
+import argparse
+import torch
+import onnxruntime
+import tensorflow
+
+import modules.globals
+import modules.metadata
+import modules.ui as ui
+from modules.processors.frame.core import get_frame_processors_modules
+from modules.utilities import has_image_extension, is_image, is_video, detect_fps, create_video, extract_frames, get_temp_frame_paths, restore_audio, create_temp, move_temp, clean_temp, normalize_output_path
+
+if 'ROCMExecutionProvider' in modules.globals.execution_providers:
+    del torch
+
+warnings.filterwarnings('ignore', category=FutureWarning, module='insightface')
+warnings.filterwarnings('ignore', category=UserWarning, module='torchvision')
+
+
+def parse_args() -> None:
+    signal.signal(signal.SIGINT, lambda signal_number, frame: destroy())
+    program = argparse.ArgumentParser()
+    program.add_argument('-s', '--source', help='select an source image', dest='source_path')
+    program.add_argument('-t', '--target', help='select an target image or video', dest='target_path')
+    program.add_argument('-o', '--output', help='select output file or directory', dest='output_path')
+    program.add_argument('--frame-processor', help='pipeline of frame processors', dest='frame_processor', default=['face_swapper'], choices=['face_swapper', 'face_enhancer'], nargs='+')
+    program.add_argument('--keep-fps', help='keep original fps', dest='keep_fps', action='store_true', default=False)
+    program.add_argument('--keep-audio', help='keep original audio', dest='keep_audio', action='store_true', default=True)
+    program.add_argument('--keep-frames', help='keep temporary frames', dest='keep_frames', action='store_true', default=False)
+    program.add_argument('--many-faces', help='process every face', dest='many_faces', action='store_true', default=False)
+    program.add_argument('--nsfw-filter', help='filter the NSFW image or video', dest='nsfw_filter', action='store_true', default=False)
+    program.add_argument('--map-faces', help='map source target faces', dest='map_faces', action='store_true', default=False)
+    program.add_argument('--mouth-mask', help='mask the mouth region', dest='mouth_mask', action='store_true', default=False)
+    program.add_argument('--video-encoder', help='adjust output video encoder', dest='video_encoder', default='libx264', choices=['libx264', 'libx265', 'libvpx-vp9'])
+    program.add_argument('--video-quality', help='adjust output video quality', dest='video_quality', type=int, default=18, choices=range(52), metavar='[0-51]')
+    program.add_argument('-l', '--lang', help='Ui language', default="en")
+    program.add_argument('--live-mirror', help='The live camera display as you see it in the front-facing camera frame', dest='live_mirror', action='store_true', default=False)
+    program.add_argument('--live-resizable', help='The live camera frame is resizable', dest='live_resizable', action='store_true', default=False)
+    program.add_argument('--max-memory', help='maximum amount of RAM in GB', dest='max_memory', type=int, default=suggest_max_memory())
+    program.add_argument('--execution-provider', help='execution provider', dest='execution_provider', default=['cpu'], choices=suggest_execution_providers(), nargs='+')
+    program.add_argument('--execution-threads', help='number of execution threads', dest='execution_threads', type=int, default=suggest_execution_threads())
+    program.add_argument('-v', '--version', action='version', version=f'{modules.metadata.name} {modules.metadata.version}')
+
+    # register deprecated args
+    program.add_argument('-f', '--face', help=argparse.SUPPRESS, dest='source_path_deprecated')
+    program.add_argument('--cpu-cores', help=argparse.SUPPRESS, dest='cpu_cores_deprecated', type=int)
+    program.add_argument('--gpu-vendor', help=argparse.SUPPRESS, dest='gpu_vendor_deprecated')
+    program.add_argument('--gpu-threads', help=argparse.SUPPRESS, dest='gpu_threads_deprecated', type=int)
+
+    args = program.parse_args()
+
+    modules.globals.source_path = args.source_path
+    modules.globals.target_path = args.target_path
+    modules.globals.output_path = normalize_output_path(modules.globals.source_path, modules.globals.target_path, args.output_path)
+    modules.globals.frame_processors = args.frame_processor
+    modules.globals.headless = args.source_path or args.target_path or args.output_path
+    modules.globals.keep_fps = args.keep_fps
+    modules.globals.keep_audio = args.keep_audio
+    modules.globals.keep_frames = args.keep_frames
+    modules.globals.many_faces = args.many_faces
+    modules.globals.mouth_mask = args.mouth_mask
+    modules.globals.nsfw_filter = args.nsfw_filter
+    modules.globals.map_faces = args.map_faces
+    modules.globals.video_encoder = args.video_encoder
+    modules.globals.video_quality = args.video_quality
+    modules.globals.live_mirror = args.live_mirror
+    modules.globals.live_resizable = args.live_resizable
+    modules.globals.max_memory = args.max_memory
+    modules.globals.execution_providers = decode_execution_providers(args.execution_provider)
+    modules.globals.execution_threads = args.execution_threads
+    modules.globals.lang = args.lang
+
+    #for ENHANCER tumbler:
+    if 'face_enhancer' in args.frame_processor:
+        modules.globals.fp_ui['face_enhancer'] = True
+    else:
+        modules.globals.fp_ui['face_enhancer'] = False
+
+    # translate deprecated args
+    if args.source_path_deprecated:
+        print('\033[33mArgument -f and --face are deprecated. Use -s and --source instead.\033[0m')
+        modules.globals.source_path = args.source_path_deprecated
+        modules.globals.output_path = normalize_output_path(args.source_path_deprecated, modules.globals.target_path, args.output_path)
+    if args.cpu_cores_deprecated:
+        print('\033[33mArgument --cpu-cores is deprecated. Use --execution-threads instead.\033[0m')
+        modules.globals.execution_threads = args.cpu_cores_deprecated
+    if args.gpu_vendor_deprecated == 'apple':
+        print('\033[33mArgument --gpu-vendor apple is deprecated. Use --execution-provider coreml instead.\033[0m')
+        modules.globals.execution_providers = decode_execution_providers(['coreml'])
+    if args.gpu_vendor_deprecated == 'nvidia':
+        print('\033[33mArgument --gpu-vendor nvidia is deprecated. Use --execution-provider cuda instead.\033[0m')
+        modules.globals.execution_providers = decode_execution_providers(['cuda'])
+    if args.gpu_vendor_deprecated == 'amd':
+        print('\033[33mArgument --gpu-vendor amd is deprecated. Use --execution-provider cuda instead.\033[0m')
+        modules.globals.execution_providers = decode_execution_providers(['rocm'])
+    if args.gpu_threads_deprecated:
+        print('\033[33mArgument --gpu-threads is deprecated. Use --execution-threads instead.\033[0m')
+        modules.globals.execution_threads = args.gpu_threads_deprecated
+
+
+def encode_execution_providers(execution_providers: List[str]) -> List[str]:
+    return [execution_provider.replace('ExecutionProvider', '').lower() for execution_provider in execution_providers]
+
+
+def decode_execution_providers(execution_providers: List[str]) -> List[str]:
+    return [provider for provider, encoded_execution_provider in zip(onnxruntime.get_available_providers(), encode_execution_providers(onnxruntime.get_available_providers()))
+            if any(execution_provider in encoded_execution_provider for execution_provider in execution_providers)]
+
+
+def suggest_max_memory() -> int:
+    if platform.system().lower() == 'darwin':
+        return 4
+    return 16
+
+
+def suggest_execution_providers() -> List[str]:
+    return encode_execution_providers(onnxruntime.get_available_providers())
+
+
+def suggest_execution_threads() -> int:
+    if 'DmlExecutionProvider' in modules.globals.execution_providers:
+        return 1
+    if 'ROCMExecutionProvider' in modules.globals.execution_providers:
+        return 1
+    return 8
+
+
+def limit_resources() -> None:
+    # prevent tensorflow memory leak
+    gpus = tensorflow.config.experimental.list_physical_devices('GPU')
+    for gpu in gpus:
+        tensorflow.config.experimental.set_memory_growth(gpu, True)
+    # limit memory usage
+    if modules.globals.max_memory:
+        memory = modules.globals.max_memory * 1024 ** 3
+        if platform.system().lower() == 'darwin':
+            memory = modules.globals.max_memory * 1024 ** 6
+        if platform.system().lower() == 'windows':
+            import ctypes
+            kernel32 = ctypes.windll.kernel32
+            kernel32.SetProcessWorkingSetSize(-1, ctypes.c_size_t(memory), ctypes.c_size_t(memory))
+        else:
+            import resource
+            resource.setrlimit(resource.RLIMIT_DATA, (memory, memory))
+
+
+def release_resources() -> None:
+    if 'CUDAExecutionProvider' in modules.globals.execution_providers:
+        torch.cuda.empty_cache()
+
+
+def pre_check() -> bool:
+    if sys.version_info < (3, 9):
+        update_status('Python version is not supported - please upgrade to 3.9 or higher.')
+        return False
+    if not shutil.which('ffmpeg'):
+        update_status('ffmpeg is not installed.')
+        return False
+    return True
+
+
+def update_status(message: str, scope: str = 'DLC.CORE') -> None:
+    print(f'[{scope}] {message}')
+    if not modules.globals.headless:
+        ui.update_status(message)
+
+def start() -> None:
+    for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
+        if not frame_processor.pre_start():
+            return
+    update_status('Processing...')
+    # process image to image
+    if has_image_extension(modules.globals.target_path):
+        if modules.globals.nsfw_filter and ui.check_and_ignore_nsfw(modules.globals.target_path, destroy):
+            return
+        try:
+            shutil.copy2(modules.globals.target_path, modules.globals.output_path)
+        except Exception as e:
+            print("Error copying file:", str(e))
+        for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
+            update_status('Progressing...', frame_processor.NAME)
+            frame_processor.process_image(modules.globals.source_path, modules.globals.output_path, modules.globals.output_path)
+            release_resources()
+        if is_image(modules.globals.target_path):
+            update_status('Processing to image succeed!')
+        else:
+            update_status('Processing to image failed!')
+        return
+    # process image to videos
+    if modules.globals.nsfw_filter and ui.check_and_ignore_nsfw(modules.globals.target_path, destroy):
+        return
+
+    if not modules.globals.map_faces:
+        update_status('Creating temp resources...')
+        create_temp(modules.globals.target_path)
+        update_status('Extracting frames...')
+        extract_frames(modules.globals.target_path)
+
+    temp_frame_paths = get_temp_frame_paths(modules.globals.target_path)
+    for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
+        update_status('Progressing...', frame_processor.NAME)
+        frame_processor.process_video(modules.globals.source_path, temp_frame_paths)
+        release_resources()
+    # handles fps
+    if modules.globals.keep_fps:
+        update_status('Detecting fps...')
+        fps = detect_fps(modules.globals.target_path)
+        update_status(f'Creating video with {fps} fps...')
+        create_video(modules.globals.target_path, fps)
+    else:
+        update_status('Creating video with 30.0 fps...')
+        create_video(modules.globals.target_path)
+    # handle audio
+    if modules.globals.keep_audio:
+        if modules.globals.keep_fps:
+            update_status('Restoring audio...')
+        else:
+            update_status('Restoring audio might cause issues as fps are not kept...')
+        restore_audio(modules.globals.target_path, modules.globals.output_path)
+    else:
+        move_temp(modules.globals.target_path, modules.globals.output_path)
+    # clean and validate
+    clean_temp(modules.globals.target_path)
+    if is_video(modules.globals.target_path):
+        update_status('Processing to video succeed!')
+    else:
+        update_status('Processing to video failed!')
+
+
+def destroy(to_quit=True) -> None:
+    if modules.globals.target_path:
+        clean_temp(modules.globals.target_path)
+    if to_quit: quit()
+
+
+def run() -> None:
+    parse_args()
+    if not pre_check():
+        return
+    for frame_processor in get_frame_processors_modules(modules.globals.frame_processors):
+        if not frame_processor.pre_check():
+            return
+    limit_resources()
+    if modules.globals.headless:
+        start()
+    else:
+        window = ui.init(start, destroy, modules.globals.lang)
+        window.mainloop()

modules/face_analyser.py

@@ -0,0 +1,189 @@
+import os
+import shutil
+from typing import Any
+import insightface
+
+import cv2
+import numpy as np
+import modules.globals
+from tqdm import tqdm
+from modules.typing import Frame
+from modules.cluster_analysis import find_cluster_centroids, find_closest_centroid
+from modules.utilities import get_temp_directory_path, create_temp, extract_frames, clean_temp, get_temp_frame_paths
+from pathlib import Path
+
+FACE_ANALYSER = None
+
+
+def get_face_analyser() -> Any:
+    global FACE_ANALYSER
+
+    if FACE_ANALYSER is None:
+        FACE_ANALYSER = insightface.app.FaceAnalysis(name='buffalo_l', providers=modules.globals.execution_providers)
+        FACE_ANALYSER.prepare(ctx_id=0, det_size=(640, 640))
+    return FACE_ANALYSER
+
+
+def get_one_face(frame: Frame) -> Any:
+    face = get_face_analyser().get(frame)
+    try:
+        return min(face, key=lambda x: x.bbox[0])
+    except ValueError:
+        return None
+
+
+def get_many_faces(frame: Frame) -> Any:
+    try:
+        return get_face_analyser().get(frame)
+    except IndexError:
+        return None
+
+def has_valid_map() -> bool:
+    for map in modules.globals.source_target_map:
+        if "source" in map and "target" in map:
+            return True
+    return False
+
+def default_source_face() -> Any:
+    for map in modules.globals.source_target_map:
+        if "source" in map:
+            return map['source']['face']
+    return None
+
+def simplify_maps() -> Any:
+    centroids = []
+    faces = []
+    for map in modules.globals.source_target_map:
+        if "source" in map and "target" in map:
+            centroids.append(map['target']['face'].normed_embedding)
+            faces.append(map['source']['face'])
+
+    modules.globals.simple_map = {'source_faces': faces, 'target_embeddings': centroids}
+    return None
+
+def add_blank_map() -> Any:
+    try:
+        max_id = -1
+        if len(modules.globals.source_target_map) > 0:
+            max_id = max(modules.globals.source_target_map, key=lambda x: x['id'])['id']
+
+        modules.globals.source_target_map.append({
+                'id' : max_id + 1
+                })
+    except ValueError:
+        return None
+    
+def get_unique_faces_from_target_image() -> Any:
+    try:
+        modules.globals.source_target_map = []
+        target_frame = cv2.imread(modules.globals.target_path)
+        many_faces = get_many_faces(target_frame)
+        i = 0
+
+        for face in many_faces:
+            x_min, y_min, x_max, y_max = face['bbox']
+            modules.globals.source_target_map.append({
+                'id' : i, 
+                'target' : {
+                            'cv2' : target_frame[int(y_min):int(y_max), int(x_min):int(x_max)],
+                            'face' : face
+                            }
+                })
+            i = i + 1
+    except ValueError:
+        return None
+    
+    
+def get_unique_faces_from_target_video() -> Any:
+    try:
+        modules.globals.source_target_map = []
+        frame_face_embeddings = []
+        face_embeddings = []
+    
+        print('Creating temp resources...')
+        clean_temp(modules.globals.target_path)
+        create_temp(modules.globals.target_path)
+        print('Extracting frames...')
+        extract_frames(modules.globals.target_path)
+
+        temp_frame_paths = get_temp_frame_paths(modules.globals.target_path)
+
+        i = 0
+        for temp_frame_path in tqdm(temp_frame_paths, desc="Extracting face embeddings from frames"):
+            temp_frame = cv2.imread(temp_frame_path)
+            many_faces = get_many_faces(temp_frame)
+
+            for face in many_faces:
+                face_embeddings.append(face.normed_embedding)
+            
+            frame_face_embeddings.append({'frame': i, 'faces': many_faces, 'location': temp_frame_path})
+            i += 1
+
+        centroids = find_cluster_centroids(face_embeddings)
+
+        for frame in frame_face_embeddings:
+            for face in frame['faces']:
+                closest_centroid_index, _ = find_closest_centroid(centroids, face.normed_embedding)
+                face['target_centroid'] = closest_centroid_index
+
+        for i in range(len(centroids)):
+            modules.globals.source_target_map.append({
+                'id' : i
+            })
+
+            temp = []
+            for frame in tqdm(frame_face_embeddings, desc=f"Mapping frame embeddings to centroids-{i}"):
+                temp.append({'frame': frame['frame'], 'faces': [face for face in frame['faces'] if face['target_centroid'] == i], 'location': frame['location']})
+
+            modules.globals.source_target_map[i]['target_faces_in_frame'] = temp
+
+        # dump_faces(centroids, frame_face_embeddings)
+        default_target_face()
+    except ValueError:
+        return None
+    
+
+def default_target_face():
+    for map in modules.globals.source_target_map:
+        best_face = None
+        best_frame = None
+        for frame in map['target_faces_in_frame']:
+            if len(frame['faces']) > 0:
+                best_face = frame['faces'][0]
+                best_frame = frame
+                break
+
+        for frame in map['target_faces_in_frame']:
+            for face in frame['faces']:
+                if face['det_score'] > best_face['det_score']:
+                    best_face = face
+                    best_frame = frame
+
+        x_min, y_min, x_max, y_max = best_face['bbox']
+
+        target_frame = cv2.imread(best_frame['location'])
+        map['target'] = {
+                        'cv2' : target_frame[int(y_min):int(y_max), int(x_min):int(x_max)],
+                        'face' : best_face
+                        }
+
+
+def dump_faces(centroids: Any, frame_face_embeddings: list):
+    temp_directory_path = get_temp_directory_path(modules.globals.target_path)
+
+    for i in range(len(centroids)):
+        if os.path.exists(temp_directory_path + f"/{i}") and os.path.isdir(temp_directory_path + f"/{i}"):
+            shutil.rmtree(temp_directory_path + f"/{i}")
+        Path(temp_directory_path + f"/{i}").mkdir(parents=True, exist_ok=True)
+
+        for frame in tqdm(frame_face_embeddings, desc=f"Copying faces to temp/./{i}"):
+            temp_frame = cv2.imread(frame['location'])
+
+            j = 0
+            for face in frame['faces']:
+                if face['target_centroid'] == i:
+                    x_min, y_min, x_max, y_max = face['bbox']
+
+                    if temp_frame[int(y_min):int(y_max), int(x_min):int(x_max)].size > 0:
+                        cv2.imwrite(temp_directory_path + f"/{i}/{frame['frame']}_{j}.png", temp_frame[int(y_min):int(y_max), int(x_min):int(x_max)])
+                j += 1

modules/gettext.py

@@ -0,0 +1,26 @@
+import json
+from pathlib import Path
+
+class LanguageManager:
+    def __init__(self, default_language="en"):
+        self.current_language = default_language
+        self.translations = {}
+        self.load_language(default_language)
+
+    def load_language(self, language_code) -> bool:
+        """load language file"""
+        if language_code == "en":
+            return True
+        try:
+            file_path = Path(__file__).parent.parent / f"locales/{language_code}.json"
+            with open(file_path, "r", encoding="utf-8") as file:
+                self.translations = json.load(file)
+            self.current_language = language_code
+            return True
+        except FileNotFoundError:
+            print(f"Language file not found: {language_code}")
+            return False
+
+    def _(self, key, default=None) -> str:
+        """get translate text"""
+        return self.translations.get(key, default if default else key)

modules/globals.py

@@ -0,0 +1,43 @@
+import os
+from typing import List, Dict, Any
+
+ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
+WORKFLOW_DIR = os.path.join(ROOT_DIR, "workflow")
+
+file_types = [
+    ("Image", ("*.png", "*.jpg", "*.jpeg", "*.gif", "*.bmp")),
+    ("Video", ("*.mp4", "*.mkv")),
+]
+
+source_target_map = []
+simple_map = {}
+
+source_path = None
+target_path = None
+output_path = None
+frame_processors: List[str] = []
+keep_fps = True
+keep_audio = True
+keep_frames = False
+many_faces = False
+map_faces = False
+color_correction = False  # New global variable for color correction toggle
+nsfw_filter = False
+video_encoder = None
+video_quality = None
+live_mirror = False
+live_resizable = True
+max_memory = None
+execution_providers: List[str] = []
+execution_threads = None
+headless = None
+log_level = "error"
+fp_ui: Dict[str, bool] = {"face_enhancer": False}
+camera_input_combobox = None
+webcam_preview_running = False
+show_fps = False
+mouth_mask = False
+show_mouth_mask_box = False
+mask_feather_ratio = 8
+mask_down_size = 0.50
+mask_size = 1

modules/metadata.py

@@ -0,0 +1,3 @@
+name = 'Deep-Live-Cam'
+version = '1.8'
+edition = 'GitHub Edition'

modules/predicter.py

@@ -0,0 +1,36 @@
+import numpy
+import opennsfw2
+from PIL import Image
+import cv2  # Add OpenCV import
+import modules.globals  # Import globals to access the color correction toggle
+
+from modules.typing import Frame
+
+MAX_PROBABILITY = 0.85
+
+# Preload the model once for efficiency
+model = None
+
+def predict_frame(target_frame: Frame) -> bool:
+    # Convert the frame to RGB before processing if color correction is enabled
+    if modules.globals.color_correction:
+        target_frame = cv2.cvtColor(target_frame, cv2.COLOR_BGR2RGB)
+        
+    image = Image.fromarray(target_frame)
+    image = opennsfw2.preprocess_image(image, opennsfw2.Preprocessing.YAHOO)
+    global model
+    if model is None: 
+        model = opennsfw2.make_open_nsfw_model()
+        
+    views = numpy.expand_dims(image, axis=0)
+    _, probability = model.predict(views)[0]
+    return probability > MAX_PROBABILITY
+
+
+def predict_image(target_path: str) -> bool:
+    return opennsfw2.predict_image(target_path) > MAX_PROBABILITY
+
+
+def predict_video(target_path: str) -> bool:
+    _, probabilities = opennsfw2.predict_video_frames(video_path=target_path, frame_interval=100)
+    return any(probability > MAX_PROBABILITY for probability in probabilities)

modules/processors/frame/core.py

@@ -0,0 +1,84 @@
+import sys
+import importlib
+from concurrent.futures import ThreadPoolExecutor
+from types import ModuleType
+from typing import Any, List, Callable
+from tqdm import tqdm
+
+import modules
+import modules.globals                   
+
+FRAME_PROCESSORS_MODULES: List[ModuleType] = []
+FRAME_PROCESSORS_INTERFACE = [
+    'pre_check',
+    'pre_start',
+    'process_frame',
+    'process_image',
+    'process_video'
+]
+
+
+def load_frame_processor_module(frame_processor: str) -> Any:
+    try:
+        frame_processor_module = importlib.import_module(f'modules.processors.frame.{frame_processor}')
+        for method_name in FRAME_PROCESSORS_INTERFACE:
+            if not hasattr(frame_processor_module, method_name):
+                sys.exit()
+    except ImportError:
+        print(f"Frame processor {frame_processor} not found")
+        sys.exit()
+    return frame_processor_module
+
+
+def get_frame_processors_modules(frame_processors: List[str]) -> List[ModuleType]:
+    global FRAME_PROCESSORS_MODULES
+
+    if not FRAME_PROCESSORS_MODULES:
+        for frame_processor in frame_processors:
+            frame_processor_module = load_frame_processor_module(frame_processor)
+            FRAME_PROCESSORS_MODULES.append(frame_processor_module)
+    set_frame_processors_modules_from_ui(frame_processors)
+    return FRAME_PROCESSORS_MODULES
+
+def set_frame_processors_modules_from_ui(frame_processors: List[str]) -> None:
+    global FRAME_PROCESSORS_MODULES
+    current_processor_names = [proc.__name__.split('.')[-1] for proc in FRAME_PROCESSORS_MODULES]
+
+    for frame_processor, state in modules.globals.fp_ui.items():
+        if state == True and frame_processor not in current_processor_names:
+            try:
+                frame_processor_module = load_frame_processor_module(frame_processor)
+                FRAME_PROCESSORS_MODULES.append(frame_processor_module)
+                if frame_processor not in modules.globals.frame_processors:
+                     modules.globals.frame_processors.append(frame_processor)
+            except SystemExit:
+                 print(f"Warning: Failed to load frame processor {frame_processor} requested by UI state.")
+            except Exception as e:
+                 print(f"Warning: Error loading frame processor {frame_processor} requested by UI state: {e}")
+
+        elif state == False and frame_processor in current_processor_names:
+            try:
+                module_to_remove = next((mod for mod in FRAME_PROCESSORS_MODULES if mod.__name__.endswith(f'.{frame_processor}')), None)
+                if module_to_remove:
+                    FRAME_PROCESSORS_MODULES.remove(module_to_remove)
+                if frame_processor in modules.globals.frame_processors:
+                    modules.globals.frame_processors.remove(frame_processor)
+            except Exception as e:
+                 print(f"Warning: Error removing frame processor {frame_processor}: {e}")
+
+def multi_process_frame(source_path: str, temp_frame_paths: List[str], process_frames: Callable[[str, List[str], Any], None], progress: Any = None) -> None:
+    with ThreadPoolExecutor(max_workers=modules.globals.execution_threads) as executor:
+        futures = []
+        for path in temp_frame_paths:
+            future = executor.submit(process_frames, source_path, [path], progress)
+            futures.append(future)
+        for future in futures:
+            future.result()
+
+
+def process_video(source_path: str, frame_paths: list[str], process_frames: Callable[[str, List[str], Any], None]) -> None:
+    progress_bar_format = '{l_bar}{bar}| {n_fmt}/{total_fmt} [{elapsed}<{remaining}, {rate_fmt}{postfix}]'
+    total = len(frame_paths)
+    with tqdm(total=total, desc='Processing', unit='frame', dynamic_ncols=True, bar_format=progress_bar_format) as progress:
+        progress.set_postfix({'execution_providers': modules.globals.execution_providers, 'execution_threads': modules.globals.execution_threads, 'max_memory': modules.globals.max_memory})
+        multi_process_frame(source_path, frame_paths, process_frames, progress)

modules/processors/frame/face_enhancer.py

@@ -0,0 +1,130 @@
+from typing import Any, List
+import cv2
+import threading
+import gfpgan
+import os
+
+import modules.globals
+import modules.processors.frame.core
+from modules.core import update_status
+from modules.face_analyser import get_one_face
+from modules.typing import Frame, Face
+import platform
+import torch
+from modules.utilities import (
+    conditional_download,
+    is_image,
+    is_video,
+)
+
+FACE_ENHANCER = None
+THREAD_SEMAPHORE = threading.Semaphore()
+THREAD_LOCK = threading.Lock()
+NAME = "DLC.FACE-ENHANCER"
+
+abs_dir = os.path.dirname(os.path.abspath(__file__))
+models_dir = os.path.join(
+    os.path.dirname(os.path.dirname(os.path.dirname(abs_dir))), "models"
+)
+
+
+def pre_check() -> bool:
+    download_directory_path = models_dir
+    conditional_download(
+        download_directory_path,
+        [
+            "https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth"
+        ],
+    )
+    return True
+
+
+def pre_start() -> bool:
+    if not is_image(modules.globals.target_path) and not is_video(
+        modules.globals.target_path
+    ):
+        update_status("Select an image or video for target path.", NAME)
+        return False
+    return True
+
+
+TENSORRT_AVAILABLE = False
+try:
+    import torch_tensorrt
+    TENSORRT_AVAILABLE = True
+except ImportError as im:
+    print(f"TensorRT is not available: {im}")
+    pass
+except Exception as e:
+    print(f"TensorRT is not available: {e}")
+    pass
+
+def get_face_enhancer() -> Any:
+    global FACE_ENHANCER
+
+    with THREAD_LOCK:
+        if FACE_ENHANCER is None:
+            model_path = os.path.join(models_dir, "GFPGANv1.4.pth")
+            
+            selected_device = None
+            device_priority = []
+
+            if TENSORRT_AVAILABLE and torch.cuda.is_available():
+                selected_device = torch.device("cuda")
+                device_priority.append("TensorRT+CUDA")
+            elif torch.cuda.is_available():
+                selected_device = torch.device("cuda")
+                device_priority.append("CUDA")
+            elif torch.backends.mps.is_available() and platform.system() == "Darwin":
+                selected_device = torch.device("mps")
+                device_priority.append("MPS")
+            elif not torch.cuda.is_available():
+                selected_device = torch.device("cpu")
+                device_priority.append("CPU")
+            
+            FACE_ENHANCER = gfpgan.GFPGANer(model_path=model_path, upscale=1, device=selected_device)
+
+            # for debug:
+            print(f"Selected device: {selected_device} and device priority: {device_priority}")
+    return FACE_ENHANCER
+
+
+def enhance_face(temp_frame: Frame) -> Frame:
+    with THREAD_SEMAPHORE:
+        _, _, temp_frame = get_face_enhancer().enhance(temp_frame, paste_back=True)
+    return temp_frame
+
+
+def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
+    target_face = get_one_face(temp_frame)
+    if target_face:
+        temp_frame = enhance_face(temp_frame)
+    return temp_frame
+
+
+def process_frames(
+    source_path: str, temp_frame_paths: List[str], progress: Any = None
+) -> None:
+    for temp_frame_path in temp_frame_paths:
+        temp_frame = cv2.imread(temp_frame_path)
+        result = process_frame(None, temp_frame)
+        cv2.imwrite(temp_frame_path, result)
+        if progress:
+            progress.update(1)
+
+
+def process_image(source_path: str, target_path: str, output_path: str) -> None:
+    target_frame = cv2.imread(target_path)
+    result = process_frame(None, target_frame)
+    cv2.imwrite(output_path, result)
+
+
+def process_video(source_path: str, temp_frame_paths: List[str]) -> None:
+    modules.processors.frame.core.process_video(None, temp_frame_paths, process_frames)
+
+
+def process_frame_v2(temp_frame: Frame) -> Frame:
+    target_face = get_one_face(temp_frame)
+    if target_face:
+        temp_frame = enhance_face(temp_frame)
+    return temp_frame

modules/processors/frame/face_swapper.py

@@ -0,0 +1,622 @@
+from typing import Any, List
+import cv2
+import insightface
+import threading
+import numpy as np
+import modules.globals
+import logging
+import modules.processors.frame.core
+from modules.core import update_status
+from modules.face_analyser import get_one_face, get_many_faces, default_source_face
+from modules.typing import Face, Frame
+from modules.utilities import (
+    conditional_download,
+    is_image,
+    is_video,
+)
+from modules.cluster_analysis import find_closest_centroid
+import os
+
+FACE_SWAPPER = None
+THREAD_LOCK = threading.Lock()
+NAME = "DLC.FACE-SWAPPER"
+
+abs_dir = os.path.dirname(os.path.abspath(__file__))
+models_dir = os.path.join(
+    os.path.dirname(os.path.dirname(os.path.dirname(abs_dir))), "models"
+)
+
+
+def pre_check() -> bool:
+    download_directory_path = abs_dir
+    conditional_download(
+        download_directory_path,
+        [
+            "https://huggingface.co/hacksider/deep-live-cam/blob/main/inswapper_128_fp16.onnx"
+        ],
+    )
+    return True
+
+
+def pre_start() -> bool:
+    if not modules.globals.map_faces and not is_image(modules.globals.source_path):
+        update_status("Select an image for source path.", NAME)
+        return False
+    elif not modules.globals.map_faces and not get_one_face(
+        cv2.imread(modules.globals.source_path)
+    ):
+        update_status("No face in source path detected.", NAME)
+        return False
+    if not is_image(modules.globals.target_path) and not is_video(
+        modules.globals.target_path
+    ):
+        update_status("Select an image or video for target path.", NAME)
+        return False
+    return True
+
+
+def get_face_swapper() -> Any:
+    global FACE_SWAPPER
+
+    with THREAD_LOCK:
+        if FACE_SWAPPER is None:
+            model_path = os.path.join(models_dir, "inswapper_128_fp16.onnx")
+            FACE_SWAPPER = insightface.model_zoo.get_model(
+                model_path, providers=modules.globals.execution_providers
+            )
+    return FACE_SWAPPER
+
+
+def swap_face(source_face: Face, target_face: Face, temp_frame: Frame) -> Frame:
+    face_swapper = get_face_swapper()
+
+    # Apply the face swap
+    swapped_frame = face_swapper.get(
+        temp_frame, target_face, source_face, paste_back=True
+    )
+
+    if modules.globals.mouth_mask:
+        # Create a mask for the target face
+        face_mask = create_face_mask(target_face, temp_frame)
+
+        # Create the mouth mask
+        mouth_mask, mouth_cutout, mouth_box, lower_lip_polygon = (
+            create_lower_mouth_mask(target_face, temp_frame)
+        )
+
+        # Apply the mouth area
+        swapped_frame = apply_mouth_area(
+            swapped_frame, mouth_cutout, mouth_box, face_mask, lower_lip_polygon
+        )
+
+        if modules.globals.show_mouth_mask_box:
+            mouth_mask_data = (mouth_mask, mouth_cutout, mouth_box, lower_lip_polygon)
+            swapped_frame = draw_mouth_mask_visualization(
+                swapped_frame, target_face, mouth_mask_data
+            )
+
+    return swapped_frame
+
+
+def process_frame(source_face: Face, temp_frame: Frame) -> Frame:
+    if modules.globals.color_correction:
+        temp_frame = cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB)
+
+    if modules.globals.many_faces:
+        many_faces = get_many_faces(temp_frame)
+        if many_faces:
+            for target_face in many_faces:
+                if source_face and target_face:
+                    temp_frame = swap_face(source_face, target_face, temp_frame)
+                else:
+                    print("Face detection failed for target/source.")
+    else:
+        target_face = get_one_face(temp_frame)
+        if target_face and source_face:
+            temp_frame = swap_face(source_face, target_face, temp_frame)
+        else:
+            logging.error("Face detection failed for target or source.")
+    return temp_frame
+
+
+
+def process_frame_v2(temp_frame: Frame, temp_frame_path: str = "") -> Frame:
+    if is_image(modules.globals.target_path):
+        if modules.globals.many_faces:
+            source_face = default_source_face()
+            for map in modules.globals.source_target_map:
+                target_face = map["target"]["face"]
+                temp_frame = swap_face(source_face, target_face, temp_frame)
+
+        elif not modules.globals.many_faces:
+            for map in modules.globals.source_target_map:
+                if "source" in map:
+                    source_face = map["source"]["face"]
+                    target_face = map["target"]["face"]
+                    temp_frame = swap_face(source_face, target_face, temp_frame)
+
+    elif is_video(modules.globals.target_path):
+        if modules.globals.many_faces:
+            source_face = default_source_face()
+            for map in modules.globals.source_target_map:
+                target_frame = [
+                    f
+                    for f in map["target_faces_in_frame"]
+                    if f["location"] == temp_frame_path
+                ]
+
+                for frame in target_frame:
+                    for target_face in frame["faces"]:
+                        temp_frame = swap_face(source_face, target_face, temp_frame)
+
+        elif not modules.globals.many_faces:
+            for map in modules.globals.source_target_map:
+                if "source" in map:
+                    target_frame = [
+                        f
+                        for f in map["target_faces_in_frame"]
+                        if f["location"] == temp_frame_path
+                    ]
+                    source_face = map["source"]["face"]
+
+                    for frame in target_frame:
+                        for target_face in frame["faces"]:
+                            temp_frame = swap_face(source_face, target_face, temp_frame)
+
+    else:
+        detected_faces = get_many_faces(temp_frame)
+        if modules.globals.many_faces:
+            if detected_faces:
+                source_face = default_source_face()
+                for target_face in detected_faces:
+                    temp_frame = swap_face(source_face, target_face, temp_frame)
+
+        elif not modules.globals.many_faces:
+            if detected_faces:
+                if len(detected_faces) <= len(
+                    modules.globals.simple_map["target_embeddings"]
+                ):
+                    for detected_face in detected_faces:
+                        closest_centroid_index, _ = find_closest_centroid(
+                            modules.globals.simple_map["target_embeddings"],
+                            detected_face.normed_embedding,
+                        )
+
+                        temp_frame = swap_face(
+                            modules.globals.simple_map["source_faces"][
+                                closest_centroid_index
+                            ],
+                            detected_face,
+                            temp_frame,
+                        )
+                else:
+                    detected_faces_centroids = []
+                    for face in detected_faces:
+                        detected_faces_centroids.append(face.normed_embedding)
+                    i = 0
+                    for target_embedding in modules.globals.simple_map[
+                        "target_embeddings"
+                    ]:
+                        closest_centroid_index, _ = find_closest_centroid(
+                            detected_faces_centroids, target_embedding
+                        )
+
+                        temp_frame = swap_face(
+                            modules.globals.simple_map["source_faces"][i],
+                            detected_faces[closest_centroid_index],
+                            temp_frame,
+                        )
+                        i += 1
+    return temp_frame
+
+
+def process_frames(
+    source_path: str, temp_frame_paths: List[str], progress: Any = None
+) -> None:
+    if not modules.globals.map_faces:
+        source_face = get_one_face(cv2.imread(source_path))
+        for temp_frame_path in temp_frame_paths:
+            temp_frame = cv2.imread(temp_frame_path)
+            try:
+                result = process_frame(source_face, temp_frame)
+                cv2.imwrite(temp_frame_path, result)
+            except Exception as exception:
+                print(exception)
+                pass
+            if progress:
+                progress.update(1)
+    else:
+        for temp_frame_path in temp_frame_paths:
+            temp_frame = cv2.imread(temp_frame_path)
+            try:
+                result = process_frame_v2(temp_frame, temp_frame_path)
+                cv2.imwrite(temp_frame_path, result)
+            except Exception as exception:
+                print(exception)
+                pass
+            if progress:
+                progress.update(1)
+
+
+def process_image(source_path: str, target_path: str, output_path: str) -> None:
+    if not modules.globals.map_faces:
+        source_face = get_one_face(cv2.imread(source_path))
+        target_frame = cv2.imread(target_path)
+        result = process_frame(source_face, target_frame)
+        cv2.imwrite(output_path, result)
+    else:
+        if modules.globals.many_faces:
+            update_status(
+                "Many faces enabled. Using first source image. Progressing...", NAME
+            )
+        target_frame = cv2.imread(output_path)
+        result = process_frame_v2(target_frame)
+        cv2.imwrite(output_path, result)
+
+
+def process_video(source_path: str, temp_frame_paths: List[str]) -> None:
+    if modules.globals.map_faces and modules.globals.many_faces:
+        update_status(
+            "Many faces enabled. Using first source image. Progressing...", NAME
+        )
+    modules.processors.frame.core.process_video(
+        source_path, temp_frame_paths, process_frames
+    )
+
+
+def create_lower_mouth_mask(
+    face: Face, frame: Frame
+) -> (np.ndarray, np.ndarray, tuple, np.ndarray):
+    mask = np.zeros(frame.shape[:2], dtype=np.uint8)
+    mouth_cutout = None
+    landmarks = face.landmark_2d_106
+    if landmarks is not None:
+        #                  0  1  2  3  4  5  6  7  8  9  10 11 12 13 14 15 16 17 18 19 20
+        lower_lip_order = [
+            65,
+            66,
+            62,
+            70,
+            69,
+            18,
+            19,
+            20,
+            21,
+            22,
+            23,
+            24,
+            0,
+            8,
+            7,
+            6,
+            5,
+            4,
+            3,
+            2,
+            65,
+        ]
+        lower_lip_landmarks = landmarks[lower_lip_order].astype(
+            np.float32
+        )  # Use float for precise calculations
+
+        # Calculate the center of the landmarks
+        center = np.mean(lower_lip_landmarks, axis=0)
+
+        # Expand the landmarks outward
+        expansion_factor = (
+            1 + modules.globals.mask_down_size
+        )  # Adjust this for more or less expansion
+        expanded_landmarks = (lower_lip_landmarks - center) * expansion_factor + center
+
+        # Extend the top lip part
+        toplip_indices = [
+            20,
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+        ]  # Indices for landmarks 2, 65, 66, 62, 70, 69, 18
+        toplip_extension = (
+            modules.globals.mask_size * 0.5
+        )  # Adjust this factor to control the extension
+        for idx in toplip_indices:
+            direction = expanded_landmarks[idx] - center
+            direction = direction / np.linalg.norm(direction)
+            expanded_landmarks[idx] += direction * toplip_extension
+
+        # Extend the bottom part (chin area)
+        chin_indices = [
+            11,
+            12,
+            13,
+            14,
+            15,
+            16,
+        ]  # Indices for landmarks 21, 22, 23, 24, 0, 8
+        chin_extension = 2 * 0.2  # Adjust this factor to control the extension
+        for idx in chin_indices:
+            expanded_landmarks[idx][1] += (
+                expanded_landmarks[idx][1] - center[1]
+            ) * chin_extension
+
+        # Convert back to integer coordinates
+        expanded_landmarks = expanded_landmarks.astype(np.int32)
+
+        # Calculate bounding box for the expanded lower mouth
+        min_x, min_y = np.min(expanded_landmarks, axis=0)
+        max_x, max_y = np.max(expanded_landmarks, axis=0)
+
+        # Add some padding to the bounding box
+        padding = int((max_x - min_x) * 0.1)  # 10% padding
+        min_x = max(0, min_x - padding)
+        min_y = max(0, min_y - padding)
+        max_x = min(frame.shape[1], max_x + padding)
+        max_y = min(frame.shape[0], max_y + padding)
+
+        # Ensure the bounding box dimensions are valid
+        if max_x <= min_x or max_y <= min_y:
+            if (max_x - min_x) <= 1:
+                max_x = min_x + 1
+            if (max_y - min_y) <= 1:
+                max_y = min_y + 1
+
+        # Create the mask
+        mask_roi = np.zeros((max_y - min_y, max_x - min_x), dtype=np.uint8)
+        cv2.fillPoly(mask_roi, [expanded_landmarks - [min_x, min_y]], 255)
+
+        # Apply Gaussian blur to soften the mask edges
+        mask_roi = cv2.GaussianBlur(mask_roi, (15, 15), 5)
+
+        # Place the mask ROI in the full-sized mask
+        mask[min_y:max_y, min_x:max_x] = mask_roi
+
+        # Extract the masked area from the frame
+        mouth_cutout = frame[min_y:max_y, min_x:max_x].copy()
+
+        # Return the expanded lower lip polygon in original frame coordinates
+        lower_lip_polygon = expanded_landmarks
+
+    return mask, mouth_cutout, (min_x, min_y, max_x, max_y), lower_lip_polygon
+
+
+def draw_mouth_mask_visualization(
+    frame: Frame, face: Face, mouth_mask_data: tuple
+) -> Frame:
+    landmarks = face.landmark_2d_106
+    if landmarks is not None and mouth_mask_data is not None:
+        mask, mouth_cutout, (min_x, min_y, max_x, max_y), lower_lip_polygon = (
+            mouth_mask_data
+        )
+
+        vis_frame = frame.copy()
+
+        # Ensure coordinates are within frame bounds
+        height, width = vis_frame.shape[:2]
+        min_x, min_y = max(0, min_x), max(0, min_y)
+        max_x, max_y = min(width, max_x), min(height, max_y)
+
+        # Adjust mask to match the region size
+        mask_region = mask[0 : max_y - min_y, 0 : max_x - min_x]
+
+        # Remove the color mask overlay
+        # color_mask = cv2.applyColorMap((mask_region * 255).astype(np.uint8), cv2.COLORMAP_JET)
+
+        # Ensure shapes match before blending
+        vis_region = vis_frame[min_y:max_y, min_x:max_x]
+        # Remove blending with color_mask
+        # if vis_region.shape[:2] == color_mask.shape[:2]:
+        #     blended = cv2.addWeighted(vis_region, 0.7, color_mask, 0.3, 0)
+        #     vis_frame[min_y:max_y, min_x:max_x] = blended
+
+        # Draw the lower lip polygon
+        cv2.polylines(vis_frame, [lower_lip_polygon], True, (0, 255, 0), 2)
+
+        # Remove the red box
+        # cv2.rectangle(vis_frame, (min_x, min_y), (max_x, max_y), (0, 0, 255), 2)
+
+        # Visualize the feathered mask
+        feather_amount = max(
+            1,
+            min(
+                30,
+                (max_x - min_x) // modules.globals.mask_feather_ratio,
+                (max_y - min_y) // modules.globals.mask_feather_ratio,
+            ),
+        )
+        # Ensure kernel size is odd
+        kernel_size = 2 * feather_amount + 1
+        feathered_mask = cv2.GaussianBlur(
+            mask_region.astype(float), (kernel_size, kernel_size), 0
+        )
+        feathered_mask = (feathered_mask / feathered_mask.max() * 255).astype(np.uint8)
+        # Remove the feathered mask color overlay
+        # color_feathered_mask = cv2.applyColorMap(feathered_mask, cv2.COLORMAP_VIRIDIS)
+
+        # Ensure shapes match before blending feathered mask
+        # if vis_region.shape == color_feathered_mask.shape:
+        #     blended_feathered = cv2.addWeighted(vis_region, 0.7, color_feathered_mask, 0.3, 0)
+        #     vis_frame[min_y:max_y, min_x:max_x] = blended_feathered
+
+        # Add labels
+        cv2.putText(
+            vis_frame,
+            "Lower Mouth Mask",
+            (min_x, min_y - 10),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.5,
+            (255, 255, 255),
+            1,
+        )
+        cv2.putText(
+            vis_frame,
+            "Feathered Mask",
+            (min_x, max_y + 20),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.5,
+            (255, 255, 255),
+            1,
+        )
+
+        return vis_frame
+    return frame
+
+
+def apply_mouth_area(
+    frame: np.ndarray,
+    mouth_cutout: np.ndarray,
+    mouth_box: tuple,
+    face_mask: np.ndarray,
+    mouth_polygon: np.ndarray,
+) -> np.ndarray:
+    min_x, min_y, max_x, max_y = mouth_box
+    box_width = max_x - min_x
+    box_height = max_y - min_y
+
+    if (
+        mouth_cutout is None
+        or box_width is None
+        or box_height is None
+        or face_mask is None
+        or mouth_polygon is None
+    ):
+        return frame
+
+    try:
+        resized_mouth_cutout = cv2.resize(mouth_cutout, (box_width, box_height))
+        roi = frame[min_y:max_y, min_x:max_x]
+
+        if roi.shape != resized_mouth_cutout.shape:
+            resized_mouth_cutout = cv2.resize(
+                resized_mouth_cutout, (roi.shape[1], roi.shape[0])
+            )
+
+        color_corrected_mouth = apply_color_transfer(resized_mouth_cutout, roi)
+
+        # Use the provided mouth polygon to create the mask
+        polygon_mask = np.zeros(roi.shape[:2], dtype=np.uint8)
+        adjusted_polygon = mouth_polygon - [min_x, min_y]
+        cv2.fillPoly(polygon_mask, [adjusted_polygon], 255)
+
+        # Apply feathering to the polygon mask
+        feather_amount = min(
+            30,
+            box_width // modules.globals.mask_feather_ratio,
+            box_height // modules.globals.mask_feather_ratio,
+        )
+        feathered_mask = cv2.GaussianBlur(
+            polygon_mask.astype(float), (0, 0), feather_amount
+        )
+        feathered_mask = feathered_mask / feathered_mask.max()
+
+        face_mask_roi = face_mask[min_y:max_y, min_x:max_x]
+        combined_mask = feathered_mask * (face_mask_roi / 255.0)
+
+        combined_mask = combined_mask[:, :, np.newaxis]
+        blended = (
+            color_corrected_mouth * combined_mask + roi * (1 - combined_mask)
+        ).astype(np.uint8)
+
+        # Apply face mask to blended result
+        face_mask_3channel = (
+            np.repeat(face_mask_roi[:, :, np.newaxis], 3, axis=2) / 255.0
+        )
+        final_blend = blended * face_mask_3channel + roi * (1 - face_mask_3channel)
+
+        frame[min_y:max_y, min_x:max_x] = final_blend.astype(np.uint8)
+    except Exception as e:
+        pass
+
+    return frame
+
+
+def create_face_mask(face: Face, frame: Frame) -> np.ndarray:
+    mask = np.zeros(frame.shape[:2], dtype=np.uint8)
+    landmarks = face.landmark_2d_106
+    if landmarks is not None:
+        # Convert landmarks to int32
+        landmarks = landmarks.astype(np.int32)
+
+        # Extract facial features
+        right_side_face = landmarks[0:16]
+        left_side_face = landmarks[17:32]
+        right_eye = landmarks[33:42]
+        right_eye_brow = landmarks[43:51]
+        left_eye = landmarks[87:96]
+        left_eye_brow = landmarks[97:105]
+
+        # Calculate forehead extension
+        right_eyebrow_top = np.min(right_eye_brow[:, 1])
+        left_eyebrow_top = np.min(left_eye_brow[:, 1])
+        eyebrow_top = min(right_eyebrow_top, left_eyebrow_top)
+
+        face_top = np.min([right_side_face[0, 1], left_side_face[-1, 1]])
+        forehead_height = face_top - eyebrow_top
+        extended_forehead_height = int(forehead_height * 5.0)  # Extend by 50%
+
+        # Create forehead points
+        forehead_left = right_side_face[0].copy()
+        forehead_right = left_side_face[-1].copy()
+        forehead_left[1] -= extended_forehead_height
+        forehead_right[1] -= extended_forehead_height
+
+        # Combine all points to create the face outline
+        face_outline = np.vstack(
+            [
+                [forehead_left],
+                right_side_face,
+                left_side_face[
+                    ::-1
+                ],  # Reverse left side to create a continuous outline
+                [forehead_right],
+            ]
+        )
+
+        # Calculate padding
+        padding = int(
+            np.linalg.norm(right_side_face[0] - left_side_face[-1]) * 0.05
+        )  # 5% of face width
+
+        # Create a slightly larger convex hull for padding
+        hull = cv2.convexHull(face_outline)
+        hull_padded = []
+        for point in hull:
+            x, y = point[0]
+            center = np.mean(face_outline, axis=0)
+            direction = np.array([x, y]) - center
+            direction = direction / np.linalg.norm(direction)
+            padded_point = np.array([x, y]) + direction * padding
+            hull_padded.append(padded_point)
+
+        hull_padded = np.array(hull_padded, dtype=np.int32)
+
+        # Fill the padded convex hull
+        cv2.fillConvexPoly(mask, hull_padded, 255)
+
+        # Smooth the mask edges
+        mask = cv2.GaussianBlur(mask, (5, 5), 3)
+
+    return mask
+
+
+def apply_color_transfer(source, target):
+    """
+    Apply color transfer from target to source image
+    """
+    source = cv2.cvtColor(source, cv2.COLOR_BGR2LAB).astype("float32")
+    target = cv2.cvtColor(target, cv2.COLOR_BGR2LAB).astype("float32")
+
+    source_mean, source_std = cv2.meanStdDev(source)
+    target_mean, target_std = cv2.meanStdDev(target)
+
+    # Reshape mean and std to be broadcastable
+    source_mean = source_mean.reshape(1, 1, 3)
+    source_std = source_std.reshape(1, 1, 3)
+    target_mean = target_mean.reshape(1, 1, 3)
+    target_std = target_std.reshape(1, 1, 3)
+
+    # Perform the color transfer
+    source = (source - source_mean) * (target_std / source_std) + target_mean
+
+    return cv2.cvtColor(np.clip(source, 0, 255).astype("uint8"), cv2.COLOR_LAB2BGR)

modules/typing.py

@@ -0,0 +1,7 @@
+from typing import Any
+
+from insightface.app.common import Face
+import numpy
+
+Face = Face
+Frame = numpy.ndarray[Any, Any]

modules/ui.json

@@ -0,0 +1,158 @@
+{
+  "CTk": {
+    "fg_color": ["gray95", "gray10"]
+  },
+  "CTkToplevel": {
+    "fg_color": ["gray95", "gray10"]
+  },
+  "CTkFrame": {
+    "corner_radius": 0,
+    "border_width": 0,
+    "fg_color": ["gray90", "gray13"],
+    "top_fg_color": ["gray85", "gray16"],
+    "border_color": ["gray65", "gray28"]
+  },
+  "CTkButton": {
+    "corner_radius": 0,
+    "border_width": 0,
+    "fg_color": ["#2aa666", "#1f538d"],
+    "hover_color": ["#3cb666", "#14375e"],
+    "border_color": ["#3e4a40", "#949A9F"],
+    "text_color": ["#f3faf6", "#f3faf6"],
+    "text_color_disabled": ["gray74", "gray60"]
+  },
+  "CTkLabel": {
+    "corner_radius": 0,
+    "fg_color": "transparent",
+    "text_color": ["gray14", "gray84"]
+  },
+  "CTkEntry": {
+    "corner_radius": 0,
+    "border_width": 2,
+    "fg_color": ["#F9F9FA", "#343638"],
+    "border_color": ["#979DA2", "#565B5E"],
+    "text_color": ["gray14", "gray84"],
+    "placeholder_text_color": ["gray52", "gray62"]
+  },
+  "CTkCheckbox": {
+    "corner_radius": 0,
+    "border_width": 3,
+    "fg_color": ["#2aa666", "#1f538d"],
+    "border_color": ["#3e4a40", "#949A9F"],
+    "hover_color": ["#3cb666", "#14375e"],
+    "checkmark_color": ["#f3faf6", "gray90"],
+    "text_color": ["gray14", "gray84"],
+    "text_color_disabled": ["gray60", "gray45"]
+  },
+  "CTkSwitch": {
+    "corner_radius": 1000,
+    "border_width": 3,
+    "button_length": 0,
+    "fg_color": ["#939BA2", "#4A4D50"],
+    "progress_color": ["#2aa666", "#1f538d"],
+    "button_color": ["gray36", "#D5D9DE"],
+    "button_hover_color": ["gray20", "gray100"],
+    "text_color": ["gray14", "gray84"],
+    "text_color_disabled": ["gray60", "gray45"]
+  },
+  "CTkRadiobutton": {
+    "corner_radius": 1000,
+    "border_width_checked": 6,
+    "border_width_unchecked": 3,
+    "fg_color": ["#2aa666", "#1f538d"],
+    "border_color": ["#3e4a40", "#949A9F"],
+    "hover_color": ["#3cb666", "#14375e"],
+    "text_color": ["gray14", "gray84"],
+    "text_color_disabled": ["gray60", "gray45"]
+  },
+  "CTkProgressBar": {
+    "corner_radius": 1000,
+    "border_width": 0,
+    "fg_color": ["#939BA2", "#4A4D50"],
+    "progress_color": ["#2aa666", "#1f538d"],
+    "border_color": ["gray", "gray"]
+  },
+  "CTkSlider": {
+    "corner_radius": 1000,
+    "button_corner_radius": 1000,
+    "border_width": 6,
+    "button_length": 0,
+    "fg_color": ["#939BA2", "#4A4D50"],
+    "progress_color": ["gray40", "#AAB0B5"],
+    "button_color": ["#2aa666", "#1f538d"],
+    "button_hover_color": ["#3cb666", "#14375e"]
+  },
+  "CTkOptionMenu": {
+    "corner_radius": 0,
+    "fg_color": ["#2aa666", "#1f538d"],
+    "button_color": ["#3cb666", "#14375e"],
+    "button_hover_color": ["#234567", "#1e2c40"],
+    "text_color": ["#f3faf6", "#f3faf6"],
+    "text_color_disabled": ["gray74", "gray60"]
+  },
+  "CTkComboBox": {
+    "corner_radius": 0,
+    "border_width": 2,
+    "fg_color": ["#F9F9FA", "#343638"],
+    "border_color": ["#979DA2", "#565B5E"],
+    "button_color": ["#979DA2", "#565B5E"],
+    "button_hover_color": ["#6E7174", "#7A848D"],
+    "text_color": ["gray14", "gray84"],
+    "text_color_disabled": ["gray50", "gray45"]
+  },
+  "CTkScrollbar": {
+    "corner_radius": 1000,
+    "border_spacing": 4,
+    "fg_color": "transparent",
+    "button_color": ["gray55", "gray41"],
+    "button_hover_color": ["gray40", "gray53"]
+  },
+  "CTkSegmentedButton": {
+    "corner_radius": 0,
+    "border_width": 2,
+    "fg_color": ["#979DA2", "gray29"],
+    "selected_color": ["#2aa666", "#1f538d"],
+    "selected_hover_color": ["#3cb666", "#14375e"],
+    "unselected_color": ["#979DA2", "gray29"],
+    "unselected_hover_color": ["gray70", "gray41"],
+    "text_color": ["#f3faf6", "#f3faf6"],
+    "text_color_disabled": ["gray74", "gray60"]
+  },
+  "CTkTextbox": {
+    "corner_radius": 0,
+    "border_width": 0,
+    "fg_color": ["gray100", "gray20"],
+    "border_color": ["#979DA2", "#565B5E"],
+    "text_color": ["gray14", "gray84"],
+    "scrollbar_button_color": ["gray55", "gray41"],
+    "scrollbar_button_hover_color": ["gray40", "gray53"]
+  },
+  "CTkScrollableFrame": {
+    "label_fg_color": ["gray80", "gray21"]
+  },
+  "DropdownMenu": {
+    "fg_color": ["gray90", "gray20"],
+    "hover_color": ["gray75", "gray28"],
+    "text_color": ["gray14", "gray84"]
+  },
+  "CTkFont": {
+    "macOS": {
+      "family": "Avenir",
+      "size": 18,
+      "weight": "normal"
+    },
+    "Windows": {
+      "family": "Corbel",
+      "size": 18,
+      "weight": "normal"
+    },
+    "Linux": {
+      "family": "Montserrat",
+      "size": 18,
+      "weight": "normal"
+    }
+  },
+  "URL": {
+    "text_color": ["gray74", "gray60"]
+  }
+}

modules/ui.py

@@ -0,0 +1,1206 @@
+import os
+import webbrowser
+import customtkinter as ctk
+from typing import Callable, Tuple
+import cv2
+from cv2_enumerate_cameras import enumerate_cameras  # Add this import
+from PIL import Image, ImageOps
+import time
+import json
+import modules.globals
+import modules.metadata
+from modules.face_analyser import (
+    get_one_face,
+    get_unique_faces_from_target_image,
+    get_unique_faces_from_target_video,
+    add_blank_map,
+    has_valid_map,
+    simplify_maps,
+)
+from modules.capturer import get_video_frame, get_video_frame_total
+from modules.processors.frame.core import get_frame_processors_modules
+from modules.utilities import (
+    is_image,
+    is_video,
+    resolve_relative_path,
+    has_image_extension,
+)
+from modules.video_capture import VideoCapturer
+from modules.gettext import LanguageManager
+import platform
+
+if platform.system() == "Windows":
+    from pygrabber.dshow_graph import FilterGraph
+
+ROOT = None
+POPUP = None
+POPUP_LIVE = None
+ROOT_HEIGHT = 700
+ROOT_WIDTH = 600
+
+PREVIEW = None
+PREVIEW_MAX_HEIGHT = 700
+PREVIEW_MAX_WIDTH = 1200
+PREVIEW_DEFAULT_WIDTH = 960
+PREVIEW_DEFAULT_HEIGHT = 540
+
+POPUP_WIDTH = 750
+POPUP_HEIGHT = 810
+POPUP_SCROLL_WIDTH = (740,)
+POPUP_SCROLL_HEIGHT = 700
+
+POPUP_LIVE_WIDTH = 900
+POPUP_LIVE_HEIGHT = 820
+POPUP_LIVE_SCROLL_WIDTH = (890,)
+POPUP_LIVE_SCROLL_HEIGHT = 700
+
+MAPPER_PREVIEW_MAX_HEIGHT = 100
+MAPPER_PREVIEW_MAX_WIDTH = 100
+
+DEFAULT_BUTTON_WIDTH = 200
+DEFAULT_BUTTON_HEIGHT = 40
+
+RECENT_DIRECTORY_SOURCE = None
+RECENT_DIRECTORY_TARGET = None
+RECENT_DIRECTORY_OUTPUT = None
+
+_ = None
+preview_label = None
+preview_slider = None
+source_label = None
+target_label = None
+status_label = None
+popup_status_label = None
+popup_status_label_live = None
+source_label_dict = {}
+source_label_dict_live = {}
+target_label_dict_live = {}
+
+img_ft, vid_ft = modules.globals.file_types
+
+
+def init(start: Callable[[], None], destroy: Callable[[], None], lang: str) -> ctk.CTk:
+    global ROOT, PREVIEW, _
+
+    lang_manager = LanguageManager(lang)
+    _ = lang_manager._
+    ROOT = create_root(start, destroy)
+    PREVIEW = create_preview(ROOT)
+
+    return ROOT
+
+
+def save_switch_states():
+    switch_states = {
+        "keep_fps": modules.globals.keep_fps,
+        "keep_audio": modules.globals.keep_audio,
+        "keep_frames": modules.globals.keep_frames,
+        "many_faces": modules.globals.many_faces,
+        "map_faces": modules.globals.map_faces,
+        "color_correction": modules.globals.color_correction,
+        "nsfw_filter": modules.globals.nsfw_filter,
+        "live_mirror": modules.globals.live_mirror,
+        "live_resizable": modules.globals.live_resizable,
+        "fp_ui": modules.globals.fp_ui,
+        "show_fps": modules.globals.show_fps,
+        "mouth_mask": modules.globals.mouth_mask,
+        "show_mouth_mask_box": modules.globals.show_mouth_mask_box,
+    }
+    with open("switch_states.json", "w") as f:
+        json.dump(switch_states, f)
+
+
+def load_switch_states():
+    try:
+        with open("switch_states.json", "r") as f:
+            switch_states = json.load(f)
+        modules.globals.keep_fps = switch_states.get("keep_fps", True)
+        modules.globals.keep_audio = switch_states.get("keep_audio", True)
+        modules.globals.keep_frames = switch_states.get("keep_frames", False)
+        modules.globals.many_faces = switch_states.get("many_faces", False)
+        modules.globals.map_faces = switch_states.get("map_faces", False)
+        modules.globals.color_correction = switch_states.get("color_correction", False)
+        modules.globals.nsfw_filter = switch_states.get("nsfw_filter", False)
+        modules.globals.live_mirror = switch_states.get("live_mirror", False)
+        modules.globals.live_resizable = switch_states.get("live_resizable", False)
+        modules.globals.fp_ui = switch_states.get("fp_ui", {"face_enhancer": False})
+        modules.globals.show_fps = switch_states.get("show_fps", False)
+        modules.globals.mouth_mask = switch_states.get("mouth_mask", False)
+        modules.globals.show_mouth_mask_box = switch_states.get(
+            "show_mouth_mask_box", False
+        )
+    except FileNotFoundError:
+        # If the file doesn't exist, use default values
+        pass
+
+
+def create_root(start: Callable[[], None], destroy: Callable[[], None]) -> ctk.CTk:
+    global source_label, target_label, status_label, show_fps_switch
+
+    load_switch_states()
+
+    ctk.deactivate_automatic_dpi_awareness()
+    ctk.set_appearance_mode("system")
+    ctk.set_default_color_theme(resolve_relative_path("ui.json"))
+
+    root = ctk.CTk()
+    root.minsize(ROOT_WIDTH, ROOT_HEIGHT)
+    root.title(
+        f"{modules.metadata.name} {modules.metadata.version} {modules.metadata.edition}"
+    )
+    root.configure()
+    root.protocol("WM_DELETE_WINDOW", lambda: destroy())
+
+    source_label = ctk.CTkLabel(root, text=None)
+    source_label.place(relx=0.1, rely=0.1, relwidth=0.3, relheight=0.25)
+
+    target_label = ctk.CTkLabel(root, text=None)
+    target_label.place(relx=0.6, rely=0.1, relwidth=0.3, relheight=0.25)
+
+    select_face_button = ctk.CTkButton(
+        root, text=_("Select a face"), cursor="hand2", command=lambda: select_source_path()
+    )
+    select_face_button.place(relx=0.1, rely=0.4, relwidth=0.3, relheight=0.1)
+
+    swap_faces_button = ctk.CTkButton(
+        root, text="↔", cursor="hand2", command=lambda: swap_faces_paths()
+    )
+    swap_faces_button.place(relx=0.45, rely=0.4, relwidth=0.1, relheight=0.1)
+
+    select_target_button = ctk.CTkButton(
+        root,
+        text=_("Select a target"),
+        cursor="hand2",
+        command=lambda: select_target_path(),
+    )
+    select_target_button.place(relx=0.6, rely=0.4, relwidth=0.3, relheight=0.1)
+
+    keep_fps_value = ctk.BooleanVar(value=modules.globals.keep_fps)
+    keep_fps_checkbox = ctk.CTkSwitch(
+        root,
+        text=_("Keep fps"),
+        variable=keep_fps_value,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "keep_fps", keep_fps_value.get()),
+            save_switch_states(),
+        ),
+    )
+    keep_fps_checkbox.place(relx=0.1, rely=0.6)
+
+    keep_frames_value = ctk.BooleanVar(value=modules.globals.keep_frames)
+    keep_frames_switch = ctk.CTkSwitch(
+        root,
+        text=_("Keep frames"),
+        variable=keep_frames_value,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "keep_frames", keep_frames_value.get()),
+            save_switch_states(),
+        ),
+    )
+    keep_frames_switch.place(relx=0.1, rely=0.65)
+
+    enhancer_value = ctk.BooleanVar(value=modules.globals.fp_ui["face_enhancer"])
+    enhancer_switch = ctk.CTkSwitch(
+        root,
+        text=_("Face Enhancer"),
+        variable=enhancer_value,
+        cursor="hand2",
+        command=lambda: (
+            update_tumbler("face_enhancer", enhancer_value.get()),
+            save_switch_states(),
+        ),
+    )
+    enhancer_switch.place(relx=0.1, rely=0.7)
+
+    keep_audio_value = ctk.BooleanVar(value=modules.globals.keep_audio)
+    keep_audio_switch = ctk.CTkSwitch(
+        root,
+        text=_("Keep audio"),
+        variable=keep_audio_value,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "keep_audio", keep_audio_value.get()),
+            save_switch_states(),
+        ),
+    )
+    keep_audio_switch.place(relx=0.6, rely=0.6)
+
+    many_faces_value = ctk.BooleanVar(value=modules.globals.many_faces)
+    many_faces_switch = ctk.CTkSwitch(
+        root,
+        text=_("Many faces"),
+        variable=many_faces_value,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "many_faces", many_faces_value.get()),
+            save_switch_states(),
+        ),
+    )
+    many_faces_switch.place(relx=0.6, rely=0.65)
+
+    color_correction_value = ctk.BooleanVar(value=modules.globals.color_correction)
+    color_correction_switch = ctk.CTkSwitch(
+        root,
+        text=_("Fix Blueish Cam"),
+        variable=color_correction_value,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "color_correction", color_correction_value.get()),
+            save_switch_states(),
+        ),
+    )
+    color_correction_switch.place(relx=0.6, rely=0.70)
+
+    #    nsfw_value = ctk.BooleanVar(value=modules.globals.nsfw_filter)
+    #    nsfw_switch = ctk.CTkSwitch(root, text='NSFW filter', variable=nsfw_value, cursor='hand2', command=lambda: setattr(modules.globals, 'nsfw_filter', nsfw_value.get()))
+    #    nsfw_switch.place(relx=0.6, rely=0.7)
+
+    map_faces = ctk.BooleanVar(value=modules.globals.map_faces)
+    map_faces_switch = ctk.CTkSwitch(
+        root,
+        text=_("Map faces"),
+        variable=map_faces,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "map_faces", map_faces.get()),
+            save_switch_states(),
+            close_mapper_window() if not map_faces.get() else None
+        ),
+    )
+    map_faces_switch.place(relx=0.1, rely=0.75)
+
+    show_fps_value = ctk.BooleanVar(value=modules.globals.show_fps)
+    show_fps_switch = ctk.CTkSwitch(
+        root,
+        text=_("Show FPS"),
+        variable=show_fps_value,
+        cursor="hand2",
+        command=lambda: (
+            setattr(modules.globals, "show_fps", show_fps_value.get()),
+            save_switch_states(),
+        ),
+    )
+    show_fps_switch.place(relx=0.6, rely=0.75)
+
+    mouth_mask_var = ctk.BooleanVar(value=modules.globals.mouth_mask)
+    mouth_mask_switch = ctk.CTkSwitch(
+        root,
+        text=_("Mouth Mask"),
+        variable=mouth_mask_var,
+        cursor="hand2",
+        command=lambda: setattr(modules.globals, "mouth_mask", mouth_mask_var.get()),
+    )
+    mouth_mask_switch.place(relx=0.1, rely=0.55)
+
+    show_mouth_mask_box_var = ctk.BooleanVar(value=modules.globals.show_mouth_mask_box)
+    show_mouth_mask_box_switch = ctk.CTkSwitch(
+        root,
+        text=_("Show Mouth Mask Box"),
+        variable=show_mouth_mask_box_var,
+        cursor="hand2",
+        command=lambda: setattr(
+            modules.globals, "show_mouth_mask_box", show_mouth_mask_box_var.get()
+        ),
+    )
+    show_mouth_mask_box_switch.place(relx=0.6, rely=0.55)
+
+    start_button = ctk.CTkButton(
+        root, text=_("Start"), cursor="hand2", command=lambda: analyze_target(start, root)
+    )
+    start_button.place(relx=0.15, rely=0.80, relwidth=0.2, relheight=0.05)
+
+    stop_button = ctk.CTkButton(
+        root, text=_("Destroy"), cursor="hand2", command=lambda: destroy()
+    )
+    stop_button.place(relx=0.4, rely=0.80, relwidth=0.2, relheight=0.05)
+
+    preview_button = ctk.CTkButton(
+        root, text=_("Preview"), cursor="hand2", command=lambda: toggle_preview()
+    )
+    preview_button.place(relx=0.65, rely=0.80, relwidth=0.2, relheight=0.05)
+
+    # --- Camera Selection ---
+    camera_label = ctk.CTkLabel(root, text=_("Select Camera:"))
+    camera_label.place(relx=0.1, rely=0.86, relwidth=0.2, relheight=0.05)
+
+    available_cameras = get_available_cameras()
+    camera_indices, camera_names = available_cameras
+
+    if not camera_names or camera_names[0] == "No cameras found":
+        camera_variable = ctk.StringVar(value="No cameras found")
+        camera_optionmenu = ctk.CTkOptionMenu(
+            root,
+            variable=camera_variable,
+            values=["No cameras found"],
+            state="disabled",
+        )
+    else:
+        camera_variable = ctk.StringVar(value=camera_names[0])
+        camera_optionmenu = ctk.CTkOptionMenu(
+            root, variable=camera_variable, values=camera_names
+        )
+
+    camera_optionmenu.place(relx=0.35, rely=0.86, relwidth=0.25, relheight=0.05)
+
+    live_button = ctk.CTkButton(
+        root,
+        text=_("Live"),
+        cursor="hand2",
+        command=lambda: webcam_preview(
+            root,
+            (
+                camera_indices[camera_names.index(camera_variable.get())]
+                if camera_names and camera_names[0] != "No cameras found"
+                else None
+            ),
+        ),
+        state=(
+            "normal"
+            if camera_names and camera_names[0] != "No cameras found"
+            else "disabled"
+        ),
+    )
+    live_button.place(relx=0.65, rely=0.86, relwidth=0.2, relheight=0.05)
+    # --- End Camera Selection ---
+
+    status_label = ctk.CTkLabel(root, text=None, justify="center")
+    status_label.place(relx=0.1, rely=0.9, relwidth=0.8)
+
+    donate_label = ctk.CTkLabel(
+        root, text="Deep Live Cam", justify="center", cursor="hand2"
+    )
+    donate_label.place(relx=0.1, rely=0.95, relwidth=0.8)
+    donate_label.configure(
+        text_color=ctk.ThemeManager.theme.get("URL").get("text_color")
+    )
+    donate_label.bind(
+        "<Button>", lambda event: webbrowser.open("https://deeplivecam.net")
+    )
+
+    return root
+
+def close_mapper_window():
+    global POPUP, POPUP_LIVE
+    if POPUP and POPUP.winfo_exists():
+        POPUP.destroy()
+        POPUP = None
+    if POPUP_LIVE and POPUP_LIVE.winfo_exists():
+        POPUP_LIVE.destroy()
+        POPUP_LIVE = None
+
+
+def analyze_target(start: Callable[[], None], root: ctk.CTk):
+    if POPUP != None and POPUP.winfo_exists():
+        update_status("Please complete pop-up or close it.")
+        return
+
+    if modules.globals.map_faces:
+        modules.globals.source_target_map = []
+
+        if is_image(modules.globals.target_path):
+            update_status("Getting unique faces")
+            get_unique_faces_from_target_image()
+        elif is_video(modules.globals.target_path):
+            update_status("Getting unique faces")
+            get_unique_faces_from_target_video()
+
+        if len(modules.globals.source_target_map) > 0:
+            create_source_target_popup(start, root, modules.globals.source_target_map)
+        else:
+            update_status("No faces found in target")
+    else:
+        select_output_path(start)
+
+
+def create_source_target_popup(
+        start: Callable[[], None], root: ctk.CTk, map: list
+) -> None:
+    global POPUP, popup_status_label
+
+    POPUP = ctk.CTkToplevel(root)
+    POPUP.title(_("Source x Target Mapper"))
+    POPUP.geometry(f"{POPUP_WIDTH}x{POPUP_HEIGHT}")
+    POPUP.focus()
+
+    def on_submit_click(start):
+        if has_valid_map():
+            POPUP.destroy()
+            select_output_path(start)
+        else:
+            update_pop_status("Atleast 1 source with target is required!")
+
+    scrollable_frame = ctk.CTkScrollableFrame(
+        POPUP, width=POPUP_SCROLL_WIDTH, height=POPUP_SCROLL_HEIGHT
+    )
+    scrollable_frame.grid(row=0, column=0, padx=0, pady=0, sticky="nsew")
+
+    def on_button_click(map, button_num):
+        map = update_popup_source(scrollable_frame, map, button_num)
+
+    for item in map:
+        id = item["id"]
+
+        button = ctk.CTkButton(
+            scrollable_frame,
+            text=_("Select source image"),
+            command=lambda id=id: on_button_click(map, id),
+            width=DEFAULT_BUTTON_WIDTH,
+            height=DEFAULT_BUTTON_HEIGHT,
+        )
+        button.grid(row=id, column=0, padx=50, pady=10)
+
+        x_label = ctk.CTkLabel(
+            scrollable_frame,
+            text=f"X",
+            width=MAPPER_PREVIEW_MAX_WIDTH,
+            height=MAPPER_PREVIEW_MAX_HEIGHT,
+        )
+        x_label.grid(row=id, column=2, padx=10, pady=10)
+
+        image = Image.fromarray(cv2.cvtColor(item["target"]["cv2"], cv2.COLOR_BGR2RGB))
+        image = image.resize(
+            (MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
+        )
+        tk_image = ctk.CTkImage(image, size=image.size)
+
+        target_image = ctk.CTkLabel(
+            scrollable_frame,
+            text=f"T-{id}",
+            width=MAPPER_PREVIEW_MAX_WIDTH,
+            height=MAPPER_PREVIEW_MAX_HEIGHT,
+        )
+        target_image.grid(row=id, column=3, padx=10, pady=10)
+        target_image.configure(image=tk_image)
+
+    popup_status_label = ctk.CTkLabel(POPUP, text=None, justify="center")
+    popup_status_label.grid(row=1, column=0, pady=15)
+
+    close_button = ctk.CTkButton(
+        POPUP, text=_("Submit"), command=lambda: on_submit_click(start)
+    )
+    close_button.grid(row=2, column=0, pady=10)
+
+
+def update_popup_source(
+        scrollable_frame: ctk.CTkScrollableFrame, map: list, button_num: int
+) -> list:
+    global source_label_dict
+
+    source_path = ctk.filedialog.askopenfilename(
+        title=_("select an source image"),
+        initialdir=RECENT_DIRECTORY_SOURCE,
+        filetypes=[img_ft],
+    )
+
+    if "source" in map[button_num]:
+        map[button_num].pop("source")
+        source_label_dict[button_num].destroy()
+        del source_label_dict[button_num]
+
+    if source_path == "":
+        return map
+    else:
+        cv2_img = cv2.imread(source_path)
+        face = get_one_face(cv2_img)
+
+        if face:
+            x_min, y_min, x_max, y_max = face["bbox"]
+
+            map[button_num]["source"] = {
+                "cv2": cv2_img[int(y_min): int(y_max), int(x_min): int(x_max)],
+                "face": face,
+            }
+
+            image = Image.fromarray(
+                cv2.cvtColor(map[button_num]["source"]["cv2"], cv2.COLOR_BGR2RGB)
+            )
+            image = image.resize(
+                (MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
+            )
+            tk_image = ctk.CTkImage(image, size=image.size)
+
+            source_image = ctk.CTkLabel(
+                scrollable_frame,
+                text=f"S-{button_num}",
+                width=MAPPER_PREVIEW_MAX_WIDTH,
+                height=MAPPER_PREVIEW_MAX_HEIGHT,
+            )
+            source_image.grid(row=button_num, column=1, padx=10, pady=10)
+            source_image.configure(image=tk_image)
+            source_label_dict[button_num] = source_image
+        else:
+            update_pop_status("Face could not be detected in last upload!")
+        return map
+
+
+def create_preview(parent: ctk.CTkToplevel) -> ctk.CTkToplevel:
+    global preview_label, preview_slider
+
+    preview = ctk.CTkToplevel(parent)
+    preview.withdraw()
+    preview.title(_("Preview"))
+    preview.configure()
+    preview.protocol("WM_DELETE_WINDOW", lambda: toggle_preview())
+    preview.resizable(width=True, height=True)
+
+    preview_label = ctk.CTkLabel(preview, text=None)
+    preview_label.pack(fill="both", expand=True)
+
+    preview_slider = ctk.CTkSlider(
+        preview, from_=0, to=0, command=lambda frame_value: update_preview(frame_value)
+    )
+
+    return preview
+
+
+def update_status(text: str) -> None:
+    status_label.configure(text=_(text))
+    ROOT.update()
+
+
+def update_pop_status(text: str) -> None:
+    popup_status_label.configure(text=_(text))
+
+
+def update_pop_live_status(text: str) -> None:
+    popup_status_label_live.configure(text=_(text))
+
+
+def update_tumbler(var: str, value: bool) -> None:
+    modules.globals.fp_ui[var] = value
+    save_switch_states()
+    # If we're currently in a live preview, update the frame processors
+    if PREVIEW.state() == "normal":
+        global frame_processors
+        frame_processors = get_frame_processors_modules(
+            modules.globals.frame_processors
+        )
+
+
+def select_source_path() -> None:
+    global RECENT_DIRECTORY_SOURCE, img_ft, vid_ft
+
+    PREVIEW.withdraw()
+    source_path = ctk.filedialog.askopenfilename(
+        title=_("select an source image"),
+        initialdir=RECENT_DIRECTORY_SOURCE,
+        filetypes=[img_ft],
+    )
+    if is_image(source_path):
+        modules.globals.source_path = source_path
+        RECENT_DIRECTORY_SOURCE = os.path.dirname(modules.globals.source_path)
+        image = render_image_preview(modules.globals.source_path, (200, 200))
+        source_label.configure(image=image)
+    else:
+        modules.globals.source_path = None
+        source_label.configure(image=None)
+
+
+def swap_faces_paths() -> None:
+    global RECENT_DIRECTORY_SOURCE, RECENT_DIRECTORY_TARGET
+
+    source_path = modules.globals.source_path
+    target_path = modules.globals.target_path
+
+    if not is_image(source_path) or not is_image(target_path):
+        return
+
+    modules.globals.source_path = target_path
+    modules.globals.target_path = source_path
+
+    RECENT_DIRECTORY_SOURCE = os.path.dirname(modules.globals.source_path)
+    RECENT_DIRECTORY_TARGET = os.path.dirname(modules.globals.target_path)
+
+    PREVIEW.withdraw()
+
+    source_image = render_image_preview(modules.globals.source_path, (200, 200))
+    source_label.configure(image=source_image)
+
+    target_image = render_image_preview(modules.globals.target_path, (200, 200))
+    target_label.configure(image=target_image)
+
+
+def select_target_path() -> None:
+    global RECENT_DIRECTORY_TARGET, img_ft, vid_ft
+
+    PREVIEW.withdraw()
+    target_path = ctk.filedialog.askopenfilename(
+        title=_("select an target image or video"),
+        initialdir=RECENT_DIRECTORY_TARGET,
+        filetypes=[img_ft, vid_ft],
+    )
+    if is_image(target_path):
+        modules.globals.target_path = target_path
+        RECENT_DIRECTORY_TARGET = os.path.dirname(modules.globals.target_path)
+        image = render_image_preview(modules.globals.target_path, (200, 200))
+        target_label.configure(image=image)
+    elif is_video(target_path):
+        modules.globals.target_path = target_path
+        RECENT_DIRECTORY_TARGET = os.path.dirname(modules.globals.target_path)
+        video_frame = render_video_preview(target_path, (200, 200))
+        target_label.configure(image=video_frame)
+    else:
+        modules.globals.target_path = None
+        target_label.configure(image=None)
+
+
+def select_output_path(start: Callable[[], None]) -> None:
+    global RECENT_DIRECTORY_OUTPUT, img_ft, vid_ft
+
+    if is_image(modules.globals.target_path):
+        output_path = ctk.filedialog.asksaveasfilename(
+            title=_("save image output file"),
+            filetypes=[img_ft],
+            defaultextension=".png",
+            initialfile="output.png",
+            initialdir=RECENT_DIRECTORY_OUTPUT,
+        )
+    elif is_video(modules.globals.target_path):
+        output_path = ctk.filedialog.asksaveasfilename(
+            title=_("save video output file"),
+            filetypes=[vid_ft],
+            defaultextension=".mp4",
+            initialfile="output.mp4",
+            initialdir=RECENT_DIRECTORY_OUTPUT,
+        )
+    else:
+        output_path = None
+    if output_path:
+        modules.globals.output_path = output_path
+        RECENT_DIRECTORY_OUTPUT = os.path.dirname(modules.globals.output_path)
+        start()
+
+
+def check_and_ignore_nsfw(target, destroy: Callable = None) -> bool:
+    """Check if the target is NSFW.
+    TODO: Consider to make blur the target.
+    """
+    from numpy import ndarray
+    from modules.predicter import predict_image, predict_video, predict_frame
+
+    if type(target) is str:  # image/video file path
+        check_nsfw = predict_image if has_image_extension(target) else predict_video
+    elif type(target) is ndarray:  # frame object
+        check_nsfw = predict_frame
+    if check_nsfw and check_nsfw(target):
+        if destroy:
+            destroy(
+                to_quit=False
+            )  # Do not need to destroy the window frame if the target is NSFW
+        update_status("Processing ignored!")
+        return True
+    else:
+        return False
+
+
+def fit_image_to_size(image, width: int, height: int):
+    if width is None or height is None or width <= 0 or height <= 0:
+        return image
+    h, w, _ = image.shape
+    ratio_h = 0.0
+    ratio_w = 0.0
+    ratio_w = width / w
+    ratio_h = height / h
+    # Use the smaller ratio to ensure the image fits within the given dimensions
+    ratio = min(ratio_w, ratio_h)
+    
+    # Compute new dimensions, ensuring they're at least 1 pixel
+    new_width = max(1, int(ratio * w))
+    new_height = max(1, int(ratio * h))
+    new_size = (new_width, new_height)
+
+    return cv2.resize(image, dsize=new_size)
+
+
+def render_image_preview(image_path: str, size: Tuple[int, int]) -> ctk.CTkImage:
+    image = Image.open(image_path)
+    if size:
+        image = ImageOps.fit(image, size, Image.LANCZOS)
+    return ctk.CTkImage(image, size=image.size)
+
+
+def render_video_preview(
+        video_path: str, size: Tuple[int, int], frame_number: int = 0
+) -> ctk.CTkImage:
+    capture = cv2.VideoCapture(video_path)
+    if frame_number:
+        capture.set(cv2.CAP_PROP_POS_FRAMES, frame_number)
+    has_frame, frame = capture.read()
+    if has_frame:
+        image = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+        if size:
+            image = ImageOps.fit(image, size, Image.LANCZOS)
+        return ctk.CTkImage(image, size=image.size)
+    capture.release()
+    cv2.destroyAllWindows()
+
+
+def toggle_preview() -> None:
+    if PREVIEW.state() == "normal":
+        PREVIEW.withdraw()
+    elif modules.globals.source_path and modules.globals.target_path:
+        init_preview()
+        update_preview()
+
+
+def init_preview() -> None:
+    if is_image(modules.globals.target_path):
+        preview_slider.pack_forget()
+    if is_video(modules.globals.target_path):
+        video_frame_total = get_video_frame_total(modules.globals.target_path)
+        preview_slider.configure(to=video_frame_total)
+        preview_slider.pack(fill="x")
+        preview_slider.set(0)
+
+
+def update_preview(frame_number: int = 0) -> None:
+    if modules.globals.source_path and modules.globals.target_path:
+        update_status("Processing...")
+        temp_frame = get_video_frame(modules.globals.target_path, frame_number)
+        if modules.globals.nsfw_filter and check_and_ignore_nsfw(temp_frame):
+            return
+        for frame_processor in get_frame_processors_modules(
+                modules.globals.frame_processors
+        ):
+            temp_frame = frame_processor.process_frame(
+                get_one_face(cv2.imread(modules.globals.source_path)), temp_frame
+            )
+        image = Image.fromarray(cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB))
+        image = ImageOps.contain(
+            image, (PREVIEW_MAX_WIDTH, PREVIEW_MAX_HEIGHT), Image.LANCZOS
+        )
+        image = ctk.CTkImage(image, size=image.size)
+        preview_label.configure(image=image)
+        update_status("Processing succeed!")
+        PREVIEW.deiconify()
+
+
+def webcam_preview(root: ctk.CTk, camera_index: int):
+    global POPUP_LIVE
+
+    if POPUP_LIVE and POPUP_LIVE.winfo_exists():
+        update_status("Source x Target Mapper is already open.")
+        POPUP_LIVE.focus()
+        return
+
+    if not modules.globals.map_faces:
+        if modules.globals.source_path is None:
+            update_status("Please select a source image first")
+            return
+        create_webcam_preview(camera_index)
+    else:
+        modules.globals.source_target_map = []
+        create_source_target_popup_for_webcam(
+            root, modules.globals.source_target_map, camera_index
+        )
+
+
+
+def get_available_cameras():
+    """Returns a list of available camera names and indices."""
+    if platform.system() == "Windows":
+        try:
+            graph = FilterGraph()
+            devices = graph.get_input_devices()
+
+            # Create list of indices and names
+            camera_indices = list(range(len(devices)))
+            camera_names = devices
+
+            # If no cameras found through DirectShow, try OpenCV fallback
+            if not camera_names:
+                # Try to open camera with index -1 and 0
+                test_indices = [-1, 0]
+                working_cameras = []
+
+                for idx in test_indices:
+                    cap = cv2.VideoCapture(idx)
+                    if cap.isOpened():
+                        working_cameras.append(f"Camera {idx}")
+                        cap.release()
+
+                if working_cameras:
+                    return test_indices[: len(working_cameras)], working_cameras
+
+            # If still no cameras found, return empty lists
+            if not camera_names:
+                return [], ["No cameras found"]
+
+            return camera_indices, camera_names
+
+        except Exception as e:
+            print(f"Error detecting cameras: {str(e)}")
+            return [], ["No cameras found"]
+    else:
+        # Unix-like systems (Linux/Mac) camera detection
+        camera_indices = []
+        camera_names = []
+
+        if platform.system() == "Darwin":  # macOS specific handling
+            # Try to open the default FaceTime camera first
+            cap = cv2.VideoCapture(0)
+            if cap.isOpened():
+                camera_indices.append(0)
+                camera_names.append("FaceTime Camera")
+                cap.release()
+
+            # On macOS, additional cameras typically use indices 1 and 2
+            for i in [1, 2]:
+                cap = cv2.VideoCapture(i)
+                if cap.isOpened():
+                    camera_indices.append(i)
+                    camera_names.append(f"Camera {i}")
+                    cap.release()
+        else:
+            # Linux camera detection - test first 10 indices
+            for i in range(10):
+                cap = cv2.VideoCapture(i)
+                if cap.isOpened():
+                    camera_indices.append(i)
+                    camera_names.append(f"Camera {i}")
+                    cap.release()
+
+        if not camera_names:
+            return [], ["No cameras found"]
+
+        return camera_indices, camera_names
+
+
+def create_webcam_preview(camera_index: int):
+    global preview_label, PREVIEW
+
+    cap = VideoCapturer(camera_index)
+    if not cap.start(PREVIEW_DEFAULT_WIDTH, PREVIEW_DEFAULT_HEIGHT, 60):
+        update_status("Failed to start camera")
+        return
+
+    preview_label.configure(width=PREVIEW_DEFAULT_WIDTH, height=PREVIEW_DEFAULT_HEIGHT)
+    PREVIEW.deiconify()
+
+    frame_processors = get_frame_processors_modules(modules.globals.frame_processors)
+    source_image = None
+    prev_time = time.time()
+    fps_update_interval = 0.5
+    frame_count = 0
+    fps = 0
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        temp_frame = frame.copy()
+
+        if modules.globals.live_mirror:
+            temp_frame = cv2.flip(temp_frame, 1)
+
+        if modules.globals.live_resizable:
+            temp_frame = fit_image_to_size(
+                temp_frame, PREVIEW.winfo_width(), PREVIEW.winfo_height()
+            )
+
+        else:
+            temp_frame = fit_image_to_size(
+                temp_frame, PREVIEW.winfo_width(), PREVIEW.winfo_height()
+            )
+
+        if not modules.globals.map_faces:
+            if source_image is None and modules.globals.source_path:
+                source_image = get_one_face(cv2.imread(modules.globals.source_path))
+
+            for frame_processor in frame_processors:
+                if frame_processor.NAME == "DLC.FACE-ENHANCER":
+                    if modules.globals.fp_ui["face_enhancer"]:
+                        temp_frame = frame_processor.process_frame(None, temp_frame)
+                else:
+                    temp_frame = frame_processor.process_frame(source_image, temp_frame)
+        else:
+            modules.globals.target_path = None
+            for frame_processor in frame_processors:
+                if frame_processor.NAME == "DLC.FACE-ENHANCER":
+                    if modules.globals.fp_ui["face_enhancer"]:
+                        temp_frame = frame_processor.process_frame_v2(temp_frame)
+                else:
+                    temp_frame = frame_processor.process_frame_v2(temp_frame)
+
+        # Calculate and display FPS
+        current_time = time.time()
+        frame_count += 1
+        if current_time - prev_time >= fps_update_interval:
+            fps = frame_count / (current_time - prev_time)
+            frame_count = 0
+            prev_time = current_time
+
+        if modules.globals.show_fps:
+            cv2.putText(
+                temp_frame,
+                f"FPS: {fps:.1f}",
+                (10, 30),
+                cv2.FONT_HERSHEY_SIMPLEX,
+                1,
+                (0, 255, 0),
+                2,
+            )
+
+        image = cv2.cvtColor(temp_frame, cv2.COLOR_BGR2RGB)
+        image = Image.fromarray(image)
+        image = ImageOps.contain(
+            image, (temp_frame.shape[1], temp_frame.shape[0]), Image.LANCZOS
+        )
+        image = ctk.CTkImage(image, size=image.size)
+        preview_label.configure(image=image)
+        ROOT.update()
+
+        if PREVIEW.state() == "withdrawn":
+            break
+
+    cap.release()
+    PREVIEW.withdraw()
+
+
+def create_source_target_popup_for_webcam(
+        root: ctk.CTk, map: list, camera_index: int
+) -> None:
+    global POPUP_LIVE, popup_status_label_live
+
+    POPUP_LIVE = ctk.CTkToplevel(root)
+    POPUP_LIVE.title(_("Source x Target Mapper"))
+    POPUP_LIVE.geometry(f"{POPUP_LIVE_WIDTH}x{POPUP_LIVE_HEIGHT}")
+    POPUP_LIVE.focus()
+
+    def on_submit_click():
+        if has_valid_map():
+            simplify_maps()
+            update_pop_live_status("Mappings successfully submitted!")
+            create_webcam_preview(camera_index)  # Open the preview window
+        else:
+            update_pop_live_status("At least 1 source with target is required!")
+
+    def on_add_click():
+        add_blank_map()
+        refresh_data(map)
+        update_pop_live_status("Please provide mapping!")
+
+    def on_clear_click():
+        clear_source_target_images(map)
+        refresh_data(map)
+        update_pop_live_status("All mappings cleared!")
+
+    popup_status_label_live = ctk.CTkLabel(POPUP_LIVE, text=None, justify="center")
+    popup_status_label_live.grid(row=1, column=0, pady=15)
+
+    add_button = ctk.CTkButton(POPUP_LIVE, text=_("Add"), command=lambda: on_add_click())
+    add_button.place(relx=0.1, rely=0.92, relwidth=0.2, relheight=0.05)
+
+    clear_button = ctk.CTkButton(POPUP_LIVE, text=_("Clear"), command=lambda: on_clear_click())
+    clear_button.place(relx=0.4, rely=0.92, relwidth=0.2, relheight=0.05)
+
+    close_button = ctk.CTkButton(
+        POPUP_LIVE, text=_("Submit"), command=lambda: on_submit_click()
+    )
+    close_button.place(relx=0.7, rely=0.92, relwidth=0.2, relheight=0.05)
+
+
+
+def clear_source_target_images(map: list):
+    global source_label_dict_live, target_label_dict_live
+
+    for item in map:
+        if "source" in item:
+            del item["source"]
+        if "target" in item:
+            del item["target"]
+
+    for button_num in list(source_label_dict_live.keys()):
+        source_label_dict_live[button_num].destroy()
+        del source_label_dict_live[button_num]
+
+    for button_num in list(target_label_dict_live.keys()):
+        target_label_dict_live[button_num].destroy()
+        del target_label_dict_live[button_num]
+
+
+def refresh_data(map: list):
+    global POPUP_LIVE
+
+    scrollable_frame = ctk.CTkScrollableFrame(
+        POPUP_LIVE, width=POPUP_LIVE_SCROLL_WIDTH, height=POPUP_LIVE_SCROLL_HEIGHT
+    )
+    scrollable_frame.grid(row=0, column=0, padx=0, pady=0, sticky="nsew")
+
+    def on_sbutton_click(map, button_num):
+        map = update_webcam_source(scrollable_frame, map, button_num)
+
+    def on_tbutton_click(map, button_num):
+        map = update_webcam_target(scrollable_frame, map, button_num)
+
+    for item in map:
+        id = item["id"]
+
+        button = ctk.CTkButton(
+            scrollable_frame,
+            text=_("Select source image"),
+            command=lambda id=id: on_sbutton_click(map, id),
+            width=DEFAULT_BUTTON_WIDTH,
+            height=DEFAULT_BUTTON_HEIGHT,
+        )
+        button.grid(row=id, column=0, padx=30, pady=10)
+
+        x_label = ctk.CTkLabel(
+            scrollable_frame,
+            text=f"X",
+            width=MAPPER_PREVIEW_MAX_WIDTH,
+            height=MAPPER_PREVIEW_MAX_HEIGHT,
+        )
+        x_label.grid(row=id, column=2, padx=10, pady=10)
+
+        button = ctk.CTkButton(
+            scrollable_frame,
+            text=_("Select target image"),
+            command=lambda id=id: on_tbutton_click(map, id),
+            width=DEFAULT_BUTTON_WIDTH,
+            height=DEFAULT_BUTTON_HEIGHT,
+        )
+        button.grid(row=id, column=3, padx=20, pady=10)
+
+        if "source" in item:
+            image = Image.fromarray(
+                cv2.cvtColor(item["source"]["cv2"], cv2.COLOR_BGR2RGB)
+            )
+            image = image.resize(
+                (MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
+            )
+            tk_image = ctk.CTkImage(image, size=image.size)
+
+            source_image = ctk.CTkLabel(
+                scrollable_frame,
+                text=f"S-{id}",
+                width=MAPPER_PREVIEW_MAX_WIDTH,
+                height=MAPPER_PREVIEW_MAX_HEIGHT,
+            )
+            source_image.grid(row=id, column=1, padx=10, pady=10)
+            source_image.configure(image=tk_image)
+
+        if "target" in item:
+            image = Image.fromarray(
+                cv2.cvtColor(item["target"]["cv2"], cv2.COLOR_BGR2RGB)
+            )
+            image = image.resize(
+                (MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
+            )
+            tk_image = ctk.CTkImage(image, size=image.size)
+
+            target_image = ctk.CTkLabel(
+                scrollable_frame,
+                text=f"T-{id}",
+                width=MAPPER_PREVIEW_MAX_WIDTH,
+                height=MAPPER_PREVIEW_MAX_HEIGHT,
+            )
+            target_image.grid(row=id, column=4, padx=20, pady=10)
+            target_image.configure(image=tk_image)
+
+
+def update_webcam_source(
+        scrollable_frame: ctk.CTkScrollableFrame, map: list, button_num: int
+) -> list:
+    global source_label_dict_live
+
+    source_path = ctk.filedialog.askopenfilename(
+        title=_("select an source image"),
+        initialdir=RECENT_DIRECTORY_SOURCE,
+        filetypes=[img_ft],
+    )
+
+    if "source" in map[button_num]:
+        map[button_num].pop("source")
+        source_label_dict_live[button_num].destroy()
+        del source_label_dict_live[button_num]
+
+    if source_path == "":
+        return map
+    else:
+        cv2_img = cv2.imread(source_path)
+        face = get_one_face(cv2_img)
+
+        if face:
+            x_min, y_min, x_max, y_max = face["bbox"]
+
+            map[button_num]["source"] = {
+                "cv2": cv2_img[int(y_min): int(y_max), int(x_min): int(x_max)],
+                "face": face,
+            }
+
+            image = Image.fromarray(
+                cv2.cvtColor(map[button_num]["source"]["cv2"], cv2.COLOR_BGR2RGB)
+            )
+            image = image.resize(
+                (MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
+            )
+            tk_image = ctk.CTkImage(image, size=image.size)
+
+            source_image = ctk.CTkLabel(
+                scrollable_frame,
+                text=f"S-{button_num}",
+                width=MAPPER_PREVIEW_MAX_WIDTH,
+                height=MAPPER_PREVIEW_MAX_HEIGHT,
+            )
+            source_image.grid(row=button_num, column=1, padx=10, pady=10)
+            source_image.configure(image=tk_image)
+            source_label_dict_live[button_num] = source_image
+        else:
+            update_pop_live_status("Face could not be detected in last upload!")
+        return map
+
+
+def update_webcam_target(
+        scrollable_frame: ctk.CTkScrollableFrame, map: list, button_num: int
+) -> list:
+    global target_label_dict_live
+
+    target_path = ctk.filedialog.askopenfilename(
+        title=_("select an target image"),
+        initialdir=RECENT_DIRECTORY_SOURCE,
+        filetypes=[img_ft],
+    )
+
+    if "target" in map[button_num]:
+        map[button_num].pop("target")
+        target_label_dict_live[button_num].destroy()
+        del target_label_dict_live[button_num]
+
+    if target_path == "":
+        return map
+    else:
+        cv2_img = cv2.imread(target_path)
+        face = get_one_face(cv2_img)
+
+        if face:
+            x_min, y_min, x_max, y_max = face["bbox"]
+
+            map[button_num]["target"] = {
+                "cv2": cv2_img[int(y_min): int(y_max), int(x_min): int(x_max)],
+                "face": face,
+            }
+
+            image = Image.fromarray(
+                cv2.cvtColor(map[button_num]["target"]["cv2"], cv2.COLOR_BGR2RGB)
+            )
+            image = image.resize(
+                (MAPPER_PREVIEW_MAX_WIDTH, MAPPER_PREVIEW_MAX_HEIGHT), Image.LANCZOS
+            )
+            tk_image = ctk.CTkImage(image, size=image.size)
+
+            target_image = ctk.CTkLabel(
+                scrollable_frame,
+                text=f"T-{button_num}",
+                width=MAPPER_PREVIEW_MAX_WIDTH,
+                height=MAPPER_PREVIEW_MAX_HEIGHT,
+            )
+            target_image.grid(row=button_num, column=4, padx=20, pady=10)
+            target_image.configure(image=tk_image)
+            target_label_dict_live[button_num] = target_image
+        else:
+            update_pop_live_status("Face could not be detected in last upload!")
+        return map

modules/utilities.py

@@ -0,0 +1,209 @@
+import glob
+import mimetypes
+import os
+import platform
+import shutil
+import ssl
+import subprocess
+import urllib
+from pathlib import Path
+from typing import List, Any
+from tqdm import tqdm
+
+import modules.globals
+
+TEMP_FILE = "temp.mp4"
+TEMP_DIRECTORY = "temp"
+
+# monkey patch ssl for mac
+if platform.system().lower() == "darwin":
+    ssl._create_default_https_context = ssl._create_unverified_context
+
+
+def run_ffmpeg(args: List[str]) -> bool:
+    commands = [
+        "ffmpeg",
+        "-hide_banner",
+        "-hwaccel",
+        "auto",
+        "-loglevel",
+        modules.globals.log_level,
+    ]
+    commands.extend(args)
+    try:
+        subprocess.check_output(commands, stderr=subprocess.STDOUT)
+        return True
+    except Exception:
+        pass
+    return False
+
+
+def detect_fps(target_path: str) -> float:
+    command = [
+        "ffprobe",
+        "-v",
+        "error",
+        "-select_streams",
+        "v:0",
+        "-show_entries",
+        "stream=r_frame_rate",
+        "-of",
+        "default=noprint_wrappers=1:nokey=1",
+        target_path,
+    ]
+    output = subprocess.check_output(command).decode().strip().split("/")
+    try:
+        numerator, denominator = map(int, output)
+        return numerator / denominator
+    except Exception:
+        pass
+    return 30.0
+
+
+def extract_frames(target_path: str) -> None:
+    temp_directory_path = get_temp_directory_path(target_path)
+    run_ffmpeg(
+        [
+            "-i",
+            target_path,
+            "-pix_fmt",
+            "rgb24",
+            os.path.join(temp_directory_path, "%04d.png"),
+        ]
+    )
+
+
+def create_video(target_path: str, fps: float = 30.0) -> None:
+    temp_output_path = get_temp_output_path(target_path)
+    temp_directory_path = get_temp_directory_path(target_path)
+    run_ffmpeg(
+        [
+            "-r",
+            str(fps),
+            "-i",
+            os.path.join(temp_directory_path, "%04d.png"),
+            "-c:v",
+            modules.globals.video_encoder,
+            "-crf",
+            str(modules.globals.video_quality),
+            "-pix_fmt",
+            "yuv420p",
+            "-vf",
+            "colorspace=bt709:iall=bt601-6-625:fast=1",
+            "-y",
+            temp_output_path,
+        ]
+    )
+
+
+def restore_audio(target_path: str, output_path: str) -> None:
+    temp_output_path = get_temp_output_path(target_path)
+    done = run_ffmpeg(
+        [
+            "-i",
+            temp_output_path,
+            "-i",
+            target_path,
+            "-c:v",
+            "copy",
+            "-map",
+            "0:v:0",
+            "-map",
+            "1:a:0",
+            "-y",
+            output_path,
+        ]
+    )
+    if not done:
+        move_temp(target_path, output_path)
+
+
+def get_temp_frame_paths(target_path: str) -> List[str]:
+    temp_directory_path = get_temp_directory_path(target_path)
+    return glob.glob((os.path.join(glob.escape(temp_directory_path), "*.png")))
+
+
+def get_temp_directory_path(target_path: str) -> str:
+    target_name, _ = os.path.splitext(os.path.basename(target_path))
+    target_directory_path = os.path.dirname(target_path)
+    return os.path.join(target_directory_path, TEMP_DIRECTORY, target_name)
+
+
+def get_temp_output_path(target_path: str) -> str:
+    temp_directory_path = get_temp_directory_path(target_path)
+    return os.path.join(temp_directory_path, TEMP_FILE)
+
+
+def normalize_output_path(source_path: str, target_path: str, output_path: str) -> Any:
+    if source_path and target_path:
+        source_name, _ = os.path.splitext(os.path.basename(source_path))
+        target_name, target_extension = os.path.splitext(os.path.basename(target_path))
+        if os.path.isdir(output_path):
+            return os.path.join(
+                output_path, source_name + "-" + target_name + target_extension
+            )
+    return output_path
+
+
+def create_temp(target_path: str) -> None:
+    temp_directory_path = get_temp_directory_path(target_path)
+    Path(temp_directory_path).mkdir(parents=True, exist_ok=True)
+
+
+def move_temp(target_path: str, output_path: str) -> None:
+    temp_output_path = get_temp_output_path(target_path)
+    if os.path.isfile(temp_output_path):
+        if os.path.isfile(output_path):
+            os.remove(output_path)
+        shutil.move(temp_output_path, output_path)
+
+
+def clean_temp(target_path: str) -> None:
+    temp_directory_path = get_temp_directory_path(target_path)
+    parent_directory_path = os.path.dirname(temp_directory_path)
+    if not modules.globals.keep_frames and os.path.isdir(temp_directory_path):
+        shutil.rmtree(temp_directory_path)
+    if os.path.exists(parent_directory_path) and not os.listdir(parent_directory_path):
+        os.rmdir(parent_directory_path)
+
+
+def has_image_extension(image_path: str) -> bool:
+    return image_path.lower().endswith(("png", "jpg", "jpeg"))
+
+
+def is_image(image_path: str) -> bool:
+    if image_path and os.path.isfile(image_path):
+        mimetype, _ = mimetypes.guess_type(image_path)
+        return bool(mimetype and mimetype.startswith("image/"))
+    return False
+
+
+def is_video(video_path: str) -> bool:
+    if video_path and os.path.isfile(video_path):
+        mimetype, _ = mimetypes.guess_type(video_path)
+        return bool(mimetype and mimetype.startswith("video/"))
+    return False
+
+
+def conditional_download(download_directory_path: str, urls: List[str]) -> None:
+    if not os.path.exists(download_directory_path):
+        os.makedirs(download_directory_path)
+    for url in urls:
+        download_file_path = os.path.join(
+            download_directory_path, os.path.basename(url)
+        )
+        if not os.path.exists(download_file_path):
+            request = urllib.request.urlopen(url)  # type: ignore[attr-defined]
+            total = int(request.headers.get("Content-Length", 0))
+            with tqdm(
+                total=total,
+                desc="Downloading",
+                unit="B",
+                unit_scale=True,
+                unit_divisor=1024,
+            ) as progress:
+                urllib.request.urlretrieve(url, download_file_path, reporthook=lambda count, block_size, total_size: progress.update(block_size))  # type: ignore[attr-defined]
+
+
+def resolve_relative_path(path: str) -> str:
+    return os.path.abspath(os.path.join(os.path.dirname(__file__), path))

modules/video_capture.py

@@ -0,0 +1,94 @@
+import cv2
+import numpy as np
+from typing import Optional, Tuple, Callable
+import platform
+import threading
+
+# Only import Windows-specific library if on Windows
+if platform.system() == "Windows":
+    from pygrabber.dshow_graph import FilterGraph
+
+
+class VideoCapturer:
+    def __init__(self, device_index: int):
+        self.device_index = device_index
+        self.frame_callback = None
+        self._current_frame = None
+        self._frame_ready = threading.Event()
+        self.is_running = False
+        self.cap = None
+
+        # Initialize Windows-specific components if on Windows
+        if platform.system() == "Windows":
+            self.graph = FilterGraph()
+            # Verify device exists
+            devices = self.graph.get_input_devices()
+            if self.device_index >= len(devices):
+                raise ValueError(
+                    f"Invalid device index {device_index}. Available devices: {len(devices)}"
+                )
+
+    def start(self, width: int = 960, height: int = 540, fps: int = 60) -> bool:
+        """Initialize and start video capture"""
+        try:
+            if platform.system() == "Windows":
+                # Windows-specific capture methods
+                capture_methods = [
+                    (self.device_index, cv2.CAP_DSHOW),  # Try DirectShow first
+                    (self.device_index, cv2.CAP_ANY),  # Then try default backend
+                    (-1, cv2.CAP_ANY),  # Try -1 as fallback
+                    (0, cv2.CAP_ANY),  # Finally try 0 without specific backend
+                ]
+
+                for dev_id, backend in capture_methods:
+                    try:
+                        self.cap = cv2.VideoCapture(dev_id, backend)
+                        if self.cap.isOpened():
+                            break
+                        self.cap.release()
+                    except Exception:
+                        continue
+            else:
+                # Unix-like systems (Linux/Mac) capture method
+                self.cap = cv2.VideoCapture(self.device_index)
+
+            if not self.cap or not self.cap.isOpened():
+                raise RuntimeError("Failed to open camera")
+
+            # Configure format
+            self.cap.set(cv2.CAP_PROP_FRAME_WIDTH, width)
+            self.cap.set(cv2.CAP_PROP_FRAME_HEIGHT, height)
+            self.cap.set(cv2.CAP_PROP_FPS, fps)
+
+            self.is_running = True
+            return True
+
+        except Exception as e:
+            print(f"Failed to start capture: {str(e)}")
+            if self.cap:
+                self.cap.release()
+            return False
+
+    def read(self) -> Tuple[bool, Optional[np.ndarray]]:
+        """Read a frame from the camera"""
+        if not self.is_running or self.cap is None:
+            return False, None
+
+        ret, frame = self.cap.read()
+        if ret:
+            self._current_frame = frame
+            if self.frame_callback:
+                self.frame_callback(frame)
+            return True, frame
+        return False, None
+
+    def release(self) -> None:
+        """Stop capture and release resources"""
+        if self.is_running and self.cap is not None:
+            self.cap.release()
+            self.is_running = False
+            self.cap = None
+
+    def set_frame_callback(self, callback: Callable[[np.ndarray], None]) -> None:
+        """Set callback for frame processing"""
+        self.frame_callback = callback

mypi.ini

@@ -0,0 +1,7 @@
+[mypy]
+check_untyped_defs = True
+disallow_any_generics = True
+disallow_untyped_calls = True
+disallow_untyped_defs = True
+ignore_missing_imports = True
+strict_optional = False

requirements.txt

@@ -0,0 +1,21 @@
+--extra-index-url https://download.pytorch.org/whl/cu118
+
+numpy>=1.23.5,<2
+typing-extensions>=4.8.0
+opencv-python==4.10.0.84
+cv2_enumerate_cameras==1.1.15
+onnx==1.16.0
+insightface==0.7.3
+psutil==5.9.8
+tk==0.1.0
+customtkinter==5.2.2
+pillow==11.1.0
+torch==2.5.1+cu118; sys_platform != 'darwin'
+torch==2.5.1; sys_platform == 'darwin'
+torchvision==0.20.1; sys_platform != 'darwin'
+torchvision==0.20.1; sys_platform == 'darwin'
+onnxruntime-silicon==1.16.3; sys_platform == 'darwin' and platform_machine == 'arm64'
+onnxruntime-gpu==1.17; sys_platform != 'darwin'
+tensorflow; sys_platform != 'darwin'
+opennsfw2==0.10.2
+protobuf==4.23.2

run-cuda.bat

@@ -0,0 +1 @@
+python run.py --execution-provider cuda

run-directml.bat

@@ -0,0 +1 @@
+python run.py --execution-provider dml

run.py

@@ -0,0 +1,6 @@
+#!/usr/bin/env python3
+
+from modules import core
+
+if __name__ == '__main__':
+    core.run()