Skip to content

GitLab

Commit 0513d03d authored by jerrrrry's avatar jerrrrry
Browse files

Initial commit

parents
Pipeline #3321 canceled with stages
Expand all Show whitespace changes
Inline Side-by-side
Showing with 867 additions and 0 deletions
.gitignore 0 → 100755
View file @ 0513d03d
__pycache__
/ckpts/**/
\ No newline at end of file
LICENSE.txt 0 → 100755
View file @ 0513d03d
TENCENT HUNYUAN COMMUNITY LICENSE AGREEMENT
Tencent HunyuanVideo Release Date: December 3, 2024
THIS LICENSE AGREEMENT DOES NOT APPLY IN THE EUROPEAN UNION, UNITED KINGDOM AND SOUTH KOREA AND IS EXPRESSLY LIMITED TO THE TERRITORY, AS DEFINED BELOW.
By clicking to agree or by using, reproducing, modifying, distributing, performing or displaying any portion or element of the Tencent Hunyuan Works, including via any Hosted Service, You will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately.
1. DEFINITIONS.
a. “Acceptable Use Policy” shall mean the policy made available by Tencent as set forth in the Exhibit A.
b. “Agreement” shall mean the terms and conditions for use, reproduction, distribution, modification, performance and displaying of Tencent Hunyuan Works or any portion or element thereof set forth herein.
c. “Documentation” shall mean the specifications, manuals and documentation for Tencent Hunyuan made publicly available by Tencent.
d. “Hosted Service” shall mean a hosted service offered via an application programming interface (API), web access, or any other electronic or remote means.
e. “Licensee,” “You” or “Your” shall mean a natural person or legal entity exercising the rights granted by this Agreement and/or using the Tencent Hunyuan Works for any purpose and in any field of use.
f. “Materials” shall mean, collectively, Tencent’s proprietary Tencent Hunyuan and Documentation (and any portion thereof) as made available by Tencent under this Agreement.
g. “Model Derivatives” shall mean all: (i) modifications to Tencent Hunyuan or any Model Derivative of Tencent Hunyuan; (ii) works based on Tencent Hunyuan or any Model Derivative of Tencent Hunyuan; or (iii) any other machine learning model which is created by transfer of patterns of the weights, parameters, operations, or Output of Tencent Hunyuan or any Model Derivative of Tencent Hunyuan, to that model in order to cause that model to perform similarly to Tencent Hunyuan or a Model Derivative of Tencent Hunyuan, including distillation methods, methods that use intermediate data representations, or methods based on the generation of synthetic data Outputs by Tencent Hunyuan or a Model Derivative of Tencent Hunyuan for training that model. For clarity, Outputs by themselves are not deemed Model Derivatives.
h. “Output” shall mean the information and/or content output of Tencent Hunyuan or a Model Derivative that results from operating or otherwise using Tencent Hunyuan or a Model Derivative, including via a Hosted Service.
i. “Tencent,” “We” or “Us” shall mean THL A29 Limited.
j. “Tencent Hunyuan” shall mean the large language models, text/image/video/audio/3D generation models, and multimodal large language models and their software and algorithms, including trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing made publicly available by Us, including, without limitation to, Tencent HunyuanVideo released at [https://github.com/Tencent/HunyuanVideo].
k. “Tencent Hunyuan Works” shall mean: (i) the Materials; (ii) Model Derivatives; and (iii) all derivative works thereof.
l. “Territory” shall mean the worldwide territory, excluding the territory of the European Union, United Kingdom and South Korea.
m. “Third Party” or “Third Parties” shall mean individuals or legal entities that are not under common control with Us or You.
n. “including” shall mean including but not limited to.
2. GRANT OF RIGHTS.
We grant You, for the Territory only, a non-exclusive, non-transferable and royalty-free limited license under Tencent’s intellectual property or other rights owned by Us embodied in or utilized by the Materials to use, reproduce, distribute, create derivative works of (including Model Derivatives), and make modifications to the Materials, only in accordance with the terms of this Agreement and the Acceptable Use Policy, and You must not violate (or encourage or permit anyone else to violate) any term of this Agreement or the Acceptable Use Policy.
3. DISTRIBUTION.
You may, subject to Your compliance with this Agreement, distribute or make available to Third Parties the Tencent Hunyuan Works, exclusively in the Territory, provided that You meet all of the following conditions:
a. You must provide all such Third Party recipients of the Tencent Hunyuan Works or products or services using them a copy of this Agreement;
b. You must cause any modified files to carry prominent notices stating that You changed the files;
c. You are encouraged to: (i) publish at least one technology introduction blogpost or one public statement expressing Your experience of using the Tencent Hunyuan Works; and (ii) mark the products or services developed by using the Tencent Hunyuan Works to indicate that the product/service is “Powered by Tencent Hunyuan”; and
d. All distributions to Third Parties (other than through a Hosted Service) must be accompanied by a “Notice” text file that contains the following notice: “Tencent Hunyuan is licensed under the Tencent Hunyuan Community License Agreement, Copyright © 2024 Tencent. All Rights Reserved. The trademark rights of “Tencent Hunyuan” are owned by Tencent or its affiliate.”
You may add Your own copyright statement to Your modifications and, except as set forth in this Section and in Section 5, may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Model Derivatives as a whole, provided Your use, reproduction, modification, distribution, performance and display of the work otherwise complies with the terms and conditions of this Agreement (including as regards the Territory). If You receive Tencent Hunyuan Works from a Licensee as part of an integrated end user product, then this Section 3 of this Agreement will not apply to You.
4. ADDITIONAL COMMERCIAL TERMS.
If, on the Tencent Hunyuan version release date, the monthly active users of all products or services made available by or for Licensee is greater than 100 million monthly active users in the preceding calendar month, You must request a license from Tencent, which Tencent may grant to You in its sole discretion, and You are not authorized to exercise any of the rights under this Agreement unless or until Tencent otherwise expressly grants You such rights.
5. RULES OF USE.
a. Your use of the Tencent Hunyuan Works must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Tencent Hunyuan Works, which is hereby incorporated by reference into this Agreement. You must include the use restrictions referenced in these Sections 5(a) and 5(b) as an enforceable provision in any agreement (e.g., license agreement, terms of use, etc.) governing the use and/or distribution of Tencent Hunyuan Works and You must provide notice to subsequent users to whom You distribute that Tencent Hunyuan Works are subject to the use restrictions in these Sections 5(a) and 5(b).
b. You must not use the Tencent Hunyuan Works or any Output or results of the Tencent Hunyuan Works to improve any other AI model (other than Tencent Hunyuan or Model Derivatives thereof).
c. You must not use, reproduce, modify, distribute, or display the Tencent Hunyuan Works, Output or results of the Tencent Hunyuan Works outside the Territory. Any such use outside the Territory is unlicensed and unauthorized under this Agreement.
6. INTELLECTUAL PROPERTY.
a. Subject to Tencent’s ownership of Tencent Hunyuan Works made by or for Tencent and intellectual property rights therein, conditioned upon Your compliance with the terms and conditions of this Agreement, as between You and Tencent, You will be the owner of any derivative works and modifications of the Materials and any Model Derivatives that are made by or for You.
b. No trademark licenses are granted under this Agreement, and in connection with the Tencent Hunyuan Works, Licensee may not use any name or mark owned by or associated with Tencent or any of its affiliates, except as required for reasonable and customary use in describing and distributing the Tencent Hunyuan Works. Tencent hereby grants You a license to use “Tencent Hunyuan” (the “Mark”) in the Territory solely as required to comply with the provisions of Section 3(c), provided that You comply with any applicable laws related to trademark protection. All goodwill arising out of Your use of the Mark will inure to the benefit of Tencent.
c. If You commence a lawsuit or other proceedings (including a cross-claim or counterclaim in a lawsuit) against Us or any person or entity alleging that the Materials or any Output, or any portion of any of the foregoing, infringe any intellectual property or other right owned or licensable by You, then all licenses granted to You under this Agreement shall terminate as of the date such lawsuit or other proceeding is filed. You will defend, indemnify and hold harmless Us from and against any claim by any Third Party arising out of or related to Your or the Third Party’s use or distribution of the Tencent Hunyuan Works.
d. Tencent claims no rights in Outputs You generate. You and Your users are solely responsible for Outputs and their subsequent uses.
7. DISCLAIMERS OF WARRANTY AND LIMITATIONS OF LIABILITY.
a. We are not obligated to support, update, provide training for, or develop any further version of the Tencent Hunyuan Works or to grant any license thereto.
b. UNLESS AND ONLY TO THE EXTENT REQUIRED BY APPLICABLE LAW, THE TENCENT HUNYUAN WORKS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED “AS IS” WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES OF ANY KIND INCLUDING ANY WARRANTIES OF TITLE, MERCHANTABILITY, NONINFRINGEMENT, COURSE OF DEALING, USAGE OF TRADE, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING, REPRODUCING, MODIFYING, PERFORMING, DISPLAYING OR DISTRIBUTING ANY OF THE TENCENT HUNYUAN WORKS OR OUTPUTS AND ASSUME ANY AND ALL RISKS ASSOCIATED WITH YOUR OR A THIRD PARTY’S USE OR DISTRIBUTION OF ANY OF THE TENCENT HUNYUAN WORKS OR OUTPUTS AND YOUR EXERCISE OF RIGHTS AND PERMISSIONS UNDER THIS AGREEMENT.
c. TO THE FULLEST EXTENT PERMITTED BY APPLICABLE LAW, IN NO EVENT SHALL TENCENT OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, FOR ANY DAMAGES, INCLUDING ANY DIRECT, INDIRECT, SPECIAL, INCIDENTAL, EXEMPLARY, CONSEQUENTIAL OR PUNITIVE DAMAGES, OR LOST PROFITS OF ANY KIND ARISING FROM THIS AGREEMENT OR RELATED TO ANY OF THE TENCENT HUNYUAN WORKS OR OUTPUTS, EVEN IF TENCENT OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
8. SURVIVAL AND TERMINATION.
a. The term of this Agreement shall commence upon Your acceptance of this Agreement or access to the Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein.
b. We may terminate this Agreement if You breach any of the terms or conditions of this Agreement. Upon termination of this Agreement, You must promptly delete and cease use of the Tencent Hunyuan Works. Sections 6(a), 6(c), 7 and 9 shall survive the termination of this Agreement.
9. GOVERNING LAW AND JURISDICTION.
a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of the Hong Kong Special Administrative Region of the People’s Republic of China, without regard to conflict of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
b. Exclusive jurisdiction and venue for any dispute arising out of or relating to this Agreement will be a court of competent jurisdiction in the Hong Kong Special Administrative Region of the People’s Republic of China, and Tencent and Licensee consent to the exclusive jurisdiction of such court with respect to any such dispute.
 
EXHIBIT A
ACCEPTABLE USE POLICY
Tencent reserves the right to update this Acceptable Use Policy from time to time.
Last modified: November 5, 2024
Tencent endeavors to promote safe and fair use of its tools and features, including Tencent Hunyuan. You agree not to use Tencent Hunyuan or Model Derivatives:
1. Outside the Territory;
2. In any way that violates any applicable national, federal, state, local, international or any other law or regulation;
3. To harm Yourself or others;
4. To repurpose or distribute output from Tencent Hunyuan or any Model Derivatives to harm Yourself or others;
5. To override or circumvent the safety guardrails and safeguards We have put in place;
6. For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
7. To generate or disseminate verifiably false information and/or content with the purpose of harming others or influencing elections;
8. To generate or facilitate false online engagement, including fake reviews and other means of fake online engagement;
9. To intentionally defame, disparage or otherwise harass others;
10. To generate and/or disseminate malware (including ransomware) or any other content to be used for the purpose of harming electronic systems;
11. To generate or disseminate personal identifiable information with the purpose of harming others;
12. To generate or disseminate information (including images, code, posts, articles), and place the information in any public context (including –through the use of bot generated tweets), without expressly and conspicuously identifying that the information and/or content is machine generated;
13. To impersonate another individual without consent, authorization, or legal right;
14. To make high-stakes automated decisions in domains that affect an individual’s safety, rights or wellbeing (e.g., law enforcement, migration, medicine/health, management of critical infrastructure, safety components of products, essential services, credit, employment, housing, education, social scoring, or insurance);
15. In a manner that violates or disrespects the social ethics and moral standards of other countries or regions;
16. To perform, facilitate, threaten, incite, plan, promote or encourage violent extremism or terrorism;
17. For any use intended to discriminate against or harm individuals or groups based on protected characteristics or categories, online or offline social behavior or known or predicted personal or personality characteristics;
18. To intentionally exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;
19. For military purposes;
20. To engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or other professional practices.
Notice 0 → 100755
View file @ 0513d03d
Usage and Legal Notices:
Tencent is pleased to support the open source community by making Tencent HunyuanVideo available.
Copyright (C) 2024 THL A29 Limited, a Tencent company. All rights reserved. The below software and/or models in this distribution may have been modified by THL A29 Limited ("Tencent Modifications"). All Tencent Modifications are Copyright (C) THL A29 Limited.
Tencent HunyuanVideo is licensed under the TENCENT HUNYUAN COMMUNITY LICENSE AGREEMENT except for the third-party components listed below. Tencent HunyuanVideo does not impose any additional limitations beyond what is outlined in the repsective licenses of these third-party components. Users must comply with all terms and conditions of original licenses of these third-party components and must ensure that the usage of the third party components adheres to all relevant laws and regulations.
For avoidance of doubts, Tencent HunyuanVideo means the large language models and their software and algorithms, including trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing may be made publicly available by Tencent in accordance with TENCENT HUNYUAN COMMUNITY LICENSE AGREEMENT.
Other dependencies and licenses:
Open Source Model Licensed under the Apache License Version 2.0:
The below software in this distribution may have been modified by THL A29 Limited ("Tencent Modifications"). All Tencent Modifications are Copyright (C) 2024 THL A29 Limited.
--------------------------------------------------------------------
1. diffusers
Copyright (c) diffusers original author and authors
Please note this software has been modified by Tencent in this distribution.
2. transformers
Copyright (c) transformers original author and authors
3. safetensors
Copyright (c) safetensors original author and authors
4. flux
Copyright (c) flux original author and authors
Terms of the Apache License Version 2.0:
--------------------------------------------------------------------
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.
"Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
You must give any other recipients of the Work or Derivative Works a copy of this License; and
You must cause any modified files to carry prominent notices stating that You changed the files; and
You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
Open Source Software Licensed under the BSD 2-Clause License:
--------------------------------------------------------------------
1. imageio
Copyright (c) 2014-2022, imageio developers
All rights reserved.
Terms of the BSD 2-Clause License:
--------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Open Source Software Licensed under the BSD 3-Clause License:
--------------------------------------------------------------------
1. torchvision
Copyright (c) Soumith Chintala 2016,
All rights reserved.
2. flash-attn
Copyright (c) 2022, the respective contributors, as shown by the AUTHORS file.
All rights reserved.
Terms of the BSD 3-Clause License:
--------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
3. Neither the name of the copyright holder nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
Open Source Software Licensed under the BSD 3-Clause License and Other Licenses of the Third-Party Components therein:
--------------------------------------------------------------------
1. torch
Copyright (c) 2016- Facebook, Inc (Adam Paszke)
Copyright (c) 2014- Facebook, Inc (Soumith Chintala)
Copyright (c) 2011-2014 Idiap Research Institute (Ronan Collobert)
Copyright (c) 2012-2014 Deepmind Technologies (Koray Kavukcuoglu)
Copyright (c) 2011-2012 NEC Laboratories America (Koray Kavukcuoglu)
Copyright (c) 2011-2013 NYU (Clement Farabet)
Copyright (c) 2006-2010 NEC Laboratories America (Ronan Collobert, Leon Bottou, Iain Melvin, Jason Weston)
Copyright (c) 2006 Idiap Research Institute (Samy Bengio)
Copyright (c) 2001-2004 Idiap Research Institute (Ronan Collobert, Samy Bengio, Johnny Mariethoz)
A copy of the BSD 3-Clause is included in this file.
For the license of other third party components, please refer to the following URL:
https://github.com/pytorch/pytorch/tree/v2.1.1/third_party
Open Source Software Licensed under the BSD 3-Clause License and Other Licenses of the Third-Party Components therein:
--------------------------------------------------------------------
1. pandas
Copyright (c) 2008-2011, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team
All rights reserved.
Copyright (c) 2011-2023, Open source contributors.
A copy of the BSD 3-Clause is included in this file.
For the license of other third party components, please refer to the following URL:
https://github.com/pandas-dev/pandas/tree/v2.0.3/LICENSES
Open Source Software Licensed under the BSD 3-Clause License and Other Licenses of the Third-Party Components therein:
--------------------------------------------------------------------
1. numpy
Copyright (c) 2005-2022, NumPy Developers.
All rights reserved.
A copy of the BSD 3-Clause is included in this file.
For the license of other third party components, please refer to the following URL:
https://github.com/numpy/numpy/blob/v1.24.4/LICENSES_bundled.txt
Open Source Software Licensed under the MIT License:
--------------------------------------------------------------------
1. einops
Copyright (c) 2018 Alex Rogozhnikov
2. loguru
Copyright (c) 2017
Terms of the MIT License:
--------------------------------------------------------------------
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
Open Source Software Licensed under the MIT License and Other Licenses of the Third-Party Components therein:
--------------------------------------------------------------------
1. tqdm
Copyright (c) 2013 noamraph
A copy of the MIT is included in this file.
For the license of other third party components, please refer to the following URL:
https://github.com/tqdm/tqdm/blob/v4.66.2/LICENCE
Open Source Model Licensed under the MIT License:
--------------------------------------------------------------------
1. clip-large
Copyright (c) 2021 OpenAI
A copy of the MIT is included in this file.
--------------------------------------------------------------------
We may also use other third-party components:
1. llava-llama3
Copyright (c) llava-llama3 original author and authors
URL: https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-transformers#model
\ No newline at end of file
README.md 0 → 100755
View file @ 0513d03d
This diff is collapsed.
README_zh.md 0 → 100755
View file @ 0513d03d
This diff is collapsed.
assets/PenguinVideoBenchmark.csv 0 → 100755
View file @ 0513d03d
This diff is collapsed.
assets/WECHAT.md 0 → 100755
View file @ 0513d03d
<div align="center">
<img src=wechat.jpg width="60%"/>
<p> 扫码关注混元系列工作，加入「 Hunyuan Video 交流群」 </p>
<p> Scan the QR code to join the "Hunyuan Discussion Group" </p>
</div>
ckpts 0 → 120000
View file @ 0513d03d
/workspace/cicd/packages/hunyuan-video-t2v/ckpts
\ No newline at end of file
fix.sh 0 → 100644
View file @ 0513d03d
#!/bin/bash
cp modified/config.py /usr/local/lib/python3.10/dist-packages/xfuser/config/
cp modified/envs.py /usr/local/lib/python3.10/dist-packages/xfuser/
gradio_server.py 0 → 100755
View file @ 0513d03d
import os
import time
from pathlib import Path
from loguru import logger
from datetime import datetime
import gradio as gr
import random
from hyvideo.utils.file_utils import save_videos_grid
from hyvideo.config import parse_args
from hyvideo.inference import HunyuanVideoSampler
from hyvideo.constants import NEGATIVE_PROMPT
def initialize_model(model_path):
args = parse_args()
models_root_path = Path(model_path)
if not models_root_path.exists():
raise ValueError(f"`models_root` not exists: {models_root_path}")
hunyuan_video_sampler = HunyuanVideoSampler.from_pretrained(models_root_path, args=args)
return hunyuan_video_sampler
def generate_video(
model,
prompt,
resolution,
video_length,
seed,
num_inference_steps,
guidance_scale,
flow_shift,
embedded_guidance_scale
):
seed = None if seed == -1 else seed
width, height = resolution.split("x")
width, height = int(width), int(height)
negative_prompt = "" # not applicable in the inference
outputs = model.predict(
prompt=prompt,
height=height,
width=width,
video_length=video_length,
seed=seed,
negative_prompt=negative_prompt,
infer_steps=num_inference_steps,
guidance_scale=guidance_scale,
num_videos_per_prompt=1,
flow_shift=flow_shift,
batch_size=1,
embedded_guidance_scale=embedded_guidance_scale
)
samples = outputs['samples']
sample = samples[0].unsqueeze(0)
save_path = os.path.join(os.getcwd(), "gradio_outputs")
os.makedirs(save_path, exist_ok=True)
time_flag = datetime.fromtimestamp(time.time()).strftime("%Y-%m-%d-%H:%M:%S")
video_path = f"{save_path}/{time_flag}_seed{outputs['seeds'][0]}_{outputs['prompts'][0][:100].replace('/','')}.mp4"
save_videos_grid(sample, video_path, fps=24)
logger.info(f'Sample saved to: {video_path}')
return video_path
def create_demo(model_path, save_path):
model = initialize_model(model_path)
with gr.Blocks() as demo:
gr.Markdown("# Hunyuan Video Generation")
with gr.Row():
with gr.Column():
prompt = gr.Textbox(label="Prompt", value="A cat walks on the grass, realistic style.")
with gr.Row():
resolution = gr.Dropdown(
choices=[
# 720p
("1280x720 (16:9, 720p)", "1280x720"),
("720x1280 (9:16, 720p)", "720x1280"),
("1104x832 (4:3, 720p)", "1104x832"),
("832x1104 (3:4, 720p)", "832x1104"),
("960x960 (1:1, 720p)", "960x960"),
# 540p
("960x544 (16:9, 540p)", "960x544"),
("544x960 (9:16, 540p)", "544x960"),
("832x624 (4:3, 540p)", "832x624"),
("624x832 (3:4, 540p)", "624x832"),
("720x720 (1:1, 540p)", "720x720"),
],
value="1280x720",
label="Resolution"
)
video_length = gr.Dropdown(
label="Video Length",
choices=[
("2s(65f)", 65),
("5s(129f)", 129),
],
value=129,
)
num_inference_steps = gr.Slider(1, 100, value=50, step=1, label="Number of Inference Steps")
show_advanced = gr.Checkbox(label="Show Advanced Options", value=False)
with gr.Row(visible=False) as advanced_row:
with gr.Column():
seed = gr.Number(value=-1, label="Seed (-1 for random)")
guidance_scale = gr.Slider(1.0, 20.0, value=1.0, step=0.5, label="Guidance Scale")
flow_shift = gr.Slider(0.0, 10.0, value=7.0, step=0.1, label="Flow Shift")
embedded_guidance_scale = gr.Slider(1.0, 20.0, value=6.0, step=0.5, label="Embedded Guidance Scale")
show_advanced.change(fn=lambda x: gr.Row(visible=x), inputs=[show_advanced], outputs=[advanced_row])
generate_btn = gr.Button("Generate")
with gr.Column():
output = gr.Video(label="Generated Video")
generate_btn.click(
fn=lambda *inputs: generate_video(model, *inputs),
inputs=[
prompt,
resolution,
video_length,
seed,
num_inference_steps,
guidance_scale,
flow_shift,
embedded_guidance_scale
],
outputs=output
)
return demo
if __name__ == "__main__":
os.environ["GRADIO_ANALYTICS_ENABLED"] = "False"
server_name = os.getenv("SERVER_NAME", "0.0.0.0")
server_port = int(os.getenv("SERVER_PORT", "8081"))
args = parse_args()
print(args)
demo = create_demo(args.model_base, args.save_path)
demo.launch(server_name=server_name, server_port=server_port)
\ No newline at end of file
hyvideo/config.py 0 → 100755
View file @ 0513d03d
import argparse
from .constants import *
import re
from .modules.models import HUNYUAN_VIDEO_CONFIG
def parse_args(namespace=None):
parser = argparse.ArgumentParser(description="HunyuanVideo inference script")
parser = add_network_args(parser)
parser = add_extra_models_args(parser)
parser = add_denoise_schedule_args(parser)
parser = add_inference_args(parser)
parser = add_parallel_args(parser)
args = parser.parse_args(namespace=namespace)
args = sanity_check_args(args)
return args
def add_network_args(parser: argparse.ArgumentParser):
group = parser.add_argument_group(title="HunyuanVideo network args")
# Main model
group.add_argument(
"--model",
type=str,
choices=list(HUNYUAN_VIDEO_CONFIG.keys()),
default="HYVideo-T/2-cfgdistill",
)
group.add_argument(
"--latent-channels",
type=str,
default=16,
help="Number of latent channels of DiT. If None, it will be determined by `vae`. If provided, "
"it still needs to match the latent channels of the VAE model.",
)
group.add_argument(
"--precision",
type=str,
default="bf16",
choices=PRECISIONS,
help="Precision mode. Options: fp32, fp16, bf16. Applied to the backbone model and optimizer.",
)
# RoPE
group.add_argument(
"--rope-theta", type=int, default=256, help="Theta used in RoPE."
)
return parser
def add_extra_models_args(parser: argparse.ArgumentParser):
group = parser.add_argument_group(
title="Extra models args, including vae, text encoders and tokenizers)"
)
# - VAE
group.add_argument(
"--vae",
type=str,
default="884-16c-hy",
choices=list(VAE_PATH),
help="Name of the VAE model.",
)
group.add_argument(
"--vae-precision",
type=str,
default="fp16",
choices=PRECISIONS,
help="Precision mode for the VAE model.",
)
group.add_argument(
"--vae-tiling",
action="store_true",
help="Enable tiling for the VAE model to save GPU memory.",
)
group.set_defaults(vae_tiling=True)
group.add_argument(
"--text-encoder",
type=str,
default="llm",
choices=list(TEXT_ENCODER_PATH),
help="Name of the text encoder model.",
)
group.add_argument(
"--text-encoder-precision",
type=str,
default="fp16",
choices=PRECISIONS,
help="Precision mode for the text encoder model.",
)
group.add_argument(
"--text-states-dim",
type=int,
default=4096,
help="Dimension of the text encoder hidden states.",
)
group.add_argument(
"--text-len", type=int, default=256, help="Maximum length of the text input."
)
group.add_argument(
"--tokenizer",
type=str,
default="llm",
choices=list(TOKENIZER_PATH),
help="Name of the tokenizer model.",
)
group.add_argument(
"--prompt-template",
type=str,
default="dit-llm-encode",
choices=PROMPT_TEMPLATE,
help="Image prompt template for the decoder-only text encoder model.",
)
group.add_argument(
"--prompt-template-video",
type=str,
default="dit-llm-encode-video",
choices=PROMPT_TEMPLATE,
help="Video prompt template for the decoder-only text encoder model.",
)
group.add_argument(
"--hidden-state-skip-layer",
type=int,
default=2,
help="Skip layer for hidden states.",
)
group.add_argument(
"--apply-final-norm",
action="store_true",
help="Apply final normalization to the used text encoder hidden states.",
)
# - CLIP
group.add_argument(
"--text-encoder-2",
type=str,
default="clipL",
choices=list(TEXT_ENCODER_PATH),
help="Name of the second text encoder model.",
)
group.add_argument(
"--text-encoder-precision-2",
type=str,
default="fp16",
choices=PRECISIONS,
help="Precision mode for the second text encoder model.",
)
group.add_argument(
"--text-states-dim-2",
type=int,
default=768,
help="Dimension of the second text encoder hidden states.",
)
group.add_argument(
"--tokenizer-2",
type=str,
default="clipL",
choices=list(TOKENIZER_PATH),
help="Name of the second tokenizer model.",
)
group.add_argument(
"--text-len-2",
type=int,
default=77,
help="Maximum length of the second text input.",
)
return parser
def add_denoise_schedule_args(parser: argparse.ArgumentParser):
group = parser.add_argument_group(title="Denoise schedule args")
group.add_argument(
"--denoise-type",
type=str,
default="flow",
help="Denoise type for noised inputs.",
)
# Flow Matching
group.add_argument(
"--flow-shift",
type=float,
default=7.0,
help="Shift factor for flow matching schedulers.",
)
group.add_argument(
"--flow-reverse",
action="store_true",
help="If reverse, learning/sampling from t=1 -> t=0.",
)
group.add_argument(
"--flow-solver",
type=str,
default="euler",
help="Solver for flow matching.",
)
group.add_argument(
"--use-linear-quadratic-schedule",
action="store_true",
help="Use linear quadratic schedule for flow matching."
"Following MovieGen (https://ai.meta.com/static-resource/movie-gen-research-paper)",
)
group.add_argument(
"--linear-schedule-end",
type=int,
default=25,
help="End step for linear quadratic schedule for flow matching.",
)
return parser
def add_inference_args(parser: argparse.ArgumentParser):
group = parser.add_argument_group(title="Inference args")
# ======================== Model loads ========================
group.add_argument(
"--model-base",
type=str,
default="ckpts",
help="Root path of all the models, including t2v models and extra models.",
)
group.add_argument(
"--dit-weight",
type=str,
default="ckpts/hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt",
help="Path to the HunyuanVideo model. If None, search the model in the args.model_root."
"1. If it is a file, load the model directly."
"2. If it is a directory, search the model in the directory. Support two types of models: "
"1) named `pytorch_model_*.pt`"
"2) named `*_model_states.pt`, where * can be `mp_rank_00`.",
)
group.add_argument(
"--model-resolution",
type=str,
default="540p",
choices=["540p", "720p"],
help="Root path of all the models, including t2v models and extra models.",
)
group.add_argument(
"--load-key",
type=str,
default="module",
help="Key to load the model states. 'module' for the main model, 'ema' for the EMA model.",
)
group.add_argument(
"--use-cpu-offload",
action="store_true",
help="Use CPU offload for the model load.",
)
# ======================== Inference general setting ========================
group.add_argument(
"--batch-size",
type=int,
default=1,
help="Batch size for inference and evaluation.",
)
group.add_argument(
"--infer-steps",
type=int,
default=50,
help="Number of denoising steps for inference.",
)
group.add_argument(
"--disable-autocast",
action="store_true",
help="Disable autocast for denoising loop and vae decoding in pipeline sampling.",
)
group.add_argument(
"--save-path",
type=str,
default="./results",
help="Path to save the generated samples.",
)
group.add_argument(
"--save-path-suffix",
type=str,
default="",
help="Suffix for the directory of saved samples.",
)
group.add_argument(
"--name-suffix",
type=str,
default="",
help="Suffix for the names of saved samples.",
)
group.add_argument(
"--num-videos",
type=int,
default=1,
help="Number of videos to generate for each prompt.",
)
# ---sample size---
group.add_argument(
"--video-size",
type=int,
nargs="+",
default=(720, 1280),
help="Video size for training. If a single value is provided, it will be used for both height "
"and width. If two values are provided, they will be used for height and width "
"respectively.",
)
group.add_argument(
"--video-length",
type=int,
default=129,
help="How many frames to sample from a video. if using 3d vae, the number should be 4n+1",
)
# --- prompt ---
group.add_argument(
"--prompt",
type=str,
default=None,
help="Prompt for sampling during evaluation.",
)
group.add_argument(
"--seed-type",
type=str,
default="auto",
choices=["file", "random", "fixed", "auto"],
help="Seed type for evaluation. If file, use the seed from the CSV file. If random, generate a "
"random seed. If fixed, use the fixed seed given by `--seed`. If auto, `csv` will use the "
"seed column if available, otherwise use the fixed `seed` value. `prompt` will use the "
"fixed `seed` value.",
)
group.add_argument("--seed", type=int, default=None, help="Seed for evaluation.")
# Classifier-Free Guidance
group.add_argument(
"--neg-prompt", type=str, default=None, help="Negative prompt for sampling."
)
group.add_argument(
"--cfg-scale", type=float, default=1.0, help="Classifier free guidance scale."
)
group.add_argument(
"--embedded-cfg-scale",
type=float,
default=6.0,
help="Embeded classifier free guidance scale.",
)
group.add_argument(
"--use-fp8",
action="store_true",
help="Enable use fp8 for inference acceleration."
)
group.add_argument(
"--reproduce",
action="store_true",
help="Enable reproducibility by setting random seeds and deterministic algorithms.",
)
return parser
def add_parallel_args(parser: argparse.ArgumentParser):
group = parser.add_argument_group(title="Parallel args")
# ======================== Model loads ========================
group.add_argument(
"--ulysses-degree",
type=int,
default=1,
help="Ulysses degree.",
)
group.add_argument(
"--ring-degree",
type=int,
default=1,
help="Ulysses degree.",
)
return parser
def sanity_check_args(args):
# VAE channels
vae_pattern = r"\d{2,3}-\d{1,2}c-\w+"
if not re.match(vae_pattern, args.vae):
raise ValueError(
f"Invalid VAE model: {args.vae}. Must be in the format of '{vae_pattern}'."
)
vae_channels = int(args.vae.split("-")[1][:-1])
if args.latent_channels is None:
args.latent_channels = vae_channels
if vae_channels != args.latent_channels:
raise ValueError(
f"Latent channels ({args.latent_channels}) must match the VAE channels ({vae_channels})."
)
return args
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment