Upload 5 files

.gitattributes

@@ -1,35 +1,35 @@
-*.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
+*.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

.gitignore

@@ -0,0 +1,178 @@
+hf_download/
+outputs/
+repo/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc

LICENSE

@@ -0,0 +1,201 @@
+                                 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:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) 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
+
+      (d) 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
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,14 +1,483 @@
----
-title: FramePack
-emoji: 🏆
-colorFrom: purple
-colorTo: blue
-sdk: gradio
-sdk_version: 5.27.0
-app_file: app.py
-pinned: false
-license: apache-2.0
-short_description: Video diffusion, but feels like image diffusion.
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+<p align="center">
+    <img src="https://github.com/user-attachments/assets/2cc030b4-87e1-40a0-b5bf-1b7d6b62820b" width="300">
+</p>
+
+# FramePack
+
+Official implementation and desktop software for ["Packing Input Frame Context in Next-Frame Prediction Models for Video Generation"](https://lllyasviel.github.io/frame_pack_gitpage/).
+
+Links: [**Paper**](https://arxiv.org/abs/2504.12626), [**Project Page**](https://lllyasviel.github.io/frame_pack_gitpage/)
+
+FramePack is a next-frame (next-frame-section) prediction neural network structure that generates videos progressively. 
+
+FramePack compresses input contexts to a constant length so that the generation workload is invariant to video length.
+
+FramePack can process a very large number of frames with 13B models even on laptop GPUs.
+
+FramePack can be trained with a much larger batch size, similar to the batch size for image diffusion training.
+
+**Video diffusion, but feels like image diffusion.**
+
+# Notes
+
+Note that this GitHub repository is the only official FramePack website. We do not have any web services. All other websites are spam and fake, including but not limited to `framepack.co`, `frame_pack.co`, `framepack.net`, `frame_pack.net`, `framepack.ai`, `frame_pack.ai`, `framepack.pro`, `frame_pack.pro`, `framepack.cc`, `frame_pack.cc`,`framepackai.co`, `frame_pack_ai.co`, `framepackai.net`, `frame_pack_ai.net`, `framepackai.pro`, `frame_pack_ai.pro`, `framepackai.cc`, `frame_pack_ai.cc`, and so on. Again, they are all spam and fake. **Do not pay money or download files from any of those websites.**
+
+The team is on leave between April 21 and 29. PR merging will be delayed.
+
+# Requirements
+
+Note that this repo is a functional desktop software with minimal standalone high-quality sampling system and memory management.
+
+**Start with this repo before you try anything else!**
+
+Requirements:
+
+* Nvidia GPU in RTX 30XX, 40XX, 50XX series that supports fp16 and bf16. The GTX 10XX/20XX are not tested.
+* Linux or Windows operating system.
+* At least 6GB GPU memory.
+
+To generate 1-minute video (60 seconds) at 30fps (1800 frames) using 13B model, the minimal required GPU memory is 6GB. (Yes 6 GB, not a typo. Laptop GPUs are okay.)
+
+About speed, on my RTX 4090 desktop it generates at a speed of 2.5 seconds/frame (unoptimized) or 1.5 seconds/frame (teacache). On my laptops like 3070ti laptop or 3060 laptop, it is about 4x to 8x slower. [Troubleshoot if your speed is much slower than this.](https://github.com/lllyasviel/FramePack/issues/151#issuecomment-2817054649)
+
+In any case, you will directly see the generated frames since it is next-frame(-section) prediction. So you will get lots of visual feedback before the entire video is generated.
+
+# Installation
+
+**Windows**:
+
+[>>> Click Here to Download One-Click Package (CUDA 12.6 + Pytorch 2.6) <<<](https://github.com/lllyasviel/FramePack/releases/download/windows/framepack_cu126_torch26.7z)
+
+After you download, you uncompress, use `update.bat` to update, and use `run.bat` to run.
+
+Note that running `update.bat` is important, otherwise you may be using a previous version with potential bugs unfixed.
+
+![image](https://github.com/lllyasviel/stable-diffusion-webui-forge/assets/19834515/c49bd60d-82bd-4086-9859-88d472582b94)
+
+Note that the models will be downloaded automatically. You will download more than 30GB from HuggingFace.
+
+**Linux**:
+
+We recommend having an independent Python 3.10.
+
+    pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
+    pip install -r requirements.txt
+
+To start the GUI, run:
+
+    python demo_gradio.py
+
+Note that it supports `--share`, `--port`, `--server`, and so on.
+
+The software supports PyTorch attention, xformers, flash-attn, sage-attention. By default, it will just use PyTorch attention. You can install those attention kernels if you know how. 
+
+For example, to install sage-attention (linux):
+
+    pip install sageattention==1.0.6
+
+However, you are highly recommended to first try without sage-attention since it will influence results, though the influence is minimal.
+
+# GUI
+
+![ui](https://github.com/user-attachments/assets/8c5cdbb1-b80c-4b7e-ac27-83834ac24cc4)
+
+On the left you upload an image and write a prompt.
+
+On the right are the generated videos and latent previews.
+
+Because this is a next-frame-section prediction model, videos will be generated longer and longer.
+
+You will see the progress bar for each section and the latent preview for the next section.
+
+Note that the initial progress may be slower than later diffusion as the device may need some warmup.
+
+# Sanity Check
+
+Before trying your own inputs, we highly recommend going through the sanity check to find out if any hardware or software went wrong. 
+
+Next-frame-section prediction models are very sensitive to subtle differences in noise and hardware. Usually, people will get slightly different results on different devices, but the results should look overall similar. In some cases, if possible, you'll get exactly the same results.
+
+## Image-to-5-seconds
+
+Download this image:
+
+<img src="https://github.com/user-attachments/assets/f3bc35cf-656a-4c9c-a83a-bbab24858b09" width="150">
+
+Copy this prompt:
+
+`The man dances energetically, leaping mid-air with fluid arm swings and quick footwork.`
+
+Set like this:
+
+(all default parameters, with teacache turned off)
+![image](https://github.com/user-attachments/assets/0071fbb6-600c-4e0f-adc9-31980d540e9d)
+
+The result will be:
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/bc74f039-2b14-4260-a30b-ceacf611a185" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>Video may be compressed by GitHub</em>
+    </td>
+  </tr>
+</table>
+
+**Important Note:**
+
+Again, this is a next-frame-section prediction model. This means you will generate videos frame-by-frame or section-by-section.
+
+**If you get a much shorter video in the UI, like a video with only 1 second, then it is totally expected.** You just need to wait. More sections will be generated to complete the video.
+
+## Know the influence of TeaCache and Quantization
+
+Download this image:
+
+<img src="https://github.com/user-attachments/assets/42293e30-bdd4-456d-895c-8fedff71be04" width="150">
+
+Copy this prompt:
+
+`The girl dances gracefully, with clear movements, full of charm.`
+
+Set like this:
+
+![image](https://github.com/user-attachments/assets/4274207d-5180-4824-a552-d0d801933435)
+
+Turn off teacache:
+
+![image](https://github.com/user-attachments/assets/53b309fb-667b-4aa8-96a1-f129c7a09ca6)
+
+You will get this:
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/04ab527b-6da1-4726-9210-a8853dda5577" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>Video may be compressed by GitHub</em>
+    </td>
+  </tr>
+</table>
+
+Now turn on teacache:
+
+![image](https://github.com/user-attachments/assets/16ad047b-fbcc-4091-83dc-d46bea40708c)
+
+About 30% users will get this (the other 70% will get other random results depending on their hardware):
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/149fb486-9ccc-4a48-b1f0-326253051e9b" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>A typical worse result.</em>
+    </td>
+  </tr>
+</table>
+
+So you can see that teacache is not really lossless and sometimes can influence the result a lot.
+
+We recommend using teacache to try ideas and then using the full diffusion process to get high-quality results.
+
+This recommendation also applies to sage-attention, bnb quant, gguf, etc., etc.
+
+## Image-to-1-minute
+
+<img src="https://github.com/user-attachments/assets/820af6ca-3c2e-4bbc-afe8-9a9be1994ff5" width="150">
+
+`The girl dances gracefully, with clear movements, full of charm.`
+
+![image](https://github.com/user-attachments/assets/8c34fcb2-288a-44b3-a33d-9d2324e30cbd)
+
+Set video length to 60 seconds:
+
+![image](https://github.com/user-attachments/assets/5595a7ea-f74e-445e-ad5f-3fb5b4b21bee)
+
+If everything is in order you will get some result like this eventually.
+
+60s version:
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/c3be4bde-2e33-4fd4-b76d-289a036d3a47" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>Video may be compressed by GitHub</em>
+    </td>
+  </tr>
+</table>
+
+6s version:
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/37fe2c33-cb03-41e8-acca-920ab3e34861" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>Video may be compressed by GitHub</em>
+    </td>
+  </tr>
+</table>
+
+# More Examples
+
+Many more examples are in [**Project Page**](https://lllyasviel.github.io/frame_pack_gitpage/).
+
+Below are some more examples that you may be interested in reproducing.
+
+---
+
+<img src="https://github.com/user-attachments/assets/99f4d281-28ad-44f5-8700-aa7a4e5638fa" width="150">
+
+`The girl dances gracefully, with clear movements, full of charm.`
+
+![image](https://github.com/user-attachments/assets/0e98bfca-1d91-4b1d-b30f-4236b517c35e)
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/cebe178a-09ce-4b7a-8f3c-060332f4dab1" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>Video may be compressed by GitHub</em>
+    </td>
+  </tr>
+</table>
+
+---
+
+<img src="https://github.com/user-attachments/assets/853f4f40-2956-472f-aa7a-fa50da03ed92" width="150">
+
+`The girl suddenly took out a sign that said “cute” using right hand`
+
+![image](https://github.com/user-attachments/assets/d51180e4-5537-4e25-a6c6-faecae28648a)
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/116069d2-7499-4f38-ada7-8f85517d1fbb" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>Video may be compressed by GitHub</em>
+    </td>
+  </tr>
+</table>
+
+---
+
+<img src="https://github.com/user-attachments/assets/6d87c53f-81b2-4108-a704-697164ae2e81" width="150">
+
+`The girl skateboarding, repeating the endless spinning and dancing and jumping on a skateboard, with clear movements, full of charm.`
+
+![image](https://github.com/user-attachments/assets/c2cfa835-b8e6-4c28-97f8-88f42da1ffdf)
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/d9e3534a-eb17-4af2-a8ed-8e692e9993d2" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>Video may be compressed by GitHub</em>
+    </td>
+  </tr>
+</table>
+
+---
+
+<img src="https://github.com/user-attachments/assets/6e95d1a5-9674-4c9a-97a9-ddf704159b79" width="150">
+
+`The girl dances gracefully, with clear movements, full of charm.`
+
+![image](https://github.com/user-attachments/assets/7412802a-ce44-4188-b1a4-cfe19f9c9118)
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/e1b3279e-e30d-4d32-b55f-2fb1d37c81d2" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>Video may be compressed by GitHub</em>
+    </td>
+  </tr>
+</table>
+
+---
+
+<img src="https://github.com/user-attachments/assets/90fc6d7e-8f6b-4f8c-a5df-ee5b1c8b63c9" width="150">
+
+`The man dances flamboyantly, swinging his hips and striking bold poses with dramatic flair.`
+
+![image](https://github.com/user-attachments/assets/1dcf10a3-9747-4e77-a269-03a9379dd9af)
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/aaa4481b-7bf8-4c64-bc32-909659767115" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>Video may be compressed by GitHub</em>
+    </td>
+  </tr>
+</table>
+
+---
+
+<img src="https://github.com/user-attachments/assets/62ecf987-ec0c-401d-b3c9-be9ffe84ee5b" width="150">
+
+`The woman dances elegantly among the blossoms, spinning slowly with flowing sleeves and graceful hand movements.`
+
+![image](https://github.com/user-attachments/assets/396f06bc-e399-4ac3-9766-8a42d4f8d383)
+
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/f23f2f37-c9b8-45d5-a1be-7c87bd4b41cf" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>Video may be compressed by GitHub</em>
+    </td>
+  </tr>
+</table>
+
+---
+
+<img src="https://github.com/user-attachments/assets/4f740c1a-2d2f-40a6-9613-d6fe64c428aa" width="150">
+
+`The young man writes intensely, flipping papers and adjusting his glasses with swift, focused movements.`
+
+![image](https://github.com/user-attachments/assets/c4513c4b-997a-429b-b092-bb275a37b719)
+
+<table>
+  <tr>
+    <td align="center" width="300">
+      <video 
+        src="https://github.com/user-attachments/assets/62e9910e-aea6-4b2b-9333-2e727bccfc64" 
+        controls 
+        style="max-width:100%;">
+      </video>
+    </td>
+  </tr>
+  <tr>
+    <td align="center">
+      <em>Video may be compressed by GitHub</em>
+    </td>
+  </tr>
+</table>
+
+---
+
+# Prompting Guideline
+
+Many people would ask how to write better prompts. 
+
+Below is a ChatGPT template that I personally often use to get prompts:
+
+    You are an assistant that writes short, motion-focused prompts for animating images.
+
+    When the user sends an image, respond with a single, concise prompt describing visual motion (such as human activity, moving objects, or camera movements). Focus only on how the scene could come alive and become dynamic using brief phrases.
+
+    Larger and more dynamic motions (like dancing, jumping, running, etc.) are preferred over smaller or more subtle ones (like standing still, sitting, etc.).
+
+    Describe subject, then motion, then other things. For example: "The girl dances gracefully, with clear movements, full of charm."
+
+    If there is something that can dance (like a man, girl, robot, etc.), then prefer to describe it as dancing.
+
+    Stay in a loop: one image in, one motion prompt out. Do not explain, ask questions, or generate multiple options.
+
+You paste the instruct to ChatGPT and then feed it an image to get prompt like this:
+
+![image](https://github.com/user-attachments/assets/586c53b9-0b8c-4c94-b1d3-d7e7c1a705c3)
+
+*The man dances powerfully, striking sharp poses and gliding smoothly across the reflective floor.*
+
+Usually this will give you a prompt that works well. 
+
+You can also write prompts yourself. Concise prompts are usually preferred, for example:
+
+*The girl dances gracefully, with clear movements, full of charm.*
+
+*The man dances powerfully, with clear movements, full of energy.*
+
+and so on.
+
+# Cite
+
+    @article{zhang2025framepack,
+        title={Packing Input Frame Contexts in Next-Frame Prediction Models for Video Generation},
+        author={Lvmin Zhang and Maneesh Agrawala},
+        journal={Arxiv},
+        year={2025}
+    }

requirements.txt

@@ -0,0 +1,15 @@
+accelerate==1.6.0
+diffusers==0.33.1
+transformers==4.46.2
+gradio==5.23.0
+sentencepiece==0.2.0
+pillow==11.1.0
+av==12.1.0
+numpy==1.26.2
+scipy==1.12.0
+requests==2.31.0
+torchsde==0.2.6
+
+einops
+opencv-contrib-python
+safetensors