https://github.com/Djdefrag/FluidFrames
FluidFrames.RIFE | video AI frame-generation app
https://github.com/Djdefrag/FluidFrames
amd deep-learning directx12 fluidity fps frame frame-interpolation generation gui-application intel interpolation nvidia opencv python rife video windows
Last synced: about 2 months ago
JSON representation
FluidFrames.RIFE | video AI frame-generation app
- Host: GitHub
- URL: https://github.com/Djdefrag/FluidFrames
- Owner: Djdefrag
- License: mit
- Created: 2023-02-03T10:52:40.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-06-17T13:32:32.000Z (over 1 year ago)
- Last Synced: 2024-07-30T18:28:23.977Z (about 1 year ago)
- Topics: amd, deep-learning, directx12, fluidity, fps, frame, frame-interpolation, generation, gui-application, intel, interpolation, nvidia, opencv, python, rife, video, windows
- Language: Python
- Homepage:
- Size: 104 MB
- Stars: 142
- Watchers: 5
- Forks: 11
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
FluidFrames.RIFE | video AI frame generation app
## What is FluidFrames.RIFE?
FluidFrames.RIFE is a Windows app powered by RIFE AI to create frame-generated and slowmotion videos.
## Other AI projects.🤓
- https://github.com/Djdefrag/QualityScaler / QualityScaler - image/video AI upscaler app
- https://github.com/Djdefrag/RealScaler / RealScaler - image/video AI upscaler app (Real-ESRGAN)
## Credits.
- RIFE - https://github.com/megvii-research/ECCV2022-RIFE
- PraticalRIFE - https://github.com/hzwer/Practical-RIFE
## How is made. 🛠
FluidFrames is completely written in Python, from backend to frontend.
- [x] pytorch (https://github.com/pytorch/pytorch)
- [x] onnx (https://github.com/onnx/onnx)
- [x] onnxconverter-common (https://github.com/microsoft/onnxconverter-common)
- [x] onnxruntime-directml (https://github.com/microsoft/onnxruntime)
- [x] customtkinter (https://github.com/TomSchimansky/CustomTkinter)
- [x] openCV (https://github.com/opencv/opencv)
- [x] moviepy (https://github.com/Zulko/moviepy)
- [x] pyInstaller (https://github.com/pyinstaller/pyinstaller)
## Make it work by yourself. 👨💻
Prerequisites.
- Python installed on your pc (https://www.python.org/downloads/release/python-3119/)
- VSCode installed on your pc (https://code.visualstudio.com/)
- FFMPEG.exe downloaded (https://www.gyan.dev/ffmpeg/builds/) RELEASE BUILD > ffmpeg-release-essentials.7z
Getting started.
- Download the project on your PC (Green button Code > Download ZIP)
- Extract the project from the .zip
- Extract FFMPEG.exe in /Assets folder
- Open the project with VSCode (Drag&Drop the project directory on VSCode)
- Click on FluidFrames.py from left bar (VSCode will ask to install Python plugins)
- Install dependencies. In VSCode there is the "Terminal" panel, click there and execute the command "pip install -r requirements.txt"
- Close VSCode and re-open it (this will refresh all the dependecies installed)
- Click on the "Play button" in the upper right corner of VSCode
## Requirements. 🤓
- [ ] Windows 11 / Windows 10
- [ ] RAM >= 8Gb
- [ ] Any Directx12 compatible GPU with >= 2GB VRAM
## Features.
- [x] Elegant and easy to use GUI
- [x] Resize video before interpolation
- [x] Multiple GPUs support
- [x] Compatible video - mp4, wemb, gif, mkv, flv, avi, mov, qt
- [x] Video frame-generation STOP&RESUME
- [x] PRIVACY FOCUSED - no internet connection required / everything is on your PC
- [x] Video frames generation x2 / x4 / x8
- 30fps => x2 => 60fps
- 30fps => x4 => 120fps
- 30fps => x8 => 240fps
- [x] Video slowmotion x2 /x4
- 30fps => x2_slowmotion => 30fps - 2 times slower
- 30fps => x4_slowmotion => 30fps - 4 times slower
- 30fps => x8_slowmotion => 30fps - 8 times slower
## Next steps. 🤫
- [x] 1.X versions
- [x] Switch to Pytorch-directml to support all Directx12 compatible gpu (AMD, Intel, Nvidia)
- [x] New GUI with Windows 11 style
- [x] Include audio for processed video
- [x] Optimizing video frame resize and extraction speed
- [x] Multi GPU support (for pc with double GPU, integrated + dedicated)
- [x] Python 3.10 (expecting ~10% more performance)
- [x] Slowmotion function
- [x] 2.X versions
- [x] New, completely redesigned graphical interface based on @customtkinter
- [x] Fluidify multiple videos at once
- [x] Save AI generated frames as files
- [x] Support RIFE AI model updates
- [x] Support for RIFE_Lite AI model (a faster and lighter version of RIFE)
- [x] 3.x versions
- [x] New AI engine powered by onnxruntime-directml (https://github.com/microsoft/onnxruntime)
- [x] Python 3.11 (performance improvements)
- [x] Python 3.12 (performance improvements)
- [x] Display frame-generated videos info in the GUI
- [x] FFMPEG 7 (latest release)
- [x] Saving user settings (AI model, GPU, CPU etc.)
- [x] Video frame-generation STOP&RESUME
- [ ] 4.X version
- [x] Hardware accelerated video encoding (nvenc / amf / qsv)
- [x] More video extensions (.mp4 / .mkv / .avi / .mov)
- [x] Output resolution scaling
### Some Examples.
#### Videos
1. Original / x4 / x2-slomotion
https://github.com/Djdefrag/FluidFrames.RIFE/assets/32263112/e8e728b4-a2f5-4a74-8f04-5a5977c69fc4
https://github.com/Djdefrag/FluidFrames.RIFE/assets/32263112/21007233-b7ff-4836-a207-cfe3ed23ed28
3. Original / x4 / x4-slomotion
https://user-images.githubusercontent.com/32263112/235297757-5daf129e-4e19-4b8b-b6c8-b661ac1028db.mp4
https://user-images.githubusercontent.com/32263112/235297763-26bf9fdd-3d40-4aba-8688-5ef85a532ed0.mp4
https://user-images.githubusercontent.com/32263112/235297767-0adc4635-a43e-4c37-bd15-a24e1dd47f32.mp4
3. Original / x2
https://user-images.githubusercontent.com/32263112/222885925-a28122e8-92f8-4e53-b287-4ae17bb177c7.mp4
https://user-images.githubusercontent.com/32263112/222885933-f2e13869-984c-4192-8020-1668035e5cd3.mp4
4. Original / x2
https://user-images.githubusercontent.com/32263112/221165739-71dfd957-5d3d-481b-9a26-bb08d5affa6f.mp4
5. Original / x2 / x2-slomotion
https://user-images.githubusercontent.com/32263112/228229016-8b26c8f3-8a68-4b5e-b1ff-d52f9be76a03.mp4
https://user-images.githubusercontent.com/32263112/228229044-9d267a66-543e-43ca-890b-db6a70c29d0b.mp4
https://user-images.githubusercontent.com/32263112/228229083-d29a313f-3d28-4cdb-9d97-63410f28a608.mp4