Creating engaging and thrilling montages from your favorite video game moments has never been easier with Crispy, a machine-learning algorithm crafted for efficiency. In this guide, we’ll walk you through the installation process, configuration, and how to create your own montages. Let’s get started!
What is Crispy?
Crispy is a powerful machine-learning algorithm designed specifically to highlight and compile the best moments from video games. Its neural network scans each frame to detect the defined highlights, making your editing seamless and efficient.
Supported games include:
Installation and Setup
1. Prerequisites
Before diving in, ensure you have ffmpeg installed. ffprobe is also a necessity.
2. Downloading Crispy
You can find Crispy Releases available for both Windows and Linux. Make sure to download the correct file according to your operating system.
3. Running the Setup
After unzipping the downloaded file, run the setup.sh or setup.bat to configure the environment. Next, add your videos in mp4 or mp3 format to the resources folder.
Configuration
Your Crispy setup is customizable through a settings.json file. Here, you can modify parameters to tweak the algorithm’s behavior:
{
"neural-network": {
"confidence": 0.8
},
"clip": {
"framerate": 8,
"second-before": 3,
"second-after": 3,
"second-between-kills": 5
},
"stretch": false,
"game": "valorant"
}
Think of this configuration as a chef’s recipe—it guides the algorithm in selecting ingredients (frames) to make the perfect highlight dish (montage). Adjusting the “confidence” is like deciding how certain you need to be before serving—if you lower it, you invite more candidates (frames) for a taste, but also open the potential for a few less desirable ones.
Recommended Settings
Finding the optimal settings may involve some trial and error, but here are some tried-and-true configurations:
- Valorant:
{ "neural-network": { "confidence": 0.8 }, "clip": { "framerate": 8, "second-before": 4, "second-after": 0.5, "second-between-kills": 3 }, "stretch": false, "game": "valorant" } - Overwatch:
{ "neural-network": { "confidence": 0.6 }, "clip": { "framerate": 8, "second-before": 4, "second-after": 3, "second-between-kills": 5 }, "stretch": false, "game": "overwatch" } - CSGO2:
{ "neural-network": { "confidence": 0.7 }, "clip": { "framerate": 8, "second-before": 4, "second-after": 1, "second-between-kills": 3 }, "stretch": false, "game": "csgo2" } - The Finals:
{ "clip": { "framerate": 4, "second-before": 6, "second-after": 0, "second-between-kills": 6 }, "stretch": false, "game": "thefinals" }
Creating Your Montage
Once you have your settings down, simply run the application using the run.sh or run.bat file. The application has a user-friendly web interface allowing you to manage clips, segments, music, effects, and results seamlessly.
Troubleshooting
If you encounter issues such as slow processing times or frames not being detected, consider the following:
- Ensure that ffmpeg is correctly installed and accessible.
- If you’re experiencing slowness, especially in The Finals, lower the framerate in the settings to optimize speed without significantly sacrificing results.
- Check if your videos are in the correct format (mp4 or mp3) to be recognized by Crispy.
- Adjust the confidence settings to see if it improves detection quality.
For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.
Conclusion
At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.
With this guide, you should be well-equipped to navigate Crispy and create fantastic montages that capture your best gaming moments. Happy editing!

