Video2X: Machine learning video upscaling and interpolation
ML-powered video upscaling, frame interpolation, and restoration with multiple backend support.
Learn more about Video2X
Video2X is a comprehensive video enhancement toolkit that leverages state-of-the-art machine learning models to upscale, interpolate, and restore video content. It supports multiple processing backends including Real-ESRGAN, Anime4K, RIFE, and libplacebo for various enhancement tasks. The framework provides both CLI and GUI interfaces, enabling batch processing with hardware acceleration through NVIDIA CUDA, AMD ROCm, and Vulkan. Video2X handles complex video processing pipelines including codec management, audio preservation, and subtitle handling. It's particularly effective for anime content upscaling, real-world video enhancement, and frame rate interpolation up to 60fps or higher. The tool supports containerized deployment and includes comprehensive preprocessing options for optimal results across different video types.
Multiple AI Backend Support
Video2X integrates multiple cutting-edge machine learning models including Real-ESRGAN for photorealistic upscaling, Anime4K for anime-optimized enhancement, and RIFE for frame interpolation. Users can select the most appropriate algorithm for their specific content type, ensuring optimal quality enhancement whether working with anime, live-action footage, or mixed media content with flexible configuration options.
Hardware-Accelerated Processing
Leverages GPU acceleration across NVIDIA CUDA, AMD ROCm, and Vulkan backends to dramatically reduce processing time for large video files. The framework automatically optimizes memory usage and batch processing for maximum throughput, making it feasible to upscale hours of content efficiently. Multi-threading support and intelligent queue management ensure optimal hardware utilization throughout the enhancement pipeline.
Production-Ready Video Pipeline
Provides complete video processing infrastructure with automatic codec handling, audio stream preservation, subtitle management, and metadata retention. The system includes robust error handling, resume capability for interrupted processing, and comprehensive logging. Container support enables deployment in automated workflows, while the CLI interface facilitates integration into existing media processing pipelines with scriptable batch operations.
from video2x import Video2X
upscaler = Video2X()
upscaler.process(
input_path="input.mp4",
output_path="output_upscaled.mp4",
scale_factor=2
)Video2X 6.4.0 introduces Linux AppImage distribution, adds newer RIFE models, and significantly enhances the Qt6 GUI with improved task management.
- –Multi-versioning to critical functions to enhance performance in generic architecture builds.
- –RIFE models v4.25 and v4.26.
- –Support for processing videos without PTS information.
- –The feature to copy input streams' metadata to the output streams.
- –(Video2X Qt6) German translation.
This release fixes video processing issues including PTS precision problems and Qt6 interface bugs.
- –The issue of decreasing PTS precision with increasing video duration.
- –(Video2X Qt6) Errors restoring Real-CUGAN configs in the Edit Task dialog.
- –(Video2X Qt6) The incorrect comparison of version numbers.
Video2X 6.3.0 adds Real-CUGAN ncnn Vulkan support, introduces a unified logging system, and significantly enhances the Qt6 GUI with French translation.
- –A logger manager to provide unified logging across the application.
- –Support for Real-CUGAN ncnn Vulkan.
- –(Video2X Qt6) A check to ensure the required VC++ Redistributable version is installed.
- –(Video2X Qt6) A configuration manager to save user preferences like the last selected language.
- –(Video2X Qt6) A new logging widget to display logs in the UI.
See how people are using Video2X
Related Repositories
Discover similar tools and frameworks used by developers
Open Lovable
AI tool that generates React applications from website clones or user descriptions.
Stable Diffusion
Text-to-image diffusion in compressed latent space.
DINOv2
PyTorch vision transformers pretrained on 142M unlabeled images.
StabilityMatrix
Multi-backend inference UI manager with embedded dependencies.
Segment Anything
Transformer-based promptable segmentation with zero-shot generalization.