Video2X runs AI video upscaling and frame interpolation on your own hardware. It's for people who want to increase a video's resolution or generate extra frames for smoother motion, including those working with anime footage. The project is open source under AGPL-3.0.
Its choice of processing methods is a useful distinction. Anime4K, Real-ESRGAN and Real-CUGAN handle upscaling, while RIFE handles frame interpolation. Video2X also accepts custom MPV-compatible GLSL shaders, so you're not limited to its bundled processing methods. The neural models run through ncnn with Vulkan GPU acceleration.
Windows users get a graphical interface, and the tool also runs on Linux. Docker and Podman container images provide another route on Linux and macOS. Local processing uses your machine's hardware; the optional Google Colab notebook runs the workload on Google's servers for people who don't have a suitable GPU of their own.
Hardware compatibility matters here: Video2X requires a Vulkan-capable GPU, with support spanning compatible NVIDIA, AMD and Intel hardware. Its precompiled binaries also require an AVX2-capable CPU. This is a GPU-based video processing tool, so those requirements are worth checking before choosing it.
The C/C++ processing pipeline avoids using extra disk space for intermediate files. You only need storage for the final output.
Claim this page and we'll verify you by hand. Video2X gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Video2X?Promote it
Something wrong or outdated on this page?
6KUpdated 2 months agoGPL-3.0
macOS · Windows · Linux#Batch processing#ONNX#Visual workflows
chaiNNer is a desktop image processing editor for people who want AI upscaling and repeatable editing workflows without writing scripts. It runs models locally on Windows, macOS, and Linux. Connected nodes let you combine model processing with ordinary image edits in the same workflow.
36.9KUpdated 2 years agoBSD-3-Clause
macOS · Windows · Linux#Batch processing
7.3KUpdated 1 week agoApache-2.0
macOS · Windows · Linux · Docker · Web#ControlNet#Image-to-image#Inpainting
9.7KUpdated 1 day ago
macOS · Windows · Linux · Docker · Web#Batch processing#ControlNet#GGUF
30.1KUpdated 1 day ago
macOS · Windows#Image-to-image
FaceFusion is an AI face manipulation tool for photos and videos that processes media on your own machine. It's aimed at content creators, VFX artists, and film studios that want control over their footage and personal data. Local processing keeps that media on your hardware rather than sending it to a cloud service.
606Updated 4 days agoApache-2.0
Windows#ControlNet#GGUF#Inpainting
Real-ESRGAN is a local AI upscaler and restoration toolkit for people enlarging images or improving video, with dedicated models for anime illustrations and animation. It builds on ESRGAN and uses models trained entirely on synthetic data to address degraded images. The code is open source under the BSD 3-Clause license.
SD.Next is a self-hosted web interface for artists, researchers and people who want to generate and edit images or videos on their own hardware. It builds on Automatic1111 WebUI's original codebase and supports Stable Diffusion alongside other diffusion models. It's open source under Apache 2.0.
Wan2GP brings video, image, music and speech generation to your own computer, with particular attention to GPUs with limited memory. It's for creators who want several media models in one browser interface. The project builds on Wan-Video/Wan2.1.
Amuse combines AI generation with media editing in a Windows app that runs models on your own hardware. It's for people who want to create images, video, audio and text locally, then work on the results in the same application. Its editor also accepts existing local video.