k4yt3x/video2x

Add support for arbitrary ncnn, PyTorch or ONNX models

Open

#1231 opened on Nov 18, 2024

View on GitHub
 (25 comments) (2 reactions) (0 assignees)C++ (19,891 stars) (1,735 forks)batch import
help wantedstate:Backlogtype:Enhancement

Description

Hello, i love Video2x, but i think there is few models to upscale different types of footage. Would it possible to add more models, like from openmodeldb.info for example? Thanks in advance!

Contributor guide

Tech stack
cpppytorch
Domain
machine learningai
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
5
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
unclear
Prerequisites
Familiarity with C++Understanding of ML inferenceKnowledge of PyTorch or ONNXVideo2x build system
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
15
Research direction
Investigate the existing model loading code in the video2x repository, likely located in src/ directory. Review the comments in issue #1231 for maintainer feedback on desired architecture. Study the APIs of ncnn, PyTorch, and ONNX for inference. Propose a design for supporting arbitrary models, possibly through a plugin or configuration system.