HeisenBerg?'s Projects
a pipeline for turning heavily speech-based video files into clean, readable text from the audio. Currently in .py script and Google Colab formats.
for influencers and creator live streaming or live camera record when talking
Blind&Invisible Watermark ,图片盲水印,提取水印无须原图!
AutoVideo: An Automated Video Action Recognition System
Automatically edits vidx. Explanation here: https://www.youtube.com/watch?v=DQ8orIurGxw
how to generate metadata of video using gpt, clickbait title, description, thumbnail, tags
Open source scripts for videos I publish on YouTube.
A video library where you can learn to draw.
A website to stream Anime and read Manga for free.. Everything is scraped from sources online and we don't need to actually host any videos or images.
Extract the audio from a video - then translate to text
:cloud: CDNDrive = BiliDrive + SuperBed,支持任意文件的转换为视频 全速上传与下载
automatic video supercuts with python
使用ffmpeg将横向视频逆时针旋转九十度,以用来
Overlay dynamic analytics data onto 3D models using the Vertex Platform.
Assistive-Webdriver is a tool to automate end-to-end web application tests with a screen reader.
Extract the video subtitle by the RapidOCR, and this project is faster and totally off-line.
一键将视觉小说/Galgame以高分辨率重制,现已支持Kirikiri2/Z及Artemis引擎
Deploy Vite app to GitHub Pages using GitHub Actions
Tauri + Vite + Vue 3 + Vuetify 3 desktop app template
VLDB Papers including authors and abstracts.
通过GitHub的actions 自动采集节点 生成订阅信息
字幕翻译器 电子书翻译
Voice Ask me anything app. Built with Next.js, Prisma, TypeScript, Tailwind, React Query, and Cloudinary.
Local image generation using VQGAN-CLIP or CLIP guided diffusion
Containerized package for V Rising server using Wine
Volunteer Relationship Management System: This is an ambitious project to create a system that will help us measure our human capital development, reduce repetitive tasks and processes, and improve outcomes.
VTuber Cam, macOS app that displays an avatar using a virtual camera.