#
BoatNg
Follow
Starred repositories
基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.
[ECCV 2022] AutoTransition: Learning to Recommend Video Transition Effects
📹 Data-driven render automation for After Effects
The web-based motion graphics editor for everyone 📽
基于Dify自主创建的AI应用DSL工作流，你可以免费获取，无论是出于个人需求还是学习目的，它都能为您开启一段充满无限可能的智能之旅。
Easily compute clip embeddings from video frames
Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>
Pytorch domain library for recommendation systems
Best Practices on Recommendation Systems
A tool to beautify your code screenshots. Built with SolidJS and Fastify.
Fast subdomains enumeration tool for penetration testers
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
vue and ffmpeg based tool for video clips. 使用vue(vue3) + ffmpeg + wasm 实现纯前端音视频编辑，功能包括：视频剪辑、音频剪辑、音频合成裁剪、音波展示、视频抽帧、gif抽帧、帧播放器、字幕、贴图、时间轴、素材轨道
轻量、灵活、易上手的Python剪映草稿生成及导出工具，构建全自动化视频剪辑/混剪流水线
利用AI大模型，一键解说并剪辑视频； Using AI models to automatically provide commentary and edit videos with a single click.
🚀🎬 ShortGPT - Experimental AI framework for youtube shorts / tiktok channel automation
A general video understanding codebase from SenseTime X-Lab
Attribution (or visual explanation) methods for understanding video classification networks. Demo codes for WACV2021 paper: Towards Visually Explaining Video Understanding Networks with Perturbation.
PyTorch implementation of I3D model for video classification, mixed with the CRF smoothing layer for multi-label classification.
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
The official codes for "Aurora: Activating chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning"
WebAV is an SDK built on WebCodecs, designed for creating and editing video files on the web platform. WebAV 是基于 WebCodecs 构建的 SDK，用于在 Web 平台上创建/编辑视频文件。
Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Using VideoBERT to tackle video prediction