[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly …

A customisable 3D platform for agent-based AI research

Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

View model summaries in PyTorch!

Count the MACs / FLOPs of your PyTorch model.

Simple script for downloading Youtube comments without using the Youtube API

real time face swap and one-click video deepfake with only a single image

Multi-modality pre-training

Wiseflow is an agile information mining tool that extracts concise messages from various sources such as websites, WeChat official accounts, social platforms, etc. It automatically categorizes and …

Open Source realtime backend in 1 file

real time face swap and one-click video deepfake with only a single image (uncensored)

The Database Toolkit for Python

A feature-rich command-line audio/video downloader

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

A python script that discovers hidden YouTube API clients. Just a research project.

CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.

The fastest way to create an HTML app

Downloads videos and playlists from YouTube

Intelligent proxy pool for Humans™ to extract content from the internet and build your own Large Language Models in this new AI era

Python ProxyPool for web spider

Command-line program to download videos from YouTube.com and other video sites

Python Client for Google's Private InnerTube API. Works with YouTube, YouTube Music and more!

Invidious is an alternative front-end to YouTube

[NeurIPS 2024] A Generalizable World Model for Autonomous Driving

A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。

[CSUR] A Survey on Video Diffusion Models