A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

OmniTransfer implementation for LTX-2 (work in progress)

AI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents

wip - running some training with overfitting - https://wandb.ai/snoozie/vasa-overfitting

视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.

Recommend new arxiv papers of your interest daily according to your Zotero libarary.

This is the official implementation of our paper: "MiniMax-Remover: Taming Bad Noise Helps Video Object Removal"

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

This repository contains the codes for LipGAN. LipGAN was published as a part of the paper titled "Towards Automatic Face-to-Face Translation".

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

Taming Stable Diffusion for Lip Sync!

Multi-GPU CUDA stress test

Official implementation of EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars

[CVPR 2025] SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation

Label Studio is a multi-type data labeling and annotation tool with standardized output format

Label Studio SDK

OpenMMLab Computer Vision Foundation

OpenMMLab Foundational Library for Training Deep Learning Models

Easily train a good VC model with voice data <= 10 mins!

LAVIS - A One-stop Library for Language-Vision Intelligence

[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation

Open Source Computer Vision Library

The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, HarmonyOS, WebAssembly, watchOS, tvOS, visionOS

OpenMMLab Model Deployment Framework

Next generation face swapper and enhancer

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.