Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Welcome to the WSO2 API Manager source code! For info on working with the WSO2 API Manager repository and contributing code, click the link below.

Webui for using XTTS and for finetuning it

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

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.

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.

🔥 CNN for Watermark Removal using Deep Image Prior with Pytorch 🔥.

自定义Docker服务

vits2 backbone with multilingual-bert

Next generation face swapper and enhancer

a machine learning image inpainting task that instinctively removes watermarks from image indistinguishable from the ground truth image

CVPR2023 talking face implementation for Identity-Preserving Talking Face Generation With Landmark and Appearance Priors

自定义

本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。

自定义

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translatio…

Custom OpenCV

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

3D Reconstruction Software

Photogrammetric Computer Vision Framework

Generate 3D objects conditioned on text or images

Hackable and optimized Transformers building blocks, supporting a composable construction.

(ICCV2023) official repository for "Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation"

🔊 Text-Prompted Generative Audio Model

Lightning fast C++/CUDA neural network framework