General Introduction FaceFusion is an advanced cloud platform with integrated facial exchange and enhancement features that optimizes the image-to-video and image-to-image exchange process with 5 professional models to ensure flawless output. In addition, it performs facial enhancement with 7 models, using 3 different models to boost...
General Introduction Kotaemon is an open source document Q&A tool designed to provide end-users and developers with Q&A capabilities based on Retrieval Augmented Generation (RAG). Developed by Cinnamon, the project supports a variety of LLM API providers (e.g. OpenAI, AzureOpenAI, Cohere, etc.) as well as native...
GizAI is a one-stop platform with integrated AI generation, note-taking and cloud storage capabilities. Users can generate images, videos, audio, text, characters, stories, and games with GizAI, and can take collaborative notes and cloud storage on the platform.GizAI offers a wide range of AI tools to help users increase productivity and creativity, while protecting user privacy and not using user data for AI training without consent. GizAI is operated by Giz Inc. founded in Stripe Atlas and supported by programs such as Google for Startups Cloud, Microsoft for Startups Founders Hub, AWS Activate, and Paddle AI LaunchPad, among others.GizAI believes that using advanced, generative AI technology is everyone's right, offers a free ad-supported program, and allows users to generate, collaborate, and share content.
Comprehensive introduction HivisionIDPhotos is an open source lightweight AI document photo production tools, can intelligently identify the user photo scene and keying, to generate a standard document photo in line with a variety of specifications. The tool supports custom background colors and sizes, and in the future will also launch the beauty and intelligent change of formal dress function. With...
General Introduction Marker is a deep learning based document processing tool designed to convert PDF files to Markdown format quickly and accurately. It supports a wide range of document types and is especially optimized for conversion of books and scientific papers.Marker is able to remove redundant content such as headers and footers, format tables and...
General Introduction VideoReTalking is an innovative system that allows users to generate lip-synchronized facial videos based on input audio, producing high-quality and lip-synchronized output videos even with different emotions. The system breaks down this goal into three successive tasks: facial video generation with typical expressions...
General Introduction MuseV is a public project on GitHub that aims to enable the generation of avatar videos of unlimited length and high fidelity. It is based on diffusion technology and offers Image2Video, Text2Image2Video, Video2Video and many other features. Provides model structure, use cases, quick start...
Comprehensive Introduction Unstructured-IO provides a range of open source components for processing and preprocessing images and text documents such as PDF, HTML, Word documents, etc. Its main goal is to simplify and optimize data processing workflow , especially for large language model (LLM) applications to provide support.Unstructured...
General Introduction magic-html is a Python library designed to simplify the process of extracting body region content from HTML. Whether dealing with complex HTML structures or simple web pages, this library aims to provide a convenient and efficient interface for users. It supports multimodal extraction, multiple layout extracto...
WebPilot General Introduction Webpilot is a free and open source "web assistant" that allows you to communicate freely with any web page or perform automated tasks. Instead of switching pages or copying and pasting, just select text or enter commands, and webpilot will provide you with real-time information and smart...
DreamTalk Comprehensive Introduction DreamTalk is a diffusion model-driven expression talking head generation framework, jointly developed by Tsinghua University, Alibaba Group and Huazhong University of Science and Technology. It is mainly composed of three parts: a noise reduction network, a style-aware lip expert and a style predictor, and is able to generate a variety of audio input based on...
