Articles by Yang Fan

Glif This tool we have introduced many times before, built-in rich image creative workflow, many small red book pop-up creative images are from this tool. Use Glif you do not need to carry out complex configurations, because the author has encapsulated the entire process, you only need to fill in the input box with text or images, the subsequent flow ...

General Introduction FlipSketch is an open source project designed to convert static drawings into text-guided animations. Hosted on GitHub, the project provides an innovative tool that allows users to generate animation effects from text descriptions.FlipSketch combines image processing and natural language processing techniques...

Today, we are pleased to release FLUX.1 Tools, a modeling suite designed to add control and steerability to our base text-generated image model, FLUX.1, and to support the modification and re-creation of real and generated images. At the time of release, FLUX.1 Tools includes four unique features,...

General Introduction AutoFlow is an open source tool developed by PingCAP to build graph-based knowledge bases with TiDB serverless vector storage. It integrates LlamaIndex and DSPy framework to support complex dialog search and knowledge graph editing. Users can use a simple JavaScript surrogate...

ColBERT (Contextualized Post-Cultural Interaction based on BERT) is different from the traditional dense embedding model. Here is a brief description of how ColBERT works: Token-level embedding: Unlike directly creating a single vector for an entire document or query, ColBERT creates embedding vectors for each Token. After...

General Introduction good luck have fun (glhf.chat) is a website that provides an open source big model chat service. The platform allows users to run almost any open source big model using vLLM and a custom auto-scaling GPU scheduler. Users can simply paste a link to the Hugging Face repository to use the chat...

Embedding and reordering are important nodes needed to handle the knowledge base process, a good embedding model allows for a better understanding of the semantics, and a reordering model is necessary to order the knowledge fragments. Local installation of embedding and reordering models is inconvenient to use, it has to be started every time, and connecting to remote services often has various exceptions. Moreover, the small size ...

codeium can be used normally in China, especially in Windsurf, you can write the code normally if you select any model, because it does not call the original interface of the model directly. The reason of unavailability usually appears in the registration and login stage, please choose to enter the email password to register, if you choose G...

Windsurf Many people are not adapted to the use of the English interface, in fact, he and VS switch the same principle of the Chinese interface, only need a Chinese extension. Here to teach you quickly set Windsurf for the Chinese interface. First of all, open Windsurf, click on the right side of the extension, and then enter the Chinese language, download the expansion of the Earth logo. &nb...

Comprehensive introduction Ruying AI Video Synthesis is an AI video generation platform launched by Shanghai Yuyi Technology Co. Relying on "SenseNova", a large modeling capability of SenseNova, the platform provides a variety of digital human images and timbres to choose from, so that users can generate realistic AI videos by simply inputting the text. This...

Comprehensive Introduction Maxun is an open source no-code web data extraction platform that allows users to train robots in minutes to automatically crawl web data and convert it into APIs or spreadsheets. The platform supports paging and scrolling, can adapt to changes in website layout, provides powerful data crawling features for...

General Introduction Flux.1-dev-Controlnet-Upscaler is an image super-resolution tool developed by the Jasper AI research team to improve the quality of low-resolution images. The tool utilizes ControlNet technology to process images through a complex synthetic data degradation scheme that can effectively...

We're excited to announce the public beta of AI Shell! AI Shell enhances your shell with AI features that make interacting with the command line even easier.AI Shell creates an interactive shell that not only interacts with a wide range of large language models, but also provides a framework for you to...

  Introduction GraphRAG (Graph Structure Based Retrieval Enhanced Generation) is an advanced retrieval and generation method. It combines the advantages of graph data structures with the capabilities of Large Language Models (LLMs) to overcome some of the limitations of traditional RAG systems. https://github.com/adithya-s-k/AI-Engi...

General Introduction Cicada is a platform focusing on digital human video creation, utilizing AI technology to simplify the video production process. Users can choose different digital human images, input copy and generate videos with multi-language voiceovers. The platform provides a rich library of templates and materials, which are suitable for a variety of fields such as advertising and marketing, education and training...

General Introduction Apify is a full-stack web crawling and data extraction platform that provides a variety of tools and services to help users automate data extraction from any website. Users can use off-the-shelf crawling tools or build and distribute their own data extraction tools.Apify supports multiple programming languages and frameworks and provides...

Resource List Top 10 1000 Most Common Tokens 1000 Most Common Negative Tokens 20 Most Common Samplers 100 Most Common Steps 100 Most Common Dimensions 50 Most Common CFG Scales Online Pre...

Comprehensive Introduction BoltAI is a high-performance AI app designed for macOS that integrates a variety of AI models and services, including local models and cloud models. Users can seamlessly switch between different AI services in one app for a variety of scenarios such as programming, content creation, learning, etc. BoltAI works through OpenAI's G...