ArchitectGPT is an AI-powered design tool that revolutionizes home and interior design. It allows users to transform their design dreams into reality with cutting-edge AI technology that understands and adapts to their vision. With features like diverse design themes, smart room customization, curated color palettes, and effortless design experience, ArchitectGPT enables users to create stunning transformations in seconds. From transforming living spaces to visualizing technical designs, ArchitectGPT offers a seamless and intuitive platform for users to bring their creative visions to life with photorealistic precision.

qbiq is a generative AI platform designed for real estate layout design and virtual tours. It automates architectural planning processes, providing customized layout plans for any space and tenant within 24 hours. By utilizing deep-learning technology, qbiq delivers architectural-grade plans and data-driven insights, revolutionizing real estate layout planning for landlords, brokers, and architects. The platform aims to accelerate deal cycles, improve closing rates, reduce vacancy rates, and empower users to make faster and more informed decisions.

Space Planner AI is a web-based space planning tool that helps users create and manage floor plans. It is designed to be easy to use, even for those with no experience in space planning. Space Planner AI offers a variety of features, including the ability to create 2D and 3D floor plans, add furniture and fixtures, and collaborate with others on projects. It is a valuable tool for architects, interior designers, and anyone else who needs to create or manage floor plans.

Deep Space AI is an innovative platform that revolutionizes the construction industry by providing intelligent solutions for design and construction workflows. The platform offers collaborative data management, actionable insights, and coordination tools to streamline construction processes and improve operational efficiency. Deep Space AI enhances transparency, boosts productivity, and empowers teams to make informed decisions throughout all project phases. Trusted by leading teams in the design and construction industry, Deep Space AI is a game-changer in the AECO sector.

Interior Render AI is an AI-powered interior design tool that allows users to generate high-quality interior design renderings in various styles based on reference images. Users can upload indoor photos or design sketches and provide a natural language description of their desired style. The AI will then generate realistic and visually appealing renderings that can be used for inspiration, communication, and idea pitching. Interior Render AI is a valuable tool for interior designers, architects, and anyone looking to redesign their space.

Varys AI is an interior design AI tool that utilizes GPT technology to assist professionals in creating high-quality renders and design solutions effortlessly. Users can talk to a GPT advisor to develop blueprints, generate design solutions with multiple angles, and receive strategic advice for retail businesses. The tool allows for quick refurbishments, ultra-quality renders with unlimited style choices, and instant document generation with elegant wording. Varys AI aims to redefine space design workflows, improve business performance, and accelerate commercial growth through project series expansion.

VSDECO is a revolutionary AI-powered platform that empowers users to transform photos, sketches, and drawings into stunning photorealistic renders. With VSDECO, you can visualize your interior design ideas and bring your vision to life. Our platform offers a wide range of design styles to choose from, allowing you to personalize your restyling project and create the perfect space for your needs. Whether you're an architect, designer, realtor, or homeowner, VSDECO empowers you to visualize and realize your vision effortlessly.

Remodel AI is an AI-powered application that allows users to generate inspiring interior and exterior concepts for their homes in less than 30 seconds. With over 24580 remodeling designs generated, users can upload images of their home's exterior or interior and see fully remodeled versions with new flooring, wall treatments, and furniture layouts. The application offers customization options for facade style, building type, and quality, providing a seamless experience for home remodeling enthusiasts.

DreamzAR is an innovative AI landscape and interior design application that redefines yard elegance and interior spaces. The app offers a wealth of garden design ideas tailored to users' yards, allowing them to effortlessly transform their outdoor and indoor spaces with the help of advanced technology. DreamzAR provides unique front and backyard landscaping ideas, virtual property staging, and a gallery of inspiring landscape and interior designs. Users can easily visualize their design concepts by uploading photos of their yards and leveraging AI-powered tools to create stunning and personalized designs. With features like 2D and 3D design tools, augmented reality capabilities, and a vast collection of plants and garden elements, DreamzAR makes landscape and interior design accessible, efficient, and cost-effective.

Paintit.ai is an AI-driven interior design service that revolutionizes space design by leveraging the latest in AI technology. It offers personalized and innovative design solutions for residential and commercial spaces, capturing unique visions and style preferences. Users can upload photos of their space, select design preferences, and receive AI-generated design concepts that can be refined to align with individual tastes and visions.

Designera is an AI-powered design tool that allows users to create design ideas specialized to their interior spaces in seconds. Users can upload images of their rooms, select room types and themes, and receive design suggestions tailored to their preferences. The tool provides a platform for users to explore creative design concepts and get inspired by a community of designers. Designera aims to simplify the design process and empower users to visualize and transform their living spaces with ease.

Arrival is a cutting-edge software solution that allows users to design 3D virtual spaces with AI assistance and drag-and-drop functionality. It enables effortless creation of immersive environments by utilizing a built-in text-to-3D ML model, a user-friendly drag & drop interface, and seamless integration with leading virtual worlds and video gaming marketplaces.

Benty is an AI-powered application called 'Your One-Stop Shop for Home Improvement & Kitchen Bliss!' that offers a curated selection of quality essentials to enhance living spaces. Users can create unique rooms using AI technology, redesigning interiors in various themes. With trusted reviews and a growing customer base, Benty aims to revolutionize home improvement projects with its innovative features and user-friendly interface.

CinematicInteriorAI is an AI-powered application that allows users to transform their living spaces into cinematic and artistic masterpieces inspired by movies, cartoons, and famous artists. Users can upload a photo of their room, select a preferred style, and let the AI work its magic to generate a redesigned room image. With a diverse style library and the ability to share and inspire others, CinematicInteriorAI offers unlimited creative possibilities for interior design enthusiasts.

Luw.ai is an AI-powered architecture tool that allows users to design their dream spaces with AI prompts or redesign existing spaces by snapping a photo. It offers over 55 design styles and can assist users in enhancing design choices using data from them. Luw.ai also has a personalized AI image generator that connects to over 10 AIs to create designs tailored to the user's AI persona needs. Additionally, it offers features such as a magic wand tool for removing, adding, or replacing objects, AI rendering, and 3D to image conversion.

ArchiVinci is an innovative suite of AI-driven design tools encompassing the Sketch to Architectural Render AI Tool, Exterior Design AI Tool, Interior Design AI Tool, and Landscape Design AI Tool. It empowers users to effortlessly transform sketches into detailed architectural designs and enhance various aspects of design, from exteriors to interiors and landscapes.

Tilesview is a cutting-edge 3D room visualizer and tile visualizer application powered by advanced AI technology. It allows users to visualize walls, floors, rugs, paint colors, tiles, wallpapers, and carpets in a virtual space with precision. The tool revolutionizes the way businesses in the flooring and wall covering industry operate, enabling faster decision-making, increased customer engagement, and higher conversion rates. With features like core products visualizer, 360 panorama view, generating catalogs, and website integration, Tilesview offers a comprehensive solution for manufacturers, distributors, retailers, and e-commerce platforms. The application caters to various roles such as importers/exporters, tiles designers, digital media marketers, and sales professionals, empowering them with tools to enhance visualization, marketing efforts, and sales conversions.

Luma AI is a 3D capture platform that allows users to create interactive 3D scenes from videos. With Luma AI, users can capture 3D models of people, objects, and environments, and then use those models to create interactive experiences such as virtual tours, product demonstrations, and training simulations.

ReRoom AI is an AI-powered interior design tool that allows users to upload a picture of their project and discover 20+ unique design styles. Users can then enjoy photorealistic renders of their project in just seconds. ReRoom AI is perfect for anyone who wants to quickly and easily create beautiful and realistic interior designs.

Coated is an AI Interior Design Assistant that allows users to effortlessly transform any space by creating beautiful and personalized designs. Users can upload a photo, select a preferred style from a variety of options, and let Coated handle the rest. With 11+ predefined interior styles to choose from, users can easily decorate their spaces to reflect their unique preferences and tastes.

A curated list of Generative AI projects, tools, artworks, and models

This repository provides a systematic and comprehensive review of efficient LLMs research. We organize the literature in a taxonomy consisting of three main categories, covering distinct yet interconnected efficient LLMs topics from **model-centric** , **data-centric** , and **framework-centric** perspective, respectively. We hope our survey and this GitHub repository can serve as valuable resources to help researchers and practitioners gain a systematic understanding of the research developments in efficient LLMs and inspire them to contribute to this important and exciting field.

xLSTM is a new Recurrent Neural Network architecture based on ideas of the original LSTM. Through Exponential Gating with appropriate normalization and stabilization techniques and a new Matrix Memory it overcomes the limitations of the original LSTM and shows promising performance on Language Modeling when compared to Transformers or State Space Models. The package is based on PyTorch and was tested for versions >=1.8. For the CUDA version of xLSTM, you need Compute Capability >= 8.0. The xLSTM tool provides two main components: xLSTMBlockStack for non-language applications or integrating in other architectures, and xLSTMLMModel for language modeling or other token-based applications.

The Persian License Plate Recognition (PLPR) system is a state-of-the-art solution designed for detecting and recognizing Persian license plates in images and video streams. Leveraging advanced deep learning models and a user-friendly interface, it ensures reliable performance across different scenarios. The system offers advanced detection using YOLOv5 models, precise recognition of Persian characters, real-time processing capabilities, and a user-friendly GUI. It is well-suited for applications in traffic monitoring, automated vehicle identification, and similar fields. The system's architecture includes modules for resident management, entrance management, and a detailed flowchart explaining the process from system initialization to displaying results in the GUI. Hardware requirements include an Intel Core i5 processor, 8 GB RAM, a dedicated GPU with at least 4 GB VRAM, and an SSD with 20 GB of free space. The system can be installed by cloning the repository and installing required Python packages. Users can customize the video source for processing and run the application to upload and process images or video streams. The system's GUI allows for parameter adjustments to optimize performance, and the Wiki provides in-depth information on the system's architecture and model training.

cake is a pure Rust implementation of the llama3 LLM distributed inference based on Candle. The project aims to enable running large models on consumer hardware clusters of iOS, macOS, Linux, and Windows devices by sharding transformer blocks. It allows running inferences on models that wouldn't fit in a single device's GPU memory by batching contiguous transformer blocks on the same worker to minimize latency. The tool provides a way to optimize memory and disk space by splitting the model into smaller bundles for workers, ensuring they only have the necessary data. cake supports various OS, architectures, and accelerations, with different statuses for each configuration.

Awesome Mamba is a curated collection of groundbreaking research papers and articles on Mamba Architecture, a pioneering framework in deep learning known for its selective state spaces and efficiency in processing complex data structures. The repository offers a comprehensive exploration of Mamba architecture through categorized research papers covering various domains like visual recognition, speech processing, remote sensing, video processing, activity recognition, image enhancement, medical imaging, reinforcement learning, natural language processing, 3D recognition, multi-modal understanding, time series analysis, graph neural networks, point cloud analysis, and tabular data handling.

AIInfra is an open-source project focused on AI infrastructure, specifically targeting large models in distributed clusters, distributed architecture, distributed training, and algorithms related to large models. The project aims to explore and study system design in artificial intelligence and deep learning, with a focus on the hardware and software stack for building AI large model systems. It provides a comprehensive curriculum covering topics such as AI chip principles, communication and storage, AI clusters, large model training, and inference, as well as algorithms for large models. The course is designed for undergraduate and graduate students, as well as professionals working with AI large model systems, to gain a deep understanding of AI computer system architecture and design.

This repository contains scripts and tools for evaluating a chat app that uses the RAG architecture. It provides parameters to assess the quality and style of answers generated by the chat app, including system prompt, search parameters, and GPT model parameters. The tools facilitate running evaluations, with examples of evaluations on a sample chat app. The repo also offers guidance on cost estimation, setting up the project, deploying a GPT-4 model, generating ground truth data, running evaluations, and measuring the app's ability to say 'I don't know'. Users can customize evaluations, view results, and compare runs using provided tools.

A repository that lists papers related to Large Language Model (LLM) based agents. The repository covers various topics including survey, planning, feedback & reflection, memory mechanism, role playing, game playing, tool usage & human-agent interaction, benchmark & evaluation, environment & platform, agent framework, multi-agent system, and agent fine-tuning. It provides a comprehensive collection of research papers on LLM-based agents, exploring different aspects of AI agent architectures and applications.

Agentq is a tool that utilizes various agentic architectures to complete tasks on the web reliably. It includes a planner-navigator multi-agent architecture, a solo planner-actor agent, an actor-critic multi-agent architecture, and an actor-critic architecture with reinforcement learning and DPO finetuning. The repository also contains an open-source implementation of the research paper 'Agent Q'. Users can set up the tool by installing dependencies, starting Chrome in dev mode, and setting up necessary environment variables. The tool can be run to perform various tasks related to autonomous AI agents.

Only Train Once (OTO) is an automatic, architecture-agnostic DNN training and compression framework that allows users to train a general DNN from scratch or a pretrained checkpoint to achieve high performance and slimmer architecture simultaneously in a one-shot manner without fine-tuning. The framework includes features for automatic structured pruning and erasing operators, as well as hybrid structured sparse optimizers for efficient model compression. OTO provides tools for pruning zero-invariant group partitioning, constructing pruned models, and visualizing pruning and erasing dependency graphs. It supports the HESSO optimizer and offers a sanity check for compliance testing on various DNNs. The repository also includes publications, installation instructions, quick start guides, and a roadmap for future enhancements and collaborations.

A curated list of high-quality papers on resource-efficient Large Language Models (LLMs) with a focus on various aspects such as architecture design, pre-training, fine-tuning, inference, system design, and evaluation metrics. The repository covers topics like efficient transformer architectures, non-transformer architectures, memory efficiency, data efficiency, model compression, dynamic acceleration, deployment optimization, support infrastructure, and other related systems. It also provides detailed information on computation metrics, memory metrics, energy metrics, financial cost metrics, network communication metrics, and other metrics relevant to resource-efficient LLMs. The repository includes benchmarks for evaluating the efficiency of NLP models and references for further reading.

VinAI_Translate is a Vietnamese-English Neural Machine Translation System offering state-of-the-art text-to-text translation models for Vietnamese-to-English and English-to-Vietnamese. The system includes pre-trained models with different configurations and parameters, allowing for further fine-tuning. Users can interact with the models through the VinAI Translate system website or the HuggingFace space 'VinAI Translate'. Evaluation scripts are available for assessing the translation quality. The tool can be used in the 'transformers' library for Vietnamese-to-English and English-to-Vietnamese translations, supporting both GPU-based batch translation and CPU-based sequence translation examples.

Scrape It Now is a versatile tool for scraping websites with features like decoupled architecture, CLI functionality, idempotent operations, and content storage options. The tool includes a scraper component for efficient scraping, ad blocking, link detection, markdown extraction, dynamic content loading, and anonymity features. It also offers an indexer component for creating AI search indexes, chunking content, embedding chunks, and enabling semantic search. The tool supports various configurations for Azure services and local storage, providing flexibility and scalability for web scraping and indexing tasks.

Blinko is an innovative open-source project designed for individuals who want to quickly capture and organize their fleeting thoughts. It allows users to seamlessly jot down ideas the moment they strike, ensuring that no spark of creativity is lost. With advanced AI-powered note retrieval, data ownership, efficient and fast capturing, lightweight architecture, and open collaboration, Blinko offers a comprehensive solution for managing and accessing notes.

The xLSTM-jax repository contains code for training and evaluating the xLSTM model on language modeling using JAX. xLSTM is a Recurrent Neural Network architecture that improves upon the original LSTM through Exponential Gating, normalization, stabilization techniques, and a Matrix Memory. It is optimized for large-scale distributed systems with performant triton kernels for faster training and inference.

MetaGPT is a multi-agent framework that enables GPT to work in a software company, collaborating to tackle more complex tasks. It assigns different roles to GPTs to form a collaborative entity for complex tasks. MetaGPT takes a one-line requirement as input and outputs user stories, competitive analysis, requirements, data structures, APIs, documents, etc. Internally, MetaGPT includes product managers, architects, project managers, and engineers. It provides the entire process of a software company along with carefully orchestrated SOPs. MetaGPT's core philosophy is "Code = SOP(Team)", materializing SOP and applying it to teams composed of LLMs.

Agency is a python library that provides an Actor model framework for creating agent-integrated systems. It offers an easy-to-use API for connecting agents with traditional software systems, enabling flexible and scalable architectures. Agency aims to empower developers in creating custom agent-based applications by providing a foundation for experimentation and development. Key features include an intuitive API, performance and scalability through multiprocessing and AMQP support, observability and control with action and lifecycle callbacks, access policies, and detailed logging. The library also includes a demo application with multiple agent examples, OpenAI agent examples, HuggingFace transformers agent example, operating system access, Gradio UI, and Docker configuration for reference and development.

This repository contains self-trained single image super resolution (SISR) models. The models are trained on various datasets and use different network architectures. They can be used to upscale images by 2x, 4x, or 8x, and can handle various types of degradation, such as JPEG compression, noise, and blur. The models are provided as safetensors files, which can be loaded into a variety of deep learning frameworks, such as PyTorch and TensorFlow. The repository also includes a number of resources, such as examples, results, and a website where you can compare the outputs of different models.

Expert in self-assembling space architecture, focusing on TESSERAE.

Explore The City of the Future

Transforming spaces with advanced rendering techniques and aesthetic insights.

Optimizes workspace layout to enhance productivity and efficiency.

I'm an interior decorator using DALL-E 3 to visualize your space's potential.

Envision your living space in different shades and colors

Room Designer transforms your living spaces with a touch of digital magic. Simply upload your room's photo and specify your design dream, and watch as Room Designer reimagines your space with stunning creativity.

Help optimize floor plan, for better experience, please visit collov.ai

Guide to Tiny Living Spaces & Creative Solutions

I'll help you to make decisions that are imbued with Biophilia - the human tendency to be drawn towards life and life-like processes.

A friendly Fengshui guide for enhancing home energy.

A friendly guide for plant selection and care, with visual aids.

Informative guide on tiny house design and minimalist living

Expert in modern, energy-efficient architectural design.

渲染出图：展馆博物馆风格预设

精通2008版CAD的城市规划师，专注于解决规划问题

Expert in space exploration, astronomy, and celestial events

Space-themed artist for scientific inspiration

Adaptive AI for space exploration and exoplanet settlement.

Technical satellite security expert trained on space focused cybersecurity frameworks, best practices and process.