Content & Design

Spheroid AI Avatars is an innovative AI tool that enables users to create and customize interactive 3D AI avatars, which can then be placed anywhere in the real world using augmented reality technology. These avatars are designed to engage with users through voice chat, offering a dynamic and immersive experience. The platform supports various applications, including business, education, advertising, and entertainment. Users can select from a library of 3D models or upload their own, define the avatar's personality, and train it to communicate on specific topics. The avatars can be published and accessed via the XR Hub Augmented Reality App, allowing for real-world interaction. Spheroid AI Avatars also offers the Spheroid Warp tool for creating and managing AR/XR content, making it accessible even without technical knowledge.

Project Genie is an AI-powered world generation platform built on Google's Genie 3 model, Gemini, and Nano Banana Pro. It enables users to transform simple text descriptions and optional reference images into photorealistic, interactive 3D environments. The platform generates navigable worlds in real-time at 20-24 frames per second with 720p quality, consistent physics, and stable geometry. Users can explore these environments with full camera control, remix existing creations, and download exploration videos. Designed for accessibility, Project Genie eliminates the need for 3D modeling or coding skills, making advanced AI world simulation available to a wide range of creators for game prototyping, educational simulations, film previsualization, and more.

AeonChat is a 3D AI companion app designed for immersive interaction with AI girlfriends or boyfriends. It offers features like text chat, video calls, and dynamic 3D interactions with expressive animations and emotional intelligence. Users can engage in roleplay, create custom scenarios, and receive daily status updates including photos and videos from their AI companion. The AI companions possess infinite long-term memories, remembering user preferences and evolving their personality based on interactions. AeonChat also simulates a life for the AI, including emotions, hobbies, and careers, making the relationship feel more real and personal. The app is available on iOS and Android.

Map Builder AI is an advanced AI Developer Engine specifically designed for Roblox creators. It empowers developers to build dream Roblox maps faster by leveraging AI for various tasks, including generating clean and optimized Luau code, fixing bugs, and providing expert settings assistance for complex device menus. The tool also helps with level design brainstorming to create engaging mechanics. It operates on a transparent, credit-based system, eliminating subscriptions and allowing users to pay only for what they need, from quick fixes to full World Engineering. This platform is ideal for both solo developers and teams looking to accelerate their Roblox development workflow.

Seedance 2.0 Pro AI Video Generator, powered by Seedance 2.0 technology, allows creators to generate cinematic videos online with realistic motion, synchronized audio, and extensive creative control. Designed for usability, realism, and control, it excels in complex scenes with multiple characters, fast movement, and detailed interactions. The tool supports multi-modal input, combining text, images, video clips, and audio to guide video creation. It offers director-level control, enabling accurate instruction following, consistency across scenes, and controlled video extension and editing. Built for industrial-grade production, Seedio supports up to 15-second multi-scene videos with synchronized stereo audio, making it suitable for advertising, film concepts, e-commerce, and gaming.

Curio Interactive Inc. is dedicated to amplifying global creativity through interactive hardware experiences, specifically focusing on AI-powered plush toys. These AI Toys are designed to educate, enlighten, and entertain users. The current product line includes characters like Gabbo, Grem, Poppy, Lingo, Ballerina Cappuccina, Springer, The Visitor, and Professor Linus, all available for purchase. Curio emphasizes interactive experiences and plans to introduce more characters in the future. The company also provides information on its story, FAQs, contact details, privacy policy, and terms & conditions, ensuring transparency and user support.

RealLife3D specializes in converting standard 2D images and videos into immersive 3D content. Utilizing AI technology, the service streamlines the conversion process, enabling quick and cost-effective processing of numerous frames. This approach makes 3D conversion accessible beyond large-budget feature films. RealLife3D supports various 3D and VR platforms, including YouTube VR, and offers outputs such as side-by-side, VR180, and anaglyph formats. The tool is designed for content creators and immersive experience developers who want to add an extra dimension to their visual storytelling, whether for travel, journalistic, or historic content.

Stable Fast 3D (SF3D) is Stability AI's innovative solution for rapid 3D asset generation, transforming single images into detailed 3D models in an unprecedented 0.5 seconds. This technology significantly enhances workflows for professionals needing quick and high-quality 3D assets. It delivers UV unwrapped meshes and accurate material parameters, reducing illumination bake-in for better textures. Built on an improved TripoSR architecture, SF3D is suitable for gaming, VR, e-commerce, and architectural visualization. The tool offers a robust API for enterprise integration and operates on a credit-based system for generations, with a community license allowing commercial use for organizations under $1M annual revenue.

Mediate is a research and innovation lab focused on the intersection of Computer Vision and Augmented Reality. They empower people in both digital and physical spaces by crafting mobile and intelligent ecosystems that enhance productivity and joy. Their expert team, with backgrounds from institutions like MIT and Harvard, develops cutting-edge novel neural networks in collaboration with MIT to robustly parse 3D spaces. This technology is optimized to work in real-time and locally on edge devices privately. Mediate provides cross-platform services, API, and cloud integrations, offering solutions for various applications, including a visionOS app for thinking and learning, a market-leading mobile scanner for visually impaired users, and indoor navigation systems for museums.

LTX-2-LoRAs-Camera-Control-Dolly is an AI tool hosted on Hugging Face Spaces that empowers users to create dynamic video sequences with precise camera control. Users can provide an optional image and a text prompt to describe the desired motion, then select from various camera-movement LoRAs (Low-Rank Adaptation) such as 'dolly left' or 'jib up' to dictate the shot's trajectory. The tool also offers customization for video length and resolution, making it versatile for different creative needs. It's designed for experimenting with camera control in AI art and producing unique visual effects, offering an accessible way to integrate sophisticated camera movements into generated content.

QIE-Image2GuideBody is an AI-powered tool designed to assist artists and designers by converting anime-style character images into detailed body structure diagrams. It provides clear skeletal and muscle outlines, which are invaluable for understanding character anatomy, refining poses, and developing new designs. Users simply upload an anime character image and click generate to receive a guide body output. This tool is particularly useful for artists working on character design, illustration, and animation, offering a foundational visual reference to ensure anatomical accuracy and consistency in their work.

Rocco Architecture Render is an AI-powered tool hosted on Hugging Face that transforms user sketches into detailed architectural visualizations. It allows users to upload a basic sketch and then use text prompts to generate sophisticated interior or exterior designs. The tool offers flexibility by letting users choose the degree of AI intervention in the design process. Additionally, users can specify various design styles and types to achieve highly customized and specific results, making it a versatile solution for architectural rendering needs. This tool is accessible via a web interface.

Stable Diffusion Sprite Sheets is an AI-powered tool hosted on Hugging Face Spaces, designed to generate sprite sheets for various applications. This tool leverages Stable Diffusion technology to create multiple frames, which are essential for animations or game assets. While the specific functionalities and user interface details are not fully accessible due to a runtime error on the live page, the core purpose is to assist users in generating character and animation assets with AI. It aims to streamline the creation process for game developers and animators by providing AI assistance in generating visual content.

SKYLLER Solutions, a subsidiary of PTTEP, offers cutting-edge drone inspection and AI-powered asset management solutions. The platform enhances data capturing, analytics, and visualization to help businesses optimize their asset management, improve decision-making, and boost operational efficiency. Key offerings include inspection services for infrastructure, a data visualization and management platform with AI-assisted defect detection, and gas emission monitoring using drones and advanced sensors. SKYLLER also provides logistic drone services and focuses on sustainable asset management, with a vision to be a trusted partner in providing data intelligence and actionable insights. They have extensive experience with over 5,000 flights and 10,900 km covered, maintaining a zero-incident record.

Shugar AI is a platform designed for interacting with and creating AI characters. Users can explore a variety of AI-generated personalities, engage in conversations with them, and even generate their own unique AI characters. The platform offers tools that facilitate the creation and engagement process, catering to various applications where AI personalities can be utilized. It aims to provide an intuitive environment for users to bring their AI character concepts to life and interact with them in meaningful ways, making it suitable for creative projects, entertainment, or experimental applications involving artificial intelligence.

Dobby Canvas is at the forefront of AI-powered game development, offering tools designed to build the future of gaming. The platform aims to simplify and innovate the game creation process by integrating artificial intelligence. While specific features are not detailed, the overarching goal is to provide developers with advanced capabilities to create innovative game experiences. This tool is positioned for those looking to leverage AI to enhance their game development workflow and push the boundaries of traditional game design.

Digen AI is a free AI video generator designed to instantly create professional videos from images. It leverages advanced AI to provide features like realistic voice synchronization, multilingual support, and smart motion technology, eliminating the need for technical video editing skills. Users can convert static images into dynamic visual stories, making it ideal for content creators, marketers, and anyone looking to produce engaging video content quickly. The platform also includes AI tools such as video upscalers, watermark removers, FPS boosters, and various video and image models like Sora 2 and Veo 3.1, enhancing the overall video production process.

AiHouse is an all-in-one AI-powered platform designed for 3D interior design and manufacturing. It empowers businesses by streamlining design, production, and sales processes. Users can easily bring their ideas to life by creating 2D/3D floor plans and constructing rooms, even with irregular shapes. The platform offers access to over 80 million 3D models and AI templates, allowing for easy customization to client needs with process automation. AiHouse leverages AI to redesign rooms, optimize views and lighting, and render 4K images in less than 3 minutes. It also integrates with JEGA Cloud Factory for design-manufacturing integration, automating order management, cutlists, and engineering drawings from a single data source. This comprehensive solution helps interior designers, furniture brands, and manufacturers create stunning 3D spaces, boost sales, and improve workflow efficiency.

InterWiz AI is an advanced AI interviewer designed to revolutionize the hiring process by offering fast, structured, and consistent candidate screening. It leverages AI-led phone and video interviews to replace hours of manual evaluation, freeing recruiters to focus on qualified candidates. The platform features a library of over 120 expertly crafted question sets covering various skills and industries, ensuring standardized and high-quality screening. InterWiz also provides instant resume shortlisting by applying role-specific evaluation criteria to ATS resumes, significantly reducing review time. Candidates benefit from simplified scheduling, allowing them to choose interview times that suit them. The tool delivers detailed scoring and actionable insights, boosting confidence in hiring decisions and reducing time to hire by up to 60%.

LiveAvatar is an open-source implementation of the research paper "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length." This algorithm-system co-designed framework allows for real-time, streaming, and interactive avatar video generation of infinite length. Powered by a 14B-parameter diffusion model, it achieves 45 FPS on multi-card H800 GPUs with 4-step sampling and supports Block-wise Autoregressive processing for videos exceeding 10,000 seconds. Key highlights include real-time streaming interaction with low latency, infinite-length autoregressive generation, and strong generalization across cartoon characters, singing, and diverse scenarios. The project provides code for both multi-GPU and single-GPU inference, including a Gradio Web UI, and supports FP8 quantization for 48GB GPUs.

Difix3D is an open-source project designed to enhance 3D reconstructions by leveraging single-step diffusion models. It offers a comprehensive framework for improving the quality of 3D data, specifically targeting artifact removal and the refinement of novel views. The tool provides both Difix for single-step diffusion artifact removal and Difix3D for progressive 3D updates, including integration with popular 3D reconstruction frameworks like Nerfstudio and gsplat. Additionally, Difix3D+ introduces real-time post-rendering capabilities to further sharpen details and improve visual fidelity. This makes it a valuable resource for researchers and developers working on advanced 3D computer vision tasks, offering practical implementations and models for immediate use.

CAD Viewer for Google Drive™ provides a free online solution for viewing DXF and DWG files directly from your Google Drive. This web-based tool eliminates the need for software installations, making it accessible from any browser. Users can connect their Google Drive account to seamlessly open and review CAD files. The platform is designed for ease of use, offering a straightforward way to access and inspect technical drawings. It supports essential CAD file formats, ensuring compatibility for common design and engineering needs. This tool is ideal for individuals or teams who require quick and convenient access to CAD files stored in Google Drive.

Point-BERT is a PyTorch implementation of a novel pre-training paradigm for 3D point cloud Transformers, introduced in CVPR 2022. Inspired by BERT, it utilizes a Masked Point Modeling (MPM) task where point clouds are divided into local patches, and a discrete Variational AutoEncoder (dVAE) tokenizes these patches. The pre-training objective involves recovering original point tokens at masked locations, supervised by the dVAE's output. This method significantly advances the capabilities of Transformers for 3D data, facilitating tasks like classification on ModelNet40 and ScanObjectNN, few-shot learning, and part segmentation on ShapeNetPart. It is an essential tool for researchers and engineers working with 3D point cloud analysis.

MeshCNN is a general-purpose deep neural network specifically designed for 3D triangular meshes, implemented using PyTorch. This framework enables advanced tasks such as 3D shape classification and segmentation by applying convolutional, pooling, and unpooling layers directly on the mesh edges. It offers a robust solution for researchers and developers working with 3D data, providing a novel approach to process geometric information. The repository includes scripts for installation, training, and testing on datasets like SHREC and Humans, making it accessible for practical application and further development in the field of geometric deep learning.