Content & Design

The Universal Mirror is a unique public participatory artwork that explores collective emotion through anonymous reflections. Users are invited to answer a single question, "Do you feel happy right now?", and their responses contribute to a generative visual "mirror" that evolves in real-time. This project is designed to capture and visualize collective sentiment without tracking or collecting personal data, ensuring anonymity. It offers a novel way to observe and understand the emotional landscape of a global community, providing a dynamic and ever-changing artistic representation of shared human experience.

Apeture by Lexica is an advanced AI image generation platform designed to produce photorealistic images. Users can easily customize image generation settings, including specific dimensions, to achieve desired outputs. The platform features an intuitive interface with dedicated sections for managing creative projects, viewing generation history, and saving preferences. It supports a wide array of photography styles and art themes, making it versatile for various creative needs. Additionally, Lexica offers an API for programmatic image search and reverse image search, providing developers with access to its extensive image database and generation capabilities.

VideoSnapshot is an AI-powered tool designed to significantly improve video engagement by generating compelling thumbnails. Users upload their video files to the platform, where advanced AI algorithms analyze the content to identify and select the most captivating frame. This intelligent selection process ensures that the thumbnail effectively represents the video's essence and entices viewers to click. Content creators can leverage VideoSnapshot to enhance their video presence across various platforms, ultimately boosting audience engagement and video performance. The optimized thumbnail can then be easily downloaded for immediate use, streamlining the content creation workflow.

Hotshot-XL is a state-of-the-art AI text-to-GIF model designed to integrate seamlessly with Stable Diffusion XL. This open-source tool enables users to generate animated GIFs from text prompts, leveraging the power of existing or newly fine-tuned SDXL models. A key differentiator is its compatibility with personalized LORAs, meaning users can create GIFs of custom subjects without needing to fine-tune Hotshot-XL itself. It also supports SDXL ControlNet for precise composition and layout control. Hotshot-XL is trained to produce 1-second GIFs at 8 FPS and supports various aspect ratios, with recommendations for optimal results using SDXL models fine-tuned with 512x512 images. Users can run Hotshot-XL locally for greater flexibility, including changing samplers, and it offers experimental features for varying frame rates and video lengths.

Segment Anything 2 Video Tracking is an AI tool designed to segment and track objects within video content. Users can upload a video and interactively define objects using points or bounding boxes. The application then leverages the SAM2 model to automatically track these selected objects across subsequent frames, generating a segmented video output. This capability is highly useful for various applications, including detailed video analysis, content creation requiring object isolation, and potentially for AI research focusing on object recognition and tracking in dynamic environments. The tool simplifies the complex task of object tracking, making it accessible for users to create precise video segments.

Audo Studio provides one-click audio cleaning for content creators, specifically YouTubers and podcasters. It leverages advanced AI to automatically remove background noise, reduce room echoes (coming soon), and adjust volume levels, significantly enhancing speech quality. The tool is browser-based, making it accessible on any operating system without the need for downloads. Audo Studio boasts impressive statistics, having cleaned over 300,000 hours of audio for more than 25,000 users, and claims to be 10 times faster than traditional software like Adobe or Audacity. It offers a free starter plan with limited usage, making it easy for users to experience its benefits before committing to a paid plan.

LynString is an AI-powered localization tool specifically designed for Android developers, simplifying the translation of `strings.xml` files. It intelligently scans your project's `/res` folder to detect missing translations across all `values-xx` folders and fills them in with one click using AI. Powered by Google Gemini, LynString ensures high accuracy by preserving Android-specific placeholders like `%1$s` and `%2$d`, and correctly escaping special characters. It also detects modified strings for re-translation, ensuring consistency. This tool is invaluable for mobile app developers looking to efficiently expand their app's reach to global audiences, saving significant time and effort in the localization process while maintaining translation quality and consistency across over 100 languages, including RTL languages.

Arabic Tokenizer Arena is a specialized platform designed for in-depth analysis of Arabic text tokenization. Users can input their own Arabic text or select from pre-made samples, then choose one or more tokenizers to observe how they split the text. The tool offers comprehensive metrics such as token count, fertility, and Out-Of-Vocabulary (OOV) rate, providing valuable insights into the tokenization process. Additionally, it generates visual representations to help users understand the tokenization results more intuitively. This tool is particularly useful for researchers, developers, and linguists working with Arabic language processing, offering a robust environment for comparing and evaluating different tokenization strategies.

Talking Face Longer-SONIC is an AI-powered tool designed to transform static images into dynamic talking head videos. Users can upload a still image and an accompanying audio file, and the tool will animate the image to synchronize with the audio, bringing it to life. A key feature is the ability to adjust the animation intensity, giving users control over the degree of movement in the generated video. This tool is ideal for creating engaging video content for various purposes, such as social media, educational materials, or entertainment, by simply combining a visual and an audio input.

SFX Sound magic is an innovative AI tool hosted on Hugging Face Spaces, designed to generate audio from either video or text prompts. Users can input a video along with text prompts to create audio that perfectly matches the visual content, or simply use text prompts to generate desired sound effects. This application is ideal for content creators, video editors, and anyone looking to enhance their projects with custom soundscapes. The tool also features sound search capabilities, allowing users to find and utilize existing audio. While currently paused, its functionality promises a versatile solution for audio generation and integration.

PaperPilot AI is a mobile application designed to assist students and teachers in quickly generating high-quality, CBSE-style question papers. Users can easily create customized practice tests by selecting class, subject, marks, and paper patterns. This AI-powered tool streamlines exam preparation and assessment creation, providing well-worded, exam-oriented questions instantly. It aims to simplify the process of creating assessments, making it an invaluable resource for educational professionals and students preparing for exams. The tool focuses on delivering relevant and structured questions tailored to specific academic requirements.

Towards-Realtime-MOT is an open-source project that implements the Joint Detection and Embedding (JDE) model for fast and high-performance multiple-object tracking. This tool learns object detection and appearance embedding tasks simultaneously within a shared neural network, enabling near real-time tracking speeds of 22-38 FPS, including the detection step. It offers training data, baseline models, and evaluation methods for algorithm development, along with a video demo for application usage. The repository provides pre-trained models with varying input resolutions and performance metrics, making it suitable for researchers and engineers looking to develop practical MOT systems or integrate robust tracking capabilities into their projects. The project is implemented in Python with PyTorch and includes resources for custom dataset training and deployment.

UltraFusion is an image enhancement application designed to elevate the visual quality of your photographs. Utilizing advanced HDR (High Dynamic Range) technology, the tool processes uploaded images to significantly improve color vibrancy and detail. This results in photos that appear more stunning and professional, with a richer visual depth. While the current live website indicates a runtime error, the intended functionality is to provide users with a straightforward way to enhance their images, making them more appealing and detailed.

Writepaw is an AI Writing Assistant designed to help business owners, marketers, and authors create high-quality content in seconds. It offers advanced AI capabilities to optimize writing and documentation, including AI prompt templates for generating unique ideas and enhancing creativity. Users can create compelling, SEO-optimized product descriptions, craft fresh social media posts, and design their own prompt templates for various needs like newsletters and marketing copy. Writepaw also provides pre-built templates and a free-style chat mode for natural AI conversations, aiming to save time and money on content creation.

GT is an AI-powered Chrome extension designed to facilitate multilingual communication by providing immersive interpretation delivery for online events. This tool seamlessly integrates with any browser-based meeting, event, or live stream, allowing users to access real-time interpretation in their preferred language. By enhancing communication and understanding across different linguistic backgrounds, GT helps break down language barriers in virtual environments. Its core feature is the immersive interpretation delivery, making it an essential tool for international online gatherings and live content where diverse audiences are present.

PlatePose is an AI-driven platform designed to generate professional food photographs for various business needs, including delivery listings, marketing campaigns, and social media. Users upload 10-20 source pictures of a dish from different angles and lighting conditions. PlatePose's human team reviews the submission, and then its AI generates over 50 unique food images, offering up to 8 different palette styles. This tool eliminates the need for expensive professional photoshohoots, providing a cost-effective and efficient way to produce a high volume of stylized food content. Users retain full ownership of all generated images, making it ideal for maintaining consistent and diverse visual branding.

SonicVerse is an AI-powered tool designed to analyze audio clips and provide detailed descriptions of the music. Users can upload any audio file to receive a comprehensive breakdown that includes the music's genre, overall mood, specific instrumentation used, vocal presence, and the musical key. This tool is ideal for anyone needing to quickly understand the characteristics of an audio track without manual analysis. It leverages AI to process and interpret complex audio data, making it accessible for various applications where detailed music metadata is beneficial.

EZAudioCut is a powerful mobile application designed for audio recording and editing on iPhone, iPad, and Apple Watch. It provides users with high-precision editing features, including cutting, merging, and applying various audio effects such as reverb, gain, pitch shifting, and time stretching. A standout feature is its advanced AI-powered noise reduction, utilizing neural network algorithms to clean up audio. The app supports multi-track mixing, with the multi-track version (EZAudioCut-MT) allowing up to 64 tracks, volume gain, and crossfades. It also includes vocal accompaniment extraction, making it ideal for musicians, podcasters, and content creators looking to produce high-quality audio directly from their mobile devices. Additionally, it supports external microphones and offers recording monitoring.

VizStudio is a free AI infographic generator that transforms blogs, prompts, and documents into professional infographics, cover images, and charts. Powered by Gemini 2.0 Flash AI, it can create 3-10 step infographics and over 12 chart types, including pie, bar, line, and funnel charts. The tool supports more than 50 languages, including RTL languages like Arabic and Hebrew, ensuring global accessibility. Users can convert blog posts to infographics instantly by pasting a URL or content, and generate charts from text or Excel data. VizStudio is designed for users without design skills, providing a quick and efficient way to create visually appealing content for various platforms.

Ultraswap AI, operating under the name Pykaso, is an all-in-one AI content creation suite specifically designed for influencers and creators. The platform's core functionality revolves around AI faceswap, enabling users to quickly and efficiently swap faces in both images and 4K videos. A standout feature is its ability to process 4K video faceswaps in less than 60 seconds, significantly streamlining content production. Additionally, it offers a bulk swap feature, allowing users to process multiple files simultaneously, saving considerable time. Pykaso aims to help users monetize their AI influencers by providing advanced tools for creating stunning AI content in seconds.

Script Reader AI offers an innovative solution for screenwriters seeking in-depth analysis and feedback on their scripts. The platform leverages AI to provide comprehensive coverage, including overall grades, scene-by-scene critiques, and actionable suggestions for improvement. Users can upload their scripts and receive detailed insights into elements like concept, plot, character development, and pacing. The tool highlights strengths and weaknesses, offering specific recommendations to enhance narrative impact, dialogue, and overall structure. This makes it an invaluable resource for both novice and experienced screenwriters looking to refine their work and elevate their storytelling quality, ensuring their scripts are compelling and well-structured.

The Alconost MQM Annotation Tool is a free, secure, and offline-capable solution for evaluating translation quality. It enables users to upload translation outputs, annotate errors according to MQM guidelines, and export structured annotations for detailed analysis. The tool supports granular error categorization, including Accuracy, Fluency, Terminology, and Style, with severities like Minor, Major, and Critical. It converts annotations into a Quality Score (%) by normalizing error penalties by translation length, ensuring consistent scoring across languages. The tool also offers reporting and analytics, including error distribution charts and session timing estimates, and supports API integration for automated import and export of data in formats like JSONL, TSV, and CSV.

ModernMT is a leading enterprise translation AI solution that dynamically adapts to user data and document context in real-time, delivering highly customized translation quality without extensive training or maintenance. It features a Human-in-the-Loop innovation where low-confidence translations are revised by humans to continuously improve the AI model. The platform supports 200 languages and offers document-level translation, considering the entire document's content for more accurate results. ModernMT provides a simple yet powerful API for enterprises and plugins for translators, integrating with CAT tools like RWS Trados Studio, Matecat, and MemoQ. It emphasizes data security with ISO 27001:2013 certification and guarantees data privacy, ensuring translations are not used to train baseline engines.

Eindhoven University of Technology (TU/e) is a leading research university dedicated to engineering science and technology. The Industrial Engineering & Innovation Sciences department focuses on effective and value-driven innovation, researching the responsible implementation of advanced technologies like AI and robotics. The program uniquely combines social sciences, humanities, and technical sciences to address complex challenges. Key research themes include the interaction between humans and technology, supply chain management, sustainability, and data-driven intelligence. TU/e offers bachelor's and master's programs, conducts extensive research, and fosters cooperation with industry, providing a comprehensive environment for academic and professional growth.