Stable Diffusion 2.0 AI Hackathon Summary

Have you ever felt like you couldn't retain all the information from a talk, class, or event? Or maybe you feel stuck on a problem and need new perspectives to find innovative solutions? Introducing "Rubber Duck," your intelligent virtual assistant based on the concept of "rubber ducking"! The term "rubber ducking" comes from the practice in which programmers explain their problems to a rubber duck in order to clarify their thoughts and find solutions. Rubber Duck uses the power of GPT and Whisper to listen and transcribe your conversations, classes, or events, summarize the most important points, and the power of Stable diffusion to turn those abstract concepts into mnemonic support images and ask Socratic questions to help you learn and find innovative solutions. With Rubber Duck, you'll never have to worry about taking notes or missing important details again. Let Rubber Duck be your study and problem-solving companion, and see how it helps you reach new heights in your learning and creativity!

RubberDuck

We are developing a project that aims to help writers to mix written content by generating engaging images and optimizing placement within the text. Basically, We are building a web application that generates images based on user input. The user will enter some text and might specify the number of images they want to generate. Our application will analyze the text, identify entities within it, devide text into paragraphs and use that information to generate images using a generative AI model. The user will have the option to modify the generated images and generate new ones. The idea is that Ai will analyses the text and decides the best place to put images (where the reader becomes bored) and generate images according to the content. We included more detailed information in our presentation

GEMBA

Spark is a storytelling AI bot that generates personalized stories based on user choices. With Spark, users can pick their hero, action place, and category, and the bot generates a unique story in the backend using ChatGPT, in addition, Spark uses stable diffusion for image generation to create visually appealing content that enhances the storytelling experience. The backend of the bot is built using Python FastAPI, ensuring fast and efficient story generation. The frontend of the website is developed using React NextJS, providing a smooth and intuitive user interface. The project uses MongoDB for database management. Overall, Spark is an storytelling website that combines advanced AI technology with engaging visual content to create a truly immersive and unforgettable storytelling experience.

Code Vision

Our AI-powered app transforms your pet’s photo into a creative portrait in minutes! With a wide range of painted effects to select from, you can turn any photo of your beloved pet into a gallery-worthy masterpiece. Whether you want to turn your pet into a Van Gogh-style masterpiece or a medieval portrait, our app has got you covered. You can even transform your pet’s photo into a bespoke piece of wall art that will look great in any room of your home. Our app uses state-of-the-art artificial intelligence to create stunning portraits of your pet that capture their unique personality and spirit. Try it now and see how easy it is to create an artistic portrait of your cat or dog that you’ll cherish for years to come!

TAQADUM

InstaMerch is a platform that brings custom merchandise creation to new heights. By utilizing state-of-the-art technology, including the Stability API and Printful API, we offer users an intuitive and user-friendly interface to design and order unique, personalized products. From small businesses and artists to individuals seeking one-of-a-kind gifts, InstaMerch caters to a wide range of needs. As we continue to grow and evolve, we're committed to expanding our product offerings, enhancing user experience with personalized recommendations, and exploring strategic partnerships to reach an even broader audience. Experience the unparalleled ease and endless creative possibilities that InstaMerch has to offer, and join us on this exciting journey toward revolutionizing custom merchandise creation.

Visionary Virtuosos

The app is to create images that can further be used to make a story line consisting of individual images(read scenes). This app can also Enhance an existing image(like drawing or sketches) using text prompts. The App also suggests prompt, if the user explains how the picture should look like or what is the scene about in a particular story line. That Prompt can be further used to generate images and at last the user can gather all the images and publish as an album. The target audience of this application is anybody who's interested in arts. Entertainment industry can be one domain but it's use cases are not limited to that space only.

Zion

Nimbus Adventure is an innovative online educational application created specifically for children. This cutting-edge platform combines advanced technologies such as SDXL and OpenAI's GPT-3 model to generate personalized and captivating children's stories. By merging artificial intelligence and user-provided information, the application creates narratives tailored to each child. The primary goal of Nimbus Adventure is to promote positive values, motivation, and education through engaging and interactive reading experiences. The application generates texts using the GPT-3 model and creates images with Stable Diffusion SDXL, ensuring that each story is visually appealing and coherent. Among the advantages of this revolutionary application are personalized content, promotion of positive values, artificial intelligence integration, fostering creativity and imagination, and accessibility across various devices. Additionally, it offers constant updates and evolving content, a secure and private environment, and the opportunity for parents to be involved in their children's educational process. Nimbus Adventure is a unique educational tool that utilizes artificial intelligence to provide stimulating and personalized stories, encouraging education and personal growth for children in an entertaining and accessible way. With its commitment to ongoing research and development, Nimbus Adventure positions itself as an invaluable resource in children's education.

Nimbus

Get ready for the future of car design with AI-powered 3D modeling! Our cutting-edge technology utilizes machine learning to create highly detailed and realistic 3D models of cars with futuristic designs. By analyzing various data sources such as photos, sketches, and existing 3D models, our technology generates stunning representations of cars that can be used from video games to metaverse projects. And who knows? One day, we might even see personalized cars created with 3D printing technology, all thanks to the power of AI and machine learning. Get a glimpse into the future of car design with our small prototype

NuDrive

Are you curious about life, God, Jesus Christ and more? Do you have any questions about the Holy Bible? Then ask your questions as written text prompts. The living bread is a chatbot app powered by Stability Diffusion AI API designed to provide answers to your prompts using the Holy Bible. Whether it is the story of Moses and Pharoah, or the birth of Jesus Christ, or the parable of the lost sheep, or knowing how to deal with anxiety, stress, then discover the answers through the scripture and accompanying striking visual images. In the future we want to express the stories through multiple images for a single prompt.

gogetter

Touch interfaces are amazing for fast prototyping, but the endgame of any interface is to become so refined and simple that it serves it's purpose embodied in a physical object. Musicians and audio engineers know this well and have a whole industry dedicated to create amazing and useful physical interfaces. Our hands provide immediate and unbeatable feedback when it pushes a knob or fader. Response is instant. Corrections are seamless. No ghost touch, no blocking information on the screen, not weird finger movements and gestures. Artists NEED control. Mouse and keyboard interface is amazing in terms of control, but it lacks feedback. Let's spice it up with some good ol' tangible control surfaces.

Laia

Our idea for the hackathon is to create an AI-driven virtual fitting room that allows users to try on new clothes or outfits by providing an image of themselves. The application will utilize advanced image generation models and impainting to generate realistic images of the user wearing the desired clothes, enabling them to explore different styles and make more informed purchasing decisions. By employing Stable Diffusion, our virtual fitting room will be capable of synthesizing intricate clothing textures and maintaining the natural appearance of the user's body contours, thus providing an immersive and personalized shopping experience. Moreover, the application will be adept at handling various clothing types, including formal wear, casual attire, and seasonal outfits, allowing users to explore a diverse array of styles effortlessly.

AIsthetic Innovations

KlassNaut is a cutting-edge AI-powered note generator designed to streamline the note-taking process for teachers. With its easy-to-use interface, teachers can generate notes with text input or audio input, depending on their preferences. Once the input is received, the app sends the request to a Flask server that distributes the task to Celery workers via Redis. The workers utilize GPT3.5, Whisper (when audio is involved), and Stability AI to generate meticulously formatted notes, complete with corresponding images. The generated notes are then saved to PostgreSQL, allowing teachers to easily access them at any time. To ensure that teachers receive timely notifications, KlassNaut sends notifications via a socketio server once the note has been generated. Teachers can then view the note, edit it if needed, and download it in either PDF or Docx format for future reference. The KlassNaut ReactJS client is deployed to Vercel, while the server-side code is deployed on Digital Ocean, providing a seamless user experience. KlassNaut represents the future of note-taking, simplifying and enhancing the teaching and learning experience.

iT Central

GOWONU is a cutting-edge, horror-driven gaming experience that immerses players in a haunted, cursed apartment complex using advanced AI technology. With Stable Diffusion-powered, real-time 360-degree environments inspired by the notorious Kowloon, players navigate an ever-evolving labyrinth teeming with supernatural occurrences, eerie noises, and ghostly apparitions. As urban explorers, players must communicate with others inside GOWONU to create new paths and uncover the mysteries of the complex. At the heart of the game lies the player's ability to influence the world around them through the use of keywords and modifiers. This innovative mechanic ensures a unique, unpredictable experience each time, providing endless replayability. The game seamlessly incorporates Stable Diffusion, ControlNet, and Blockade technologies, delivering a captivating experience complete with music, SFX, VFX, and interactive prompts. GOWONU's rich, evolving backstory and dynamic elements such as doors, holes, and stairs create an immersive and ever-changing environment. Players are invited to explore, collect, and communicate within a spine-chilling, supernatural world that tests their courage and ingenuity. With its unique blend of horror, AI, and interactive gameplay, GOWONU offers a thrilling, unforgettable adventure that constantly adapts to challenge and enthrall its players.

GOWONU

We use AI to facilitate industrial design and modeling images. You can - generate designs based on descriptions and existing collections. - try new designs in real-world pictures. For example, you can use the model to - generate streamlined, leather material body e-cigarette design based on the <200 images collection> - try <helmet-design> on 6-month kids playing on grass. Overall Impression - Users can provide a collection of reference images - Users can use simple words to *generate* and *modify* images - The user’s product can be displayed in different scenarios We also provided demo with real users from industrial designer in e-cigarette who needs to demo to their customers with new designs. Helped kid's helment manufacture who needs to create non-real human images in order to pass regulations regarding advertisement privacy. They both benefites from our product by reducing image generation time, and increasing variaty.

Mindblink

The pet emotion detection app is an innovative platform that allows pet owners to gain insights into their pet's emotions through a trained ML model. The app allows users to upload an image of their pet, and the model analyzes the image to provide feedback on the pet's emotions. Based on the feedback provided by the model, the app generates an image that can be downloaded or shared on social media. In addition to providing feedback on pet emotions, the app also allows users to create a profile for their pet, maintain a gallery of pet images, and keep track of their pet's emotional state through a calendar feature. The app provides a fun and interactive way for pet owners to connect with their pets on a deeper level and gain a better understanding of their emotional state. While the initial version of the app only supports image detection, the team is planning to expand the functionality of the app in the future to include video detection as well. This will provide an even more comprehensive analysis of the pet's emotions and behavior, allowing users to gain a deeper understanding of their pets and strengthen their bond with them.

Beta Tech

"Try Anything" is a unique and innovative service that offers you the freedom to try anything you desire, using state-of-the-art AI technology. Whether you want to experiment with new hairstyles, try on different clothes, or select new furniture for your home, we have you covered. Our easy-to-use platform allows you to upload your photos and see instant predictions for the changes you want to make. With just a few clicks, you can transform your appearance, home decor, or even your pets. Try Anything is the perfect solution for anyone looking to explore new possibilities and unleash their creativity.

TAM

Problem: • We know that we are spoiling the Environment by destroying trees and natural resources which makes it more difficult for future generations. • Who said technology rotten us, if properly used, we can make use of it in a better way. That is what we are doing with Stability.ai, by educating users about our Environment. Solution: • Gloob-Earth teaches us the importance of Forestation and sustainability with the use of Science, Satellites and Gen AI technologies. • It educates the use of forestation and deforestations that happened in the past and it gives us the insights of deforestation happened in any part of the globe. • Users can click on several points of interest to see deforestation over time, along with satellite imagery processed by computer vision models that shows the exact tree cover loss percentage. • Users can talk with our AI buddy Glooby powered by GPT to learn more about the country and its environmental issues and discuss climate change solutions. • Users can also generate an artistic rendition powered by Stability.ai Stable Diffusion 2.0 on this subject to see potential future outcomes should we continue down this path, or choose sustainability. • Finally, the user is given the opportunity to receive sustainable product and company recommendations originating in the country they searched, through phone messaging powered by Twilio. Tech Stack: • Front End: React, Tailwindcss, Material UI, Twilio. • AI Apps: Stability.ai Stable Diffusion 2.0, GPT 3.5 Turbo • Satellite Image: ArcGIS, Google Earth Engine. • Hosting: Vercel Lets join hands to save environment with Enlightening with Gloob-Earth !!

Wizards

AI has transformed the art world with its potential for innovation and self-expression. One of the most exciting innovations in this space is the emergence of AI art generator apps. However, these apps often require text prompts, presenting a barrier for some users. One of the major challenges that users face with AI art generator apps that require text input is the issue of accessibility. Not everyone is able to type, either due to physical disabilities or other reasons. This can make it difficult or even impossible for some users to access the full range of creative possibilities offered by these apps. Karma AI aims to address this problem by providing a more user-friendly and accessible interface. By eliminating the need for text input and replacing it with a few simple clicks, Karma AI makes it possible for anyone to create beautiful, unique artwork using AI technology. This is particularly important for individuals who may face barriers to traditional forms of artistic expression, such as those with physical disabilities or other challenges. Another challenge that users face with text-based AI art generator apps is the difficulty of generating high-quality prompts. Even for individuals who are able to type, coming up with a creative and inspiring prompt can be a daunting task. With Karma AI, users can take advantage of the power of GPT, which is trained to generate high-quality prompts that are tailored to the user's preferences and interests. Overall, Karma AI represents a significant step forward in the development of AI art generator apps that are both accessible and user-friendly. By harnessing the power of cutting-edge AI technology and eliminating the need for text input, it offers a powerful tool for artists and creative individuals everywhere.

Karma AI

Our team has created an exciting prototype that utilizes cutting-edge technologies to help you explore and visualize your dreams in a whole new way. By leveraging the power of natural language processing (NLP) and Stability.ai, we've developed a system that can interpret the content of your dreams and generate stunning visual representations of them in a small booklet. Imagine being able to revisit your dreams in vivid detail, capturing the sights, sounds, and emotions that you experienced while you slept. With our prototype, you'll be able to do just that. By using NLP to analyze the content of your dreams, we can identify key themes and symbols, and then use Stability.ai to create stunning, personalized visualizations that bring your dreams to life. Whether you're looking to gain a deeper understanding of your subconscious mind or simply want to explore the fantastical worlds that your dreams create, our prototype is the perfect tool to help you do so. So why wait? Try it out for yourself and discover the endless possibilities of dream exploration.

SteamDreamTeam

The Articulator tool is an interactive interface designed to enhance art generation by combining it with art curation. Using high-quality image generation from Stable Diffusion and including a multimodal large language model allows for users to reflect on the results and instantly receive human-like critiques and descriptions. The system can assess artwork based on various criteria, including color, composition, texture, and subject matter, and generate a rating or score for various criteria. Articulator analysis can help identify generated results that are well composed, but also those that are "funny," "good for kids," "professional," or "on-brand." The human-like feedback can be an effective tool to avoid a creative block. Articulator and other multimodal tools will have an important role in future creative work whether for marketing or art therapy.

gstaff

Technoforge Automotive is a company that specializes in car design using the latest and most advanced technologies. It uses Stable Diffusion, GPT, and Segment Anything to create a powerful and efficient platform for designing cars. Stable Diffusion is an innovative and cutting-edge technology that allows designers to create high-quality and realistic images of cars using natural language inputs. It uses the open-source state-of-the-art text-to-image model to generate art using natural language. This technology is essential for creating realistic images of cars that can be used for various purposes, such as marketing and advertising, product design, and research and development. GPT is a natural language processing technology that helps designers communicate their ideas. It interprets user inputs, making it easier for designers to express their ideas in natural language. GPT is critical in ensuring that the car design tool is user-friendly and intuitive, enabling designers to communicate their ideas quickly and easily. Segment Anything is another technology used by Technoforge Automotive, which is a new task, model, and dataset for image segmentation. It enables designers to segment any object in the image, allowing them to manipulate and modify the image as needed. By using Segment Anything, designers can make changes to the design quickly and easily, ensuring that the final product is optimized for performance and efficiency. By utilizing Stable Diffusion, GPT, and Segment Anything, Technoforge Automotive can help designers create innovative and unique car designs that are optimized for performance and efficiency. These technologies work together to create a powerful and efficient platform for designing cars, ensuring that designers have all the tools they need to bring their ideas to life.

team phoeniks

HistoVerse is a platform powered by multiple AIs to bring history to life in an entirely new way. Our cutting-edge technology allows users to ask questions and receive detailed answers generated by advanced AI systems such as chatGPT and stable_diffusion - and these answers are delivered engaging and informative. But HistoVerse is more than just a question-and-answer platform - it's also a social media hub where people from all over the world can share their stories and experiences, bringing local histories to the forefront. Share your own stories and learn from others as we work together to uncover the rich tapestry of human history

HistoVerse

The basic idea is that we scrape the site and use all that data to create a story about it, then once we get that we split that story insto smaller chunks that get drawing using stable diffussion text to image api. Once we get those we match them to the audio and send all that to clove backend to create a video out of it. The idea is to help understand complex subjects with visual and audio aids, this is still very exploratory and likely only useful for specific use cases. One of the downsides is that each video requires quite a bit of images so I have hit the max requests api limit, but I think I was able to find ways to minimize that.

Clove

YouTube Thumbnails is a cutting-edge YouTube thumbnail generator that uses SDXL and GPT powered text optimization to create stunning, high-converting thumbnails. Our target audience includes YouTube content creators, digital marketing agencies, and social media managers. By addressing users' pain points of time-consuming thumbnail creation and design limitations, YouTube Thumbnails offers a seamless and cost-effective solution that saves time, enhances visual appeal, and increases engagement. With the continuous growth of YouTube as a platform, content creators face fierce competition for viewers' attention. A compelling thumbnail is crucial for attracting users and driving engagement, as it serves as the first visual impression of a video. By leveraging AI and machine learning technologies, YouTube Thumbnails aims to revolutionize the way creators approach thumbnail design.

YouTube Thumbnails

Product photography helps you create awesome images of your products to use in ads, marketing and catalogs. But it's a very time consuming and expensive task. What if you could create stunning product photos in just minutes, without the need for expensive equipment or a professional photographer? Lenskit can do that, from background removal to image enhancement, using AI to ensure that your product images are of the highest quality. Whether you're a small business owner or a large corporation, lenskit tool can help you save time and money while producing professional-grade images that will help you stand out in today's competitive market.

Morse

The audio-to-image conversion project is an innovative system that utilizes pre-trained models to classify audio input and generate images based on the classification. The system has three stages: classification, prompt generation, and image creation. In the classification stage, the system uses pre-trained models to classify audio input into different categories. The system then generates a prompt based on the classification, which is a text description of the image that the system will generate. Finally, the system sends the prompt to an AI API that uses GANs to create the image. The audio-to-image conversion system has potential use cases in various industries, including art, design, security, healthcare, education, music production, marketing, automotive, construction, and virtual reality. The system has the potential to revolutionize these industries by enabling unique and innovative approaches to problem-solving and creative expression.

TechTitans

To develop a website you need UI and graphic skill and also inspiration. Most Developers from backend to frontend don't have those skills and rely heavily on graphic designers. It's nearly impossible to develop a web site if you don't have a friend or money to hire a freelancer or an agency More over if you don't have a clear idea, It can cost quite a lot. Codesign X is a tool that integrate VS Code and Stable Diffusion (and other AI technologies later) to help developers be creative and productive from day one ! It will assist you naturally through your IDE to generate medias and code and integrate them directly in your code. Codesign X is not just an IDE extension but also a SAAS solution. The plateform will store your medias and share them, allowing collaboration with other developers or content creators. For now, Codesign include the features : - Image and code generation with aI - Images Saving - Url Shortener - Basic search engine Codesign X will provide multiple services later such as analytics and AI and will generate revenue through subscriptions plans

Uncharted

Infinify is an AI automation tool startup that aims to democratize access to AI solutions for businesses and individuals, regardless of their technical expertise or resources. The growing use of AI in various industries has made it a valuable tool for automating tasks, streamlining workflows, and gaining insights from data. However, building custom AI solutions from scratch can be time-consuming, expensive, and require a high level of technical knowledge, making it inaccessible for many potential users. The platform is cloud-based, providing scalability and easy access to users across different devices and locations. This means that users can access their workflows and data from anywhere, without needing to worry about infrastructure or hardware requirements. Infinify's platform is also designed to be secure, ensuring that user data is protected and compliant with regulations.

Infinify

Spacely AI is a game-changing interior design platform that caters to the needs of those struggling with finding the perfect furniture set to match their space. The platform enables users to upload an image of their furniture, which the AI then uses to create a room based on the furniture's style, size, and budget. This process eliminates the need for users to scour different furniture brands, which can be an arduous and frustrating task. Spacely AI allows users to mix and match different furniture brands seamlessly, ensuring that they get the best fit for their space. The AI generates complementary furniture items such as sofas, beds, and table lamps, which are tailored to the furniture's style. This feature helps users stay within their budget and eliminates the pain of trying to find items that match their style. The platform's user interface is simple and intuitive, making it easy for users to navigate and use the tools. The AI technology used by Spacely AI accurately understands the furniture's size, style, and budget. This feature ensures that users get the best possible outcome for their space. Spacely AI's mission is to provide an easy and seamless experience for enthusiasts who are struggling with finding the perfect furniture set. The platform helps users create their dream space without the hassle of going through different furniture brands.

Spacely AI

Link: https://wa.me/message/A4XZOJ7CMTTUK1 Buggy is a WhatsApp chatbot that provides users with an interactive and engaging experience. Users can chat with ChatGPT AI to get answers to their questions, generate random images, and check their network speed by simply entering the corresponding numbers as options. It's designed to be user-friendly, with a simple menu interface that makes it easy for users to navigate and get the information they need. The name Buggy was inspired by the One Piece character "Senryo Doke no Buggy," which means "Buggy, the genius clown." The chatbot is constantly improving, with new features being added regularly to make the user experience even better. Buggy is a great tool for users who want to interact with AI in a fun and easy way while getting valuable information.

JavaScript Shinobi

Prompt Chef offers an easy to use, robust platform for developing and sharing AI apps. No specialized knowledge required. New to using AI? Don't know what AI even stands for? Perfect! Use pre-made recipes build specifically for your needs. For example, use the Interior Design recipe to instantly create concept drawings for your kitchen renovation. Or use the Invitation Recipe to help with writing unlimited personalized invitations. It's like filling out a form. Know how to prompt? Want to make your own recipe? Have a prompt you want to share or just save for later? Use the editor to create your own recipes. Drag and drop inputs to make your recipe and specialized or as broad as you want. Use the configurator to specify the model used - like GPT-4 for text outputs, or Stable Diffusion XL for image outputs. Prompt Chef is free to use too. All the editor and sharing features are available for free without limits. If you like, you can simply run recipes right from the app. Running prompts will cost tokens, which can be purchased from the app. Prompt Chef supports the latest and most powerful AI models, so you don't need to use multiple tools for one job. The use cases for Prompt Chef is unlimited, and empowers everyone to start using the power of AI in their everyday life.

Oxen

Stable Diffusion is the ultimate website for creating personalized t-shirts that showcase your unique style. With our user-friendly platform, you can effortlessly design a t-shirt that perfectly reflects your individuality. Our website offers AI-generated images based on your input to generate a unique design, and our intuitive editing tools make it easy to add your own text. Simply enter your desired text to create a custom t-shirt design. Our high-quality printing process ensures that your design looks great and lasts long. With our fast and reliable shipping, you can receive your t-shirt in no time. At Stable Diffusion, we're dedicated to ensuring customer satisfaction. Our website is easy to use, and our friendly customer support team is always available to help. Start creating your personalized t-shirt today on Stable Diffusion!

T-Shirts AI - simple project

Stori helps video game developers rapidly iterate and plan their worlds before going in an building them. Building lore consistent worlds is the one of the hardest part of building a video game and we aim to make it much easier for video game developers to create worlds. With Stori you can create characters, events, items, places and make sure it is contextually relevant to the worlds that they are building. Currently you can create place founding myths, national anthems, culture, geographics, politics and technologies. We hope to be able to expand this to other forms such as character backstories and personalities.

Stori

Tech Tales is an exceptional app designed to entertain and educate children between the ages of 3-8. Our team comprises a group of highly skilled experts in AI, Web3, and art, along with experienced teachers who are dedicated to providing young minds with a fun and educational experience. At Tech Tales, we understand the importance of incorporating technology into children's learning experiences in a positive and engaging way. That's why we create stunning illustrations and visual content that capture their imaginations and inspire them to explore new worlds. Our team works tirelessly to ensure that our content is not only entertaining but also educational. Our e-books and stories teach children about the positive aspects of technology and the importance of creativity, problem-solving, and critical thinking skills. As a team, we are committed to creating a safe and secure environment for children to learn and grow. We believe that technology can be a powerful tool for learning and that it should be used responsibly and ethically. That's why we always put the safety and well-being of children first in everything we do. If you're looking for an app that combines fun, learning, and creativity, look no further than Tech Tales. Join us!

Tech Tales

AI Home Design is an interior design assistant powered by Stable Diffusion and YOLO to solve pain points felt by homeowners. It differs from other AI interior design apps out there because 1) it addresses pain points in homeowners' entire user journey, 2) functions as a social sharing platform, and 3) is an aide to augment, not replace home decor professionals and designers. FIRSTLY, the flagship "Create With AI" feature guides the user in prompt engineering to convert their design hunches from text to actual image, helping them overcome creative blockages. This also improves communication with interior designers, since words can be subjective, but images are direct. SECONDLY, homeowners may want to reimagine a space even after initial fittings like paneling and paint jobs are already done. They cannot tear down these fittings in real life, but they can use Stable Diffusion's image-to-image functionality to reimagine the space. THIRD, AI Home Design also functions as a social sharing platform where users can draw inspiration and start conversations with one another. FINALLY, homeowners still need to furnish and populate their spaces even after they have decided on their designs. This is where YOLO comes in, helping the user to recognise objects, and creating outbound e-commerce links for them to buy items. AI is thus used here to smoothen homeowner-professional interactions and engender connections. Even after the hackathon, I am continually improving the app by creating new features (see slide deck!), such as tools to facilitate discussions, recommenders, or improved object detection. On the technical front, I aim to infuse more powerful models like CLIP, Segment Anything or YOLOv8. On the business front, I am building in-app services to serve new target groups like real estate agents and elder-friendly/disability-friendly retrofitting specialists. Join me on this journey to make interior design more seamless for users, and to use AI in a coherent, impactful way.

W Tan

Arty is a unique application that combines AI-generated art with blockchain technology. Users can create a beautiful and cohesive collection of NFTs with a shared aesthetic, allowing them to showcase their creativity in an entirely new way and join the growing community of blockchain-based artists. One of Arty's key features is its ability to transform poetry into pixel art. By analyzing the emotional state of words, the app generates glitched and distorted visual parameters that capture the essence and emotional power of poetry in a visual medium. The result is a stunning collection of pixel art that transcends language and cultural barriers, providing an innovative platform for artists and creators to explore the possibilities of pixel art and poetry. Arty's user-friendly interface and gamified art-making experience make it an engaging and entertaining attraction, serving as a powerful onboarding tool from web2 to web3. The app's roadmap includes plans to promote the web3 philosophy at in-person events, using Arty as a tool to create a seamless interface between attendees and the blockchain. Our team is based in Brazil and consists of people of color, transgender individuals, and other underrepresented communities in tech, striving to create a more inclusive and accessible art world. We are actively seeking partnerships with leading technologies in the space, including MetaMask, Ledger, ETH, Polygon Matic, and others that align with our vision. Together, we can create something truly special and revolutionize the art world with blockchain technology.

Arty dapp[Prompt Poem to Pixelart]