This Event Has Finished

Aria & Allegro Multimodal Hackathon

Join the hackathon and unleash your creativity by building intelligent applications with Rhymes AI’s open-source models, Aria and Allegro.

🌟 Be one of the 10 teams: gain exclusive access to Aria’s API and explore Allegro’s text-to-video capabilities!


🚀 Take on the challenge to innovate using Aria, Rhymes AI’s open-source multimodal model.


🤖 Build applications by integrating text, images, video, code, and more with Aria’s AI or create stunning video content with Allegro.


🌍 Collaborate with a team (up to 4 members) or take on the challenge individually!


🎓 Gain insights from industry experts through workshops and sessions designed to fast-track your project.


🏆 Compete for a chance to win $5,000 in prizes!

Aria & Allegro Multimodal Hackathon event thumbnail

About Rhymes.ai


Rhymes.ai
 is an innovative company focused on developing advanced multimodal AI solutions that integrate diverse data types—such as text, images, and video—into seamless outputs. Committed to efficiency, versatility, and open-source collaboration, Rhymes AI transforms how industries leverage AI to build powerful applications.

Through its flagship models, Aria and Allegro, Rhymes AI empowers developers, researchers, and businesses to create sophisticated AI tools. Aria is designed for understanding and generating multimodal content with ease, while Allegro introduces a text-to-video generation capability, enabling the instant transformation of ideas into captivating videos. Together, these models provide a comprehensive solution for multimodal AI innovation.

Key Features of Aria & Allegro

Multimodal Native: Seamlessly processes text, images, and videos within a unified model.

Lightning-Fast Video Processing: Captures and captions 256-frame videos in just 10 seconds.

Text-to-Video Generation (Allegro): Rapidly transforms text into high-quality 720p video.

Open-Source Model: Fully available for developers to modify, customize, and extend.

Apache 2.0 License: Grants full access to weights, code, and demos.

Hackathon Challenge

The challenge is to develop innovative solutions that seamlessly integrate multiple data types—such as text, images, video, and code—into cohesive, intelligent applications using Rhymes AI’s powerful multimodal models, Aria and Allegro.


Participants can use Aria to handle diverse data inputs, creating smarter tools for healthcare, content creation, and customer service. With Allegro, teams can explore innovative text-to-video applications for media solutions.


Your challenge is to design applications that showcase the potential of Aria and Allegro through enhanced functionality, improved performance, and real-world impact.


Key requirements:


• Use Aria or Allegro as the foundational model, building or fine-tuning it to develop your application.

• Teams can have up to 4 members, or you may choose to work individually.

• All submissions must be open-source and shared through a GitHub repository.

Apply for Exclusive Access!

With high demand for early access to Rhymes AI’s groundbreaking technology, we’re excited to offer 10 API keys to selected teams. These teams will gain exclusive access to Aria and Allegro's API, provided by Rhymes.ai, and have the chance to participate in the upcoming Aria & Allegro Multimodal Hackathon.

How It Works

1. Register for the Aria Multimodal Hackathon: Complete the registration form and express your interest.
2. Form Your Team: Gather your team members and create your team profile on the lablab.ai platform.
3. Selection Process: Based on the information provided in your registration, we will carefully select the most qualified teams.

Registration is open until the 30th of October.
Teams selected for this unique opportunity will be notified by email and granted access to the Aria & Allegro API to kick off their participation in the Hackathon.

⚠️ Important Note for All Participants

For the hackathon, compute resources are allocated as follows: Aria allows unlimited tokens at a rate of 120 requests per minute (RPM), while Allegro supports 1 concurrent video generation request per team.

Thank you for making the most of these resources and working creatively within the provided setup!


✨ Don’t miss out on this chance to work with cutting-edge technology! Gather your dream team and apply now for your spot.

Technology

Rhymes AI’s flagship models, Aria and Allegro, are at the forefront of multimodal AI innovation, each designed to tackle unique challenges in processing diverse data types.

Aria is the flagship Mixture-of-Experts (MoE) model developed by Rhymes AI, specifically designed to handle multimodal inputs like text, images, and video. This open-source model focuses on efficiency and high performance. During inference, Aria activates only 3.9 billion parameters from its total 25.3 billion parameters, making it one of the fastest multimodal AI systems available today. Aria processes diverse data formats seamlessly, leveraging its 64K-long multimodal context window to deliver comprehensive insights. This capability allows it to handle long-form content, such as captioning 256-frame videos in just 10 seconds, with remarkable speed and precision.

Allegro, Rhymes AI’s text-to-video model, introduces new capabilities for creative industries, enabling users to transform text into high-quality videos quickly and efficiently. Allegro is optimized for video generation tasks, with a model size of 3B parameters, and can process short video clips at 720p resolution in a matter of minutes. Its optimized architecture allows for rapid video production, opening up new possibilities for content creators, marketers, and AI researchers alike.

👉 Read more about Rhymes AI's Aria & Allegro models

Winner

💰 Cash: $3,000

2nd Place

💰 Cash: $1,500

3rd Place

💰 Cash: $500

Please be aware that participation in lablab.ai hackathons is voluntary and subject to the specific rules and conditions outlined for each event. While we strive to provide a fair and rewarding experience for all participants, we cannot guarantee entry or success in securing prizes. All prizes and opportunities are subject to availability and participants must meet the established criteria to qualify. lablab.ai is not responsible nor held liable for any commitments or offers - including programs, giveaways, or prizes - made by third-party sponsors or partners of the hackathon. The availability and delivery of third-party prizes or benefits are solely at the discretion of the respective sponsors and are not guaranteed by lablab.ai. We reserve the right to make amendments, modifications, or cancellations to any part of the hackathon (including full cancellation of the event itself), including prizes and terms of participation, at our sole discretion. Whenever possible, we will endeavor to notify participants of significant changes within a reasonable timeframe. All submissions by participants must be original work, open source, and compliant with the MIT License unless specified otherwise. By participating, you agree to these terms, the overall event terms, and the lablab.ai general terms and are encouraged to review all event-related information carefully. Prize Distribution: lablab.ai and its partners reserve the right to distribute all prizes within a 90-day period following the end date of the hackathon. This period allows for the proper processing and verification needed to award prizes appropriately.

What to submit?

📋 Basic Information

• Project Title

• Short Description

• Long Description

• Technology & Category Tags

📸 Cover Image and Presentation

• Cover Image

• Video Presentation

• Slide Presentation

💻 App Hosting & Code Repository

• Public GitHub Repository

• Demo Application Platform

• Application URL

For further details and guidance, please visit Submission Guidelines


Judging Criteria
Application of Technology
How effectively the chosen model(s) are integrated into the solution.
Presentation
The clarity and effectiveness of the project presentation.
Business Value
The potential impact and practical value of the solution.
Originality
Uniqueness and creativity in addressing the challenge.

Hackathon Details

Join lablab.ai hackathon and innovate using the latest models in the market. Discover all the relevant details below.

🗓️ Where and when

The start date of the hackathon is mentioned according to the date specified on the hackathon page, cover and schedule. The hackathon will take place on the lablab.ai platform and lablab.ai Discord server.

🦸🏼‍♂️ Who can join?

Teams with a passion for AI are encouraged to apply! Whether you're experienced or new to AI, if you're ready to innovate with Rhymes AI’s Aria API, this is your chance. Only 10 teams will be selected, so gather your team and apply now!

😅 What about teams?

If you don't have a team, don't worry! You can connect with other participants from all over the world on our dashboard or Discord server. We also recommend checking out our Discord server to find teammates and bounce around ideas. You can join the server here.

🛠️ How to participate

The hackathon will take place online on lablab.ai platform and lablab.ai Discord Server. Please register for both in order to participate. To participate click the "Enroll" button at the bottom of the page and read our Hackathon Guidelines and Getting Started Guide.

🧠 Get prepared / Use Lablab.ai to Learn About AI

To get ready for the hackathon, visit our AI Tech pages and read up on all the available technologies. You can also check out our tutorials page for more information on how to use them. Get a head start on your project by using the resources on lablab.ai!

Speakers

Pawel Czech
Pawel Czech
Co-Founder
New Native
Dongxu Li
Research Scientist at Rhymes.AI
Noah Maazel
Engineer at Rhymes.AI
Justyna Amelia Kotłów
Event Manager
Pawel Czech
Co-Founder
Dongxu Li
Research Scientist at Rhymes.AI
Sergey Nuzhnyy
Head of Developer Relations
Junnan Li
Research Lead
Noah Maazel
Engineer at Rhymes.AI
Justyna Amelia Kotłów
Event Manager
Emmanuel Iriarte
AI Architect
Jonathan Rundberg
AI Automation Lead
Jens Ingelstedt
Global Head of Accelerators
Pawel Czech
Co-Founder
Sergey Nuzhnyy
Head of Developer Relations
Emmanuel Iriarte
AI Architect
Jonathan Rundberg
AI Automation Lead

Event Schedule

  • To be announced

Submitted concepts, prototypes and pitches

Submissions from the teams participating in the Aria & Allegro Multimodal Hackathon event and making it to the end 👊

Vercel
application badge

Lenso

Lenso is an AI-driven platform that redefines photo and video management, making it easy to search memories by keywords or visual similarity. With secure cloud storage, advanced AI analysis, and intuitive search.

Code Crusaders

Generative AI Studio
Vercel
application badge

VIsionAid

VisionAid is a medical assistant app for the visually impaired uses voice commands to interpret medical images and prescriptions, offering hands-free insights and voice-guided responses for easy, accessible healthcare.

TrioVibians

VercelRhymes.ai
Vercel
application badge

PrepAlly

PrepAlly, ur AI-powered coding prep platform, offering real-time feedback, voice-guided insights, and secure, interactive practice. Open-Source and innovative, it transforms stress into confidence and elevates your interview game-prep smarter, ace faster.

Open Community

GPT-4 Visiono1ElevenLabsVercelChatGPTRhymes.ai
Streamlit
application badge

Pulse and Prism

Pulse & Prism is an AI-powered content creation platform that transforms text into multimedia content. It can generate poetry, convert text to speech, and combine them into complete poetry videos with synchronized audio.

BTAJI Crew

streamlitOpenAIRhymes.ai
Streamlit
application badge

Game Concept Generator

🎮 Game Concept Generator is a Streamlit app for creating and managing video game concepts, generating ideas, organizing projects and documenting development.

R bot

streamlitRhymes.ai
Streamlit
application badge

RobotSight

RobotSight is an Aria-backed visual analysis assistant that can help a cleaning robot distinguish dirty items and garbage inside a hotel room.

RobotSight

streamlit
Streamlit
application badge

Allergy Detector

Allergy Detector is an innovative chatbot that helps users identify food allergens. Users enter their name, select known allergies (or have them auto-identified), and upload a photo. The app then lists ingredients and potential allergic symptoms.

anything in real time

streamlitRhymes.ai
medal
Vercel
application badge

AlgSense - Impacting 1 Billion Lives

The AlgSense platform can impact over 1 billion lives by addressing harmful algal blooms (HABs) through community monitoring tools that enhance sustainability, protect water quality, and support livelihoods.

Galera

Rhymes.aiOpenAI

Zest Health AI

Zest Healthcare AI is a powerful app that leverages Aria, a cutting-edge language model, to instantly understand user queries and provide accurate, data-driven responses.

Code Shredders

Rhymes.ai
Streamlit
application badge

YouClipAI

YouClipAI is a content creator’s dream tool for clipping key moments from long videos like podcasts or interviews. It automatically generates shareable clips with viral-worthy captions, helping creators save time on editing and captioning.

ContentGEN

streamlitRhymes.ai
Streamlit
application badge

ScholarIntel-Intel Decision Making for Scholar

ScholarIntel | Intelligence Decisions Making for Scholars. ScholarIntel is the cutting-edge technologies with solutions of Intelligence Decisions Making Platform for Researchers and Scholars to Empowering Advance and Automate Research Capabilities.

ScholarIntel

Llama 3.2SuperAGIstreamlitMongoDB
Streamlit
application badge

ViTexBrain

AI Video and Text Generator using Rhymes' Aria and Allegro models

The FynBots

Rhymes.ai
Vercel
application badge

RevisitInk - Healing Memories

Revisit Ink is a personal therapy app that helps users to heal their memories via text, audio, images and videos. We all have memories that deserve healing!

Psych

OpenAIOpenGPTsLlama 3.2Rhymes.ai
Vercel
application badge

Documate

Compile everything you read online! Just start the chrome extension, and Documate will automatically organize , compile and document all that you have read.

Lastmin

OpenAI
Streamlit
application badge

Annuncio-Revolutionize Ad Generation with AI Magic

Annuncio is an innovative application that leverages AI to seamlessly generate product advertisements, including detailed descriptions and promotional videos, all within an intuitive web interface.

ImportBrain

Rhymes.aistreamlit
medal
Streamlit
application badge

Avjo - Marketing Video Generator

Created Rhyme's AI Powered Marketing video generator. Bringing down the time and cost from $4000 monthly to $100 monthly.

Avjo

streamlitRhymes.aiOpenAI

restio

Our project aims to create a personal mood synchroniser app that integrates positive daily habits for mental health and self-improvement. By providing mindfulness exercises, AI-driven mood analysis and community support.

pathfinder

Rhymes.ai
medal

Asymptotic Cuteness

This is a project that utilizes advanced AI models—Aria and Allegro—to iteratively enhance the cuteness of a cat video.

bioAI

Rhymes.aiOpenAI

Rescure

Rescure is an AI-driven first aid assistance for emergencies. Snap, analyze, and act fast to help injured individuals with real-time guidance.

TeamX

Rhymes.aiOpenAI