DeepMind's video-to-audio (V2A) technology generates rich soundscapes for videos using video pixels and natural language text prompts.
New to the directory.
Browse by the original listing date. Added does not mean recently verified.
L-MAGIC is a novel method leveraging large language models for guidance while diffusing multiple coherent views of 360 degree panoramic scenes.
Molmo is a multimodal open language model built by Ai2, enabling users to interact with images and text for diverse applications.
Wanderboat AI is a trip planner that helps users discover restaurants, attractions, and events in minutes. It offers a personalized travel plan, outing suggestions, and import features to make trip planning easier.
UniAnimate is a framework that enables efficient and long-term human video generation by taming unified video diffusion models for consistent human image animation.
Genie is the world's best AI software engineer, achieving a 30% eval score on the industry standard SWE-Bench benchmark. It can solve bugs, build features, refactor code, and more, either autonomously or paired with the user.
Neutone Morpho is a cutting-edge AI tone morphing plugin that transforms any sound into something new and inspiring using machine learning technology.
Stable Diffusion 3 Medium is the latest and most advanced text-to-image AI model, offering exceptional quality, photorealism, and prompt understanding. Released under the Stability Community License, it is ideal for running on standard consumer GPUs without performance degradation.
A nanoGPT pipeline packed in a spreadsheet, providing a unique approach to machine learning and data analysis.
Unique3D is a novel image-to-3D framework that efficiently generates high-quality 3D meshes from single-view images, featuring state-of-the-art generation fidelity and strong generalizability.
RPGGO is a revolutionary text to game engine that enables users to create and play AI-powered RPGs and NPCs. With its intuitive interface and advanced AI capabilities, RPGGO provides a unique gaming experience.
Discopixel Face Animator uses AI to create custom music videos from uploaded photos and fun facts, providing an entertaining and unique experience.
Camb.ai is a cutting-edge AI company that specializes in voice translation and dubbing for videos. With its advanced AI technology, Camb.ai enables users to create and experience storytelling in every language.
This repository contains the source code for an all-in-one LLMs Chat UI for Apple Silicon Mac using the MLX Framework.
The Video to Sound Effects Generator by ElevenLabs is a powerful tool that converts videos into realistic sound effects. It utilizes advanced algorithms to analyze video content and generate corresponding sound effects.
Cartwheel is a powerful text-to-animation platform that allows users to animate characters for various projects by simply typing.
Built with the Gemini API, Flutter, and Firebase, the I/O Crossword is an exciting puzzle experience that challenges and entertains. Explore the Learning Pathway to learn how to recreate experiences like the I/O Crossword using Flutter and Firebase Genkit with Codelabs, Blogs, and Videos.
Quill.org is a free literacy tool that provides interactive writing and grammar activities for students. It offers a range of tools, including Quill Connect, Quill Lessons, Quill Diagnostic, Quill Proofreader, and Quill Grammar, to help students improve their writing skills.
GuideGeek is a travel companion that helps you plan and navigate your trips with ease. With a vast knowledge base and a user-friendly interface, GuideGeek is the perfect tool for travelers of all levels.
Match AI generated images with Riddle Me This, a fun and challenging game that tests your problem-solving skills.
SnapEdit is an AI-powered online photo editor that delivers amazing tools to retouch pictures easily like never before. Try it now and see your photos transformed with one click!
Create, organize, and visualize your ideas effortlessly with our mindmap generator tool. Perfect for content creators, educators, teachers, teaching assistants, tutors, or homeschooling parents alike to visualize concepts for your audience, students, or children.
GetYarn.io is a platform that allows users to find video clips from their favorite movies, TV shows, and music by searching for quotes.
FlexClip is an innovative video creation platform that empowers users to produce stunning, professional-grade videos with ease. With its intuitive interface and robust features, FlexClip makes video creation accessible to everyone.