Open Source AI Finder

A controllable text-to-Foley sound generation system from Stability AI. It generates everyday sound effects from text, with control over timing and acoustic properties.

A music generation model from the Chinese company Minimax. It supports creating music and vocals from text, instrument selection, and can produce songs up to 3 minutes long.

A platform and model for generating high-quality music from text prompts. It can create full tracks with vocals and instrumentals in a wide variety of styles.

An image editing method that uses Retrieval-Augmented Generation (RAG) and guided attention. It allows for precise edits based on a text prompt and a reference image for context.

An autonomous agent designed to play complex real-time strategy (RTS) games like StarCraft II by perceiving the game state and making strategic decisions.

Stands for Iterative Generation of Grammatical Text. It's a method to improve the grammatical correctness of text generated by LLMs by iteratively refining the output.

A model that generates images as Scalable Vector Graphics (SVGs) from text prompts. It uses a hierarchical generation process to create structured and editable vector graphics.

A motion-controllable model for generating 3D animations of human-object interactions from text descriptions and motion control signals.

A preference optimization method from Google for fine-tuning LLMs. It is designed to be a more efficient and effective alternative to methods like DPO for aligning models with human feedback.

A Rocm-based framework developed by AMD for efficient Large Language Model (LLM) inference on AMD GPUs. It aims to optimize performance for deploying LLMs on AMD hardware.