Radar
New projects people are discovering or following across Pinokio.
[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
[v.0.6] FlashVSR - Video (and Image) Upscaler. [Runs on 12GB vram, 32GB ram] Diffusion-Based Streaming Video Super-Resolution
AI agent skill for writing cinema-grade Kling 3.0 video prompts — interactive builder for text-to-video, image-to-video, multi-shot, and keyframes
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A Streamlit app that uses Google's AI to summarize YouTube video transcripts, providing concise, point-form notes. Perfect for quick content overviews.
Summarize any YouTube video in 12 languages using open-source LLMs without API keys.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Enhanced Qwen3-TTS voice cloning GUI with multi-reference samples, variation generation, and audio preprocessing.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A privacy-focused tutoring assistant that explains concepts step-by-step and generates quizzes (MCQs). Works 100% offline with Ollama (Gemma/Llama3).
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hackable and optimized Transformers building blocks, supporting a composable construction.
