Radar
New projects people are discovering or following across Pinokio.
Roblox Foundation Model for 3D Intelligence --- Cross Platform (Mac, Windows, Linux): Requires 16GB+ VRAM PC or 18GB+ Memory Macs https://github.com/Roblox/cube
AudioCraft Plus is an all-in-one WebUI for the original AudioCraft, adding many quality features on top https://github.com/GrandaddyShmax/audiocraft_plus
Prompt, run, edit, and deploy full-stack web apps. https://github.com/stackblitz-labs/bolt.diy
MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS.
Source-only local video LoRA studio, installed by the Pinokio launcher; model weights remain local.
📦 Repopack is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, and Gemini.
1 Click Installer for Retrieval-based-Voice-Conversion-WebUI (https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)
FlashVSR+ one-step diffusion video super-resolution on Apple Silicon, powered by the vpipe engine (Metal). Choose Turbo (speed, hybrid attention) or Base (quality) variants, upscale any video to 1080p/4K targets with color-preserving restoration, and compare before/after with a slider. Video runs as background jobs with live progress and a result library.
Turn any raw text into a high-quality dataset for AI finetuning https://github.com/e-p-armstrong/augmentoolkit
Anime and manga media server with a local web interface. https://github.com/5rahim/seanime
This app lets you add realistic sound to a short video or create a standalone audio clip just from a text description. Upload a video and write a prompt (you can also give a negative prompt) to rec...
[WINDOWS/LINUX ONLY] Easily train a good VC model with voice data <= 10 mins!: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI
[NVIDIA Only] Dead simple web UI for training FLUX LoRA with LOW VRAM support (From 12GB)
SOTA model-agnostic quantization for GGUF, local inference and beyond. Quantize and run text, image, video and audio models with llama.cpp, vLLM, Diffusers and PyTorch.
[NVIDIA GPU ONLY] Unofficial Implementation of Animate Anyone https://github.com/MooreThreads/Moore-AnimateAnyone
