Separate Maestro DEV build with Storyteller planning chat, saved multi-turn stories, and exact Storyteller-to-Director Short Film handoff. Includes the existing local AI video, image, music, Studio, and Director workflows. Requires an NVIDIA GPU (6GB+ VRAM).
Radar
New projects people are discovering or following across Pinokio.
Describe any song in plain English, compose it locally with an embedded Qwen GGUF model, and generate it with ACE-Step v1.5.
A free, open-source GIS for visualizing, exploring, and analyzing geospatial data locally in your browser.
[NVIDIA ONLY] Super Optimized Gradio UI for Wan2.1 video for GPU poor machines (5GB+ VRAM). Generate up to 12 sec videos https://github.com/deepbeepmeep/Wan2GP
One-click installer for Microsoft TRELLIS.2: High-quality 3D asset generation from images with PBR textures.
a lightweight text-to-speech (TTS) model that can generate high-quality speech with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation). https://huggingface.co/spaces/parler-tts/parler_tts_mini
LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation https://huggingface.co/spaces/ashawkey/LGM
Image-to-3D Gaussian splat generation from VAST-AI-Research. Requires a CUDA-capable GPU.
[WINDOWS/LINUX ONLY] Easily train a good VC model with voice data <= 10 mins!: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI
Estúdio IA para Criação de Letras, Estruturação de Prompts Suno/Udio/Mureka e Geração Musical YuE2 com Transcrição de Covers SheetSage2.
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching https://huggingface.co/spaces/mrfakename/E2-F5-TTS
a state-of-the-art open-source model for fast feedforward 3D reconstruction from a single image, developed in collaboration between Tripo AI and Stability AI. https://huggingface.co/spaces/stabilityai/TripoSR
Lightricks LTX-2.3 video generation (22B distilled-1.1) with a Gradio UI. Auto-detects GPU and configures offload.
MuseTalk is a cutting-edge video-to-video (V2V) lip-sync solution engineered to deliver highly accurate and natural mouth movements synchronized to audio input. Precision LipSync: Realistic and seamless synchronization of speech audio to facial movements. Efficiently designed to run on 8–12 GB VRAM,
Tokenizer-free multilingual TTS and voice cloning with low-VRAM and VoxCPM2 Web UI/API launch modes.
