Professional text-to-speech with voice cloning — powered by Kyutai Pocket TTS
Radar
New projects people are discovering or following across Pinokio.
[Mac Only] Super Fast MLX Powered Video Transcription https://github.com/RayFernando1337/MLX-Auto-Subtitled-Video-Generator/ by https://x.com/RayFernando1337
[MAC ONLY] A powerful and user-friendly web interface for FLUX, powered by MLX and Gradio via MFLUX
Open-source agentic video production studio. Install everything, launch the Backlot live storyboard, render zero-key demos, and open an agent shell.
Pinokio launcher for LTX-Desktop-WanGP (local video generation with WanGP backend)
A FastAPI wrapper for KokoroTTS. Integrates with Open-WebUI and other API-driven AI applications.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Customizing Realistic Human Photos via Stacked ID Embedding https://huggingface.co/spaces/TencentARC/PhotoMaker-V2
⚡️ Efficient 6B parameter image generation model with sub-second inference. Generate high-quality, photorealistic images with only 8 inference steps. Features bilingual text rendering (Chinese & English) and Single-Stream Diffusion Transformer architecture.Minimum 4GB graphics memory is supported.
Standalone local hi-res fix: enlarge images with Real-ESRGAN and reinject clean detail with Z-Image Turbo img2img. 100% local — no ComfyUI, no SwarmUI, no cloud.
Unified Image Understanding and Generation. Text-to-Image Generation, In-context Generation, Instruction-guided Image Editing, Visual Understanding (Minimum Requirements 12GBV RAM / 48GB RAM, Recommended Requirements 24GB VRAM / 32GB RAM)
Enhanced background remove and replace app built around BRIA-RMBG-2.0 https://huggingface.co/briaai/RMBG-2.0
High-quality image generation and editing powered by SenseNova-U1-8B-MoT (NEO-Unify architecture). Supports text-to-image, image-to-image editing, and reasoning mode.
Run the MLX Audio FastAPI backend and Next.js control panel with one click on Apple Silicon.
