Stable Diffusion WebUI Forge is a platform on top of Stable Diffusion WebUI (based on Gradio) to make development easier, optimize resource management, and speed up inference. https://github.com/lllyasviel/stable-diffusion-webui-forge?tab=readme-ov-file
Radar
New projects people are discovering or following across Pinokio.
Run Open Notebook locally via Docker with one-click install, start, and shutdown.
Zero-shot speech and singing conversion and TTS
Nari Dia is a powerful text-to-speech (TTS) application based on the Dia-1.6B model from Nari Labs. This application allows you to convert text into natural-sounding speech with various customization options.

Installe StreamSplat dans un env conda isolé Pinokio + build rasterizer + Depth Anything V2 checkpoint + reset propre.
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Text-to-Image model with 5B parameters. Download, explore files and run it on Hugging Face.
One-click launcher for Stable Diffusion web UI Forge (lllyasviel/stable-diffusion-webui-forge)
Professional browser-based video editor. Open source CapCut alternative. 100% browser-based, no cloud uploads, no watermarks.
state-of-the-art tuning-free method to achieve ID-Preserving generation with only single image, supporting various downstream tasks. https://instantid.github.io/
Free, open-source (MIT) desktop app for local AI image & video generation - FLUX.1, SD 3.5, SDXL, LTX Video, AnimateDiff. Electron + React + FastAPI/PyTorch. Runs on NVIDIA CUDA, Apple Silicon (Metal/MPS), or CPU. Local by default, no telemetry.
Lightweight CPU text-to-speech with preset voices and optional Hugging Face-authenticated voice cloning.
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching https://huggingface.co/spaces/mrfakename/E2-F5-TTS
Kimodo: Kinematic Motion Diffusion Model. Generates high-quality 3D human and robot motions.