LFM2.5-VL-450M (Liquid AI): compact vision–language model for image understanding. Gradio UI with image upload/URL or video (sampled frames), prompt, and generation sliders.
Radar
New projects people are discovering or following across Pinokio.
Brought to you by Cohee, RossAscends, and the SillyTavern community, SillyTavern is a local-install interface that allows you to interact with text generation AIs (LLMs) to chat and roleplay with custom characters.
Upload a photo (or provide its URL) and choose the desired resolution and model. The app separates the main subject from the background and returns the image with a transparent background. You can ...
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Android multi-tool for wireless protocol research (NFC, BLE, IR) and mobile hardware emulation. No root required.
Image-to-Image model with 6B parameters, built with Diffusers. Download, explore files and run it on Hugging Face.
Contribute to SauersML/neural-pairing development by creating an account on GitHub.
A local video studio for your coding agent. Describe a video in one sentence: your agent directs, your machine renders. Claude Code, Codex, Cursor, Devin and more. No API keys, no uploads.
freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.
Z-Image-Turbo - Efficient 6B parameter image generation model with sub-second inference, packaged for Pinokio
Herramienta de flujo de caja inteligente con IA local para PYMEs — Cámara de Comercio de Santiago
A local-first NotebookLM alternative for chatting with documents using Ollama or other LLM providers. This launcher targets 64-bit Windows 11.
NVIDIA DLSS 5 Neural Rendering (NGX feature 18) as ComfyUI nodes. Enhance image batches and video files with the real neural renderer, with optional upscaling.
Generate a story with AI or type your own, and convert it with voice cloning from uploaded samples
Remove long silences, ghost sounds and glitches from TTS audiobooks using Silero VAD
Irodori-TTS is a Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
