Instalador experimental de FastMetal-QAD 1.3B para Apple Silicon (MLX).
Radar
New projects people are discovering or following across Pinokio.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface https://github.com/comfyanonymous/ComfyUI
This tool lets you drag‑and‑drop photos, GIFs or videos (PNG, JPG, MP4, etc.) and, after confirming the file follows the terms of use, it enhances them to a higher‑resolution 4K version using AI. W...
Full-featured DAW, DJ, and VJ app interoperable w/Ableton, Reaper, Resolume & more. Stable Audio 3, Magenta RT2, Suno API, Chimera track fusion, Demucs stems, MIDI generate/notate, img > spectrogram > music, drawing > music, VST3 & .gan plugins, automix & key-lock, GLSL shaders, volumetric video, Quest 3 XR interface, MIDI auto-map, RAG assistant
Social engineering tool [Access Webcam & Microphone & Location Finder] With {Py,JS,PHP}
An arbitrary face-swapping framework on images and videos with one single trained model!
This Model Through Trip Generation uses socio-economic data to estimate zonal trip totals. Trip Distribution connects origins to destinations via a gravity model. Mode Choice splits person-trips into vehicle trips (PCE). Traffic Assignment loads these onto the network, iterating to equilibrium to yield link volumes and V/C ratios for design.
Luanti (formerly Minetest) is an open source voxel game-creation platform with easy modding and game creation
Qt-based digital signal analyzer, using Suscan core and Sigutils DSP library
One wifi password per device. Ad Blocking & Privacy Blocklists. Policy Based Network Access
A full-stack application for scraping product data from Blinkit, Zepto, and Swiggy Instamart platforms. This application allows users to search for products, see results in real-time, add items to cart, and view their cart.
Fork of the repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".
A Qt GUI app that makes it easy to selectively download multiple videos at once from Youtube and other platforms channels.
Enter a task description and optionally upload one piece of media—an audio clip, a picture, or a short video. The app sends your inputs to the Qwen3.5 Omni model, which replies with a streamed text...
