Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!
Radar
New projects people are discovering or following across Pinokio.
generate a video from an image with a text prompt
Advanced 3B parameter language model with Gradio web interface, GPU acceleration, and complete privacy
Generate stunning illusion artwork with StableDiffusion (A space by @angrypenguinPNGAP - created with Monster Labs QR ControlNet.
A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
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/Panchovix/stable-diffusion-webui-reForge
A Windows audio mixer that routes microphones, voice effects, music, and app audio into one virtual microphone, with hotkeys, monitoring, overlays, and OBS support.
a tiny vision language model that kicks ass and runs anywhere https://github.com/vikhyat/moondream
This application allows you to upload and prepare your dataset, select a language model, fine-tune it, evaluate its performance, and deploy it to Hugging Face Hub.
[MAC ONLY] FastVideo's Apple Silicon models in one iterative UI: FastH3 (video + audio, references) and FastMetal (fast silent video), native MLX. Timeline with reroll, edit, finalize and live previews.

Self-hosted, offline API directory: 11,860 APIs, instant search, admin panel and 100k+ bulk import.
Chat local com o Codex CLI, memória real em SQLite (com extração automática pela IA) e um atlas neural 3D da sua memória.