Open IP cameras from Insecam.org, in a nice dashboard collection and streaming.
Radar
New projects people are discovering or following across Pinokio.
Bulk transcribe many YouTube videos, whole playlists, or your own uploaded audio/video files at once with faster-whisper. Outputs txt, srt, vtt, or json.
diffusers InstantID + ControlNet inspired by face-to-many from fofr (https://x.com/fofrAI) - a localized Version of https://huggingface.co/spaces/multimodalart/face-to-all
Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. 逆向一切视频,逐个镜头看是拍的、AI 生成的还是代码做的,再告诉你怎么复刻。
Thirteen Claude skills that run an Instagram account: Reels off 26 scored hook formulas, a viral research skill, a caption linter, and a humanizer. Free, MIT.
Open-source AI pipeline that turns any topic into a publish-ready YouTube/Instagram/TikTok Short — research, script, voiceover, visuals, music, captions, and assembly in one command.
Local LoRA trainer for MiniMax H3, Flux2 Klein 9B & Krea 2 — trains against the exact models you deploy. Desktop GUI + headless CLI. NVIDIA only (RTX 30/40/50, driver 555+).
Create and display beautiful presentations with AI integration in Pinokio
Local web UI for orchestrating 3D generation pipelines via ComfyUI / Tripo / Tencent. https://github.com/visualbruno/3DGenStudio
Unofficial Windows ComfyUI nodes for NVIDIA DLSS Super Resolution and experimental Neural Rendering, with still and video workflows.
[NVIDIA Only] Dead simple web UI for training FLUX LoRA with LOW VRAM support (From 12GB)
AI agent that reads real theme-park blueprints, maps and coaster schematics, then builds them automatically in Planet Coaster 1 & 2 via PC-level control (Claude / Gemini / OpenAI vision + PyAutoGUI).
[NVIDIA Only] Select a portrait, click to move the head around https://github.com/jbilcke-hf/FacePoke
