Optimized Training script for Ace-Step with low VRAM support for local GPUs.
Radar
New projects people are discovering or following across Pinokio.
Volumetric photo editor for Pinokio — Thought Graph, intent bar, scene reconstruction
Free, open-source, local alternative to Opus Clip, Vizard & Klap. Turns long videos into AI-scored viral short clips (16:9/9:16/1:1) with complete-thought detection, keyword search, a pick-the-best review workflow, auto face-reframe, and word-by-word captions. 100% on your machine - no subscription, no API keys.
Netryx is a powerful, locally-hosted geolocation tool that uses state-of-the-art computer vision to identify the exact coordinates of a street-level image. It replicates the core pipeline of high-end geolocation SaaS platforms but runs entirely on your local hardware.
Video to Openpose & DWPose (All OS supported) https://github.com/sdbds/vid2pose
Official implementation of HYPIR: Harnessing Diffusion-Yielded Score Priors for Image Restoration (SIGGRAPH 2025)
Build your own data-driven market edge with swing-trade signal webhooks, dashboards, alerts, AI agents, and automation examples.
Index construction PDF drawing sets into a queryable database. Counts, dimensions, confidence scores, and sanity checks from the PDF vector layer. Claude Code skill + CLI.
Generate any location from the real world in Minecraft with a high level of detail.
Slice any audio file into fixed-length (10-60s) clips and export them all at once. Powered by ffmpeg.
Open Source Canvas: an open-source node canvas that runs ComfyUI workflows.
Drag & drop UI to build your customized LLM flow: https://github.com/FlowiseAI/Flowise
Image-Text-to-Text model. Download, explore files and run it on Hugging Face.
Robust automatic speech recognition for challenging real-world audio. Handles noise, far-field, echo, reverberation, and more using a foundation model trained on 2.6M samples across 54 acoustic scenarios.
