Just pushed an update to AIraoke-Pinokio. - Guided workflow, quality presets - YouTube download support - Cus...
Launcher updates
Phosphene 3.2.7 - fixes, mostly from bugs you reported here
v3.2.7 is out, and it is entirely fixes - most of them from reports posted right here on this board. Hit Upda...
Another of my video time-saving apps. Features include: cutting out silence, cutting out stutters, automatic ...
3D Model Generation Implemented
First steps to get 3D model generation working on Nexus OS. Still more work to be done on it, but it's a step...
AgentsViewFeatured
AI coding agents are great at moving work forward. Remembering where that work happened is harder. A useful f...
Store
Official Repository: Telegram bot which can download direct links, torrents, nzb, google drive, telegram document, any file/folder from rclone supported clouds, all yt-dlp supported sites and jdownloader supported sites, then upload them to google drive, telegram cloud or to one of rclone supported clouds
ابحث عن كتب من المكتبة الوقفية باستخدام عنوان الكتاب، تصنيفه، أو مؤلفه. احصل على نتائج البحث مع خيارات التنزيل بتنسيقات مختلفة مثل PDF و TXT و DOCX.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Free, local, open-source Opus Clip alternative. GPU-accelerated · Animated captions · Face tracking · No subscription · No watermarks.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
MOSS-Audio is an open-source foundation model for unified audio understanding, enabling speech, sound, music, captioning, QA, and reasoning in real-world scenarios.
Ollama Automated Security Intelligence Scanner
A Python framework for AI-driven character animation using neural networks.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
🔥 Official impl. of "DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing".
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
TexturizerFeatured
Minimal NVIDIA-first web app for texturing existing meshes with Hunyuan3D-2GP/mmgp while preserving rigged GLB structure when the vertex layout stays compatible.
@cocktailpeanut
4 check-ins
echomimic2Featured
[NVIDIA ONLY] Make virtual avatars talk whatever you want with an image and an audio clip https://github.com/antgroup/echomimic_v2
Automatically remove watermarks from videos generated by Sora AI.
@morpheus3 check-ins