Global radar

[NVIDIA] Pinokio launcher for the released WorldMirror 2.0 reconstruction app from HY-World 2.0. Uses a cu128 PyTorch baseline with gsplat from PyPI/JIT. https://github.com/Tencent-Hunyuan/HY-World-2.0

π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video.

Local face detection + recognition (Pimeyes alternative)

Contribute to mostwant959-ship-it/Mark-LIV-main development by creating an account on GitHub.

[NVIDIA ONLY] Efficient Implementation of Animate Anyone (13G VRAM + 2G model size) https://github.com/sdbds/Moore-AnimateAnyone-for-windows

🎬 A fully autonomous, AI driven, production dashboard for technical YouTube videos

Generate editable Ideogram JSON prompts from uploaded images.

Seedance 2.0 is a revolutionary multi-modal video generation model that bridges the gap between AI and professional filmmaking. This repository provides the official Python client for interacting with the Seedance API.

Browser-based 3D avatar head and mouth controller with keyboard and gamepad support. https://github.com/promptpirate-x/discord-id-bypass-tool

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the model.

Create 3D Meshes of Body Poses from Images.

⚡️ Efficient 6B parameter image generation model with sub-second inference. Generate high-quality, photorealistic images with only 8 inference steps. Features bilingual text rendering (Chinese & English) and Single-Stream Diffusion Transformer architecture.Minimum 4GB graphics memory is supported.

Simple Gradio app for generating images with Tongyi-MAI/Z-Image-Turbo.

Discover amazing ML apps made by the community

[NVIDIA GPU Only] An optimized version of MagicAnimate https://github.com/sdbds/magic-animate-for-windows

Type a writing prompt and the app will craft vivid, gritty novel‑style text for you. You can tweak settings such as creativity and length, and the result is a ready‑to‑use story fragment.

This app lets you have a conversation with an AI model by typing a message and optionally attaching a single image or video. The model processes the visual input together with your text and streams...

使用本地 LM Studio AI 免費校正 ASR 課程字幕，支援 PDF 參考資料，不需 API Key

Fooocus powered by FastAPI