ENFUGUE is an open-source web app for making studio-grade images and video using generative AI.
A Cli, a webUI, and a MCP server for the Z-Image-Turbo text-to-image generation model (Tongyi-MAI/Z-Image-Turbo base model as well as quantized models)
Glasses detection, classification and segmentation
A pedagogical realization of MPS method.
VGGT 3D Vision Agent optimized for Apple Silicon with Metal Performance Shaders
Metal-native differentiable 3D Gaussian Splatting for Apple Silicon: fused forward+backward rasterizer on PyTorch MPS, no CUDA anywhere.
Tensor Netwok Algorithms for EVERYONE
telegram bot for self-hosted local inference of stable diffusion, text-to-speech and large language models, such as llama3
AI watermark removal built for Apple Silicon. SynthID-class pixel regeneration, visible vendor labels and provenance metadata, with every pipeline decision measured on Metal.
FP8 Metal compute kernels for Apple Silicon MPS — fixing what PyTorch doesn't support yet. FLUX/SD3.5/ComfyUI on Mac.
Enhanced stain normalization for histopathology images with batch processing support. Optimized for CPU, GPU (CUDA), and MPS (Apple Silicon) devices.
羽毛球比赛视频智能分析 | Badminton match video analytics: TrackNet shuttle detection + YOLOv8s-pose player tracking + court homography + bullet-time FX. Runs end-to-end on Apple Silicon. 完整文档与 AI agent 任务包见 HANDOVER.md
🧠 One LLM, split across a Mac (Apple MPS) + a Windows PC (NVIDIA CUDA) — heterogeneous pipeline inference over a framework-neutral wire, bit-for-bit identical to single-machine. No torch.distributed, no datacenter.
🎨 Native AI image generation for Apple Silicon with Qwen-Image. Lightning LoRA acceleration for fast 4–8 step runs. Zero Docker, just works.
Tensor Network State Packages
To associate your repository with the mps topic, visit your repo's landing page and select "manage topics."