A high-fidelity Multimodal Diffusion Transformer (MM-DiT) built from scratch for human face synthesis, optimized for single-GPU training.
A portable Local AI Image Generator and Stable Diffusion GUI for Windows, Linux, and macOS. Run GGUF & Safetensors models 100% offline with zero setup and auto-detected GPU/NPU acc...
Dify plugin to access 100+ generative AI models (image, video, audio) via MuAPI
End-to-end fraud detection project featuring synthetic transaction data, feature engineering, Random Forest classification, model evaluation, and deployment-ready artifacts for asp...