StableDiffusion
StableDiffusion is a C implementation for running inference on the popular Stable Diffusion deep learning model using ONNX Runtime. This tool enables users to generate images from text prompts by executing the CLIP text encoder, UNet denoising scheduler, and VAE decoder components directly within .NET applications. It supports creating visual representations from natural language descriptions, such as generating scenes of landscapes or animals based on input sentences. The software requires a GPU-enabled machine with CUDA or DirectML support on Windows to perform high-performance image synthesis. Users can utilize pre-converted ONNX models available via Hugging Face for versions 1.4 and 1.5, or convert PyTorch models themselves. The project is designed for developers using Visual Studio or VS Code, allowing them to clone the repository, integrate model files, and execute image generation tasks with minimal setup on compatible hardware like NVIDIA GTX 3070 or newer. It includes examples of generated outputs an