DarwinAnim8or/Something-V2.2-OpenVINO

Something V2.2 OpenVINO

This is a conversion of NoCrypt's Something V2.2 model to OpenVINO format. The original model is a stable diffusion model that can generate realistic images from text input.

What is OpenVINO?

OpenVINO (Open Visual Inference and Neural network Optimization) is a free toolkit that facilitates the optimization and deployment of deep learning models on Intel hardware. It supports models trained with popular frameworks like TensorFlow, PyTorch, and more. It also provides a common API to run inference on various devices, such as CPU, GPU, VPU, FPGA, etc.

Why use OpenVINO?

OpenVINO can make it possible to run Stable Diffusion models (and others) on simply the CPU, rather than requiring a GPU, which can be expensive. The time to generate a 512x512 image, on HuggingFace's "CPU Upgrade" space, takes about 21~ seconds after warmup.

For more details, see this blogpost

Usage example

TODO