Text-to-Image Generation Model with DNN Architecture and Computer Vision for Embedded Devices Using Quantization Technique

Text-to-image generation is a type of deep learning task where the goal is to generate realistic images from textual descriptions. The model takes in a textual description as input and produces an image that closely matches the description. Quantization techniques have been used to reduce the size of the models while minimizing accuracy loss due to the high computational and memory requirements of these models. These models suffer from a number of problems, including a large model size and a high-accuracy model, which has led to a significant increase in computation and model storage requirements as well as increased power consumption. The study addresses these issues and concentrates on increasing model speed, lowering computational cost, compressing the size of the model, and improving the model's energy efficiency. We can achieve our objectives by using quantization techniques. This quantized model is later deployed on the embedded devices.