EfficientCLIP-GAN: High-Speed Image Generation with Compact CLIP-GAN Architecture

A high-quality, fast, and efficient text-to-image synthesis model

Generated Images

Requirements

• python 3.9
• Pytorch 1.9
• At least 1xTesla v100 32GB GPU (for training)
• Only CPU (for inference)

EfficientCLIP-GAN is a small, rapid and efficient generative model which can generate multiple pictures in one second even on the CPU as compared to Diffusion Models.

Note :

For more details on inference and training visit Github Page