AROMAL M
MARIYAM LIYANA C P
KADEEJA SHIRIN C P
MUHAMMED SALIH

Text-to-image generation is a field with great potential. It gen- erates images
from text prompt. In our project, after exploration of several models, we
decided the Attentional Generative Adversarial Network model(AttnGAN)
would give us the best performance. Im- agen, a text-to-image diffusion model
with an unprecedented degree of photorealism and a deep level of language
understanding. Imagen builds on the power of large transformer language
models in under- standing text and hinges on the strength of diffusion models
in high- fidelity image generation.