In this session, I created a web application for image generationm based on text prompt using SDXL. You can visit the web app here https://endjourney.streamlit.app/

Pre-requisites:

• Streamlit Account https://share.streamlit.io/
• Replicate https://replicate.com/

Resources:

• Stable Diffusion Paper https://arxiv.org/abs/2307.01952
• Github Repo https://github.com/Stability-AI/generative-models
• Model Card https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
• Cross Attention used in SDXL https://vaclavkosar.com/ml/cross-attention-in-transformer-architecture
• Refined used in SDXL https://sde-image-editing.github.io/
• Tuning Guide https://sdxl.replicate.dev/