SurgiLook.ai

This is the interface of SurgiLook.ai.
options can be selected by user.
This is the result of demo image.

Inspiration💡

Recently, while having a casual discussion with a friend who is pursuing an MBBS degree, we delved into the topics of our respective subjects—my engineering courses and his medical studies. The conversation eventually steered towards AI, and he asked, "Can AI generate images depicting how a person will look after surgery?" I responded, "Why not?" Since that conversation, I've embarked on a research journey into generative AI and its various models. I believe these models could significantly assist doctors and patients by providing visualizations beforehand, potentially bolstering confidence in their decisions.

What it does🚀

SurgiLook.ai allows you to upload your photo and see a realistic visualization of your face before and after cosmetic surgery. This helps you make informed decisions about your transformation.

How we built it👨‍💻

We used Hugging Face's AI model.Hugging Face is an open-source community that develops tools and resources to build, deploy, and train machine learning models. Model type: Diffusion-based text-to-image generative model Model Description: This is a model that can be used to generate and modify images based on text prompts. It is a Latent Diffusion Model that uses two fixed, pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L). For frontend we used Streamlit.Streamlit is an open-source Python library that makes it easy to create and share beautiful, custom web apps for machine learning and data science.

Challenges we ran into🤙

Relatively genrative ai is a new technology so it was bit difficult for us to be familiar with it and to create a model in first place .As well as resources were limited and we couldn't ask too much for help.

Accomplishments that we're proud of🌟

We're proud that we could implement this in very short time and we managed to do it in best possible way.

What's next for SurgiLook.ai👾

I believe after fine tuning this kind of models,we can make the model more precise as well as integerate with networks of best surgeons over the golbe to make it more scalable .That's how we can create greater impacts in this field.