Stable Diffusion - A Step Forward for Image Generation

What is the talk about?

A text-to-image model using deep learning called Stable Diffusion was released in 2022. Although it can be used for various tasks including inpainting, outpainting, and creating image-to-image translations
directed by text prompts, its primary usage is to generate detailed visuals conditioned on text
descriptions. The idea of "Super-Resolution" is the foundation of stable diffusion. We develop a deep learning model with Super-Resolution that can denoise a noisy input image and provide a high-resolution image as an output. Using the distribution of their training data, deep learning models replicate the visual details that would most likely be presented as input.

Bio of the speaker
Suman Paul Choudhury - I am currently working as a Data Science Solution Consultant at Sahaj. My area of expertise lies in the area of Computer Vision and Image Processing Domain. I have handled 3 major projects for Fashion, Retail
and Cyber security domain and developed APIs to ensure end-to-end product pipelines. I have done my Masters in Signal processing (specifically speaker verification) and have 5 IEEE
publications related to this domain

Who should be attending? What should they know?
Data Scientist , ML engineers , Data Analyst

Depth of topic:
Intermediate