Shrinivasan Sankar

Lumiere — The most promising Text-to-Video model yet from Google

Would you like to see Monalisa smile like a witch? Or would

ControlNet — Take complete control of images from the generative model

This week let's look at one of the most influential

QLoRA — Train your LLMs on a Single GPU

In my previous article, we saw about Low-Rank Adaptation or LoRA. LoRA

LoRA - Low-Rank Adaptation of LLMs (paper explained)

Introduction Whenever we want a custom model for our application, we start

Stable Video Diffusion — Convert Text and Images to Videos

Stability AI, one of the leading players in the image generation space,

Emu — the foundation model for Emu Edit and Emu Video

“Enhancing Image Generation Models Using Photogenic Needles in a Haystack” aka. Emu

Best of Generative AI Research this week

We have handpicked some of the best Generative AI research work published

Model Quantization in Deep Learning

Quantization in general can be defined as mapping values from a large

MusicGen from Meta AI — Model Architecture, Vector Quantization and Model Conditining explained

MusicGen or Simple and Controllable Music Generation is the latest work from

Prompting and prompt engineering? — a comprehensive introduction

Prompting and prompt engineering are easily the most in demand skill of

ImageBind: One Embedding Space To Bind Them All — paper explained

Images are truly binding. An image of a beach, reminds the pleasant

DINO-V2: Learning Robust Visual Features without Supervision — Model Explained

Introduction If you take the field of Natural Language Processing, the foundational