YoVDO

Understanding and Mitigating Copying in Diffusion Models

Offered By: Google TechTalks via YouTube

Tags

Diffusion Models Courses Artificial Intelligence Courses Machine Learning Courses Computer Vision Courses Stable Diffusion Courses Image Processing Courses Image Generation Courses Data Replication Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the challenges and solutions surrounding content replication in diffusion models through this Google TechTalk presented by Gowthami Somepalli. Delve into various frameworks for detecting replication and learn about the study that identified memorization in Stable Diffusion 1.4. Examine the factors contributing to memorization in diffusion models, including the often-overlooked role of text conditioning. Discover proposed techniques for reducing data replication during both training and inference times. Gain valuable insights into the complexities of maintaining originality in AI-generated art and graphic design as cutting-edge diffusion models continue to produce high-quality, customizable images for commercial purposes.

Syllabus

Understanding and Mitigating Copying in Diffusion Models


Taught by

Google TechTalks

Related Courses

The New AI Model Licenses Have a Legal Loophole - OpenRAIL-M of BLOOM, Stable Diffusion, etc.
Yannic Kilcher via YouTube
Stable Diffusion - Master AI Art: Installation, Prompts, Txt2img-Img2img, Out-Inpaint and Resize Tutorial
ChamferZone via YouTube
Get Started With Stable Diffusion - Code, HF Spaces, Diffusers Notebooks
Aleksa Gordić - The AI Epiphany via YouTube
Stable Diffusion Animation Tutorial - Deforum All Settings Explained - Make Your Own AI Video
Sebastian Kamph via YouTube
Stable Diffusion - What, Why, How?
Edan Meyer via YouTube