Schedule
Building with Stable Diffusion

Building with Stable Diffusion

Hands-on workshop on Generative AI, Text2Image, Dreambooth, LORA and ControlNet

10:00–10:15

Introduction to Text2Image Models

10:15–10:45

Prompt Engineering (Anatomy & Process)

10:45–11:30

Advance Prompt Engineering (Parameters, Attention Weights, Negative Prompts)

11:30–12:00

Img2img - Stylizing images, mask object removal, object enhancement, in-painting, instruct pix2pix

12:00–13:00

Parameter Tuning using Automatic1111 webUI

13:00–14:00

Lunch Break

14:00–15:00

ControlNet

15:00–15:30

Model Fine Tuning Techniques - Textual Inversion, Dreambooth, LORA, Merging

15:30–16:00

Stylizing using Textual Inversion

16:00–16:50

Model Fine Tuning using LORA

16:50–17:00

QnA

10:00–10:15

Recap Day 1

10:15–11:00

Latent Diffusion Models Theory

11:00–12:00

Text2Image pipeline using Diffusers

12:00–13:00

Serverless model deployment using Replicate

13:00–14:00

Lunch

14:00–15:00

Model fine tuning Deployment

15:00–16:00

Model Inference Deployment

16:00–16:15

Unit Economics of Text2Image Applications

16:15–16:50

Future applications and business opportunities

16:50–17:00

QnA

Hosted by

Generative AI meetup for ChatGPT, Stable Diffusion/DALL-E and related technologies