Build with AI
on Google Cloud
Session #1 Intro to GenAI
1/22/2025
Seattle | Surrey | Vancouver | Burnaby
GDG Seattle
2
Margaret Maynard-Reid
Yenchi Lin
Clive Boulton
Vishal Pallerla
I/O Extended 2019
2024 Build with AI
DevFest Seattle 2018
DevFest Seattle 2022
WTM Lightning Talks 2018
Cloud Study Jam 2018
DevFest Seattle 2017
DevFest Seattle 2016
DevFest Seattle 2015
DevFest Seattle 2024
Follow GDG Seattle on LinkedIn
GDG Surrey
3
Follow GDG Surrey on LinkedIn
GDG Vancouver
Follow GDG Seattle on LinkedIn
4
Follow GDG Vancouver on LinkedIn
Join our GDG Vancouver Community
Volunteer Interest Form
GDG Burnaby
GDG Burnaby Bevy | LinkedIn
5
Build with AI
on Google Cloud
Agenda
● Study series overview
● Cloud Skills Boost walkthrough
● CSB beginner path repris
● Intro to GenAI on Google Cloud
● Prompt Design
● Q & A - 20 min
Seattle | Surrey | Vancouver | Burnaby
Build with AI
on Google Cloud
Study series
overview
7
Topics for this session
● Online study series overview
● Intro to GenAI on Google Cloud
● GenAI beginner path
● …
8
9
Link to Story on Medium
Study series overview
Follow 5 generative AI paths on Google Cloud Skills Boost:
1. 1/22/25 - Beginner: Intro to GenAI (link)
2. 2/5/25 - Generate Smarter GenAI Outputs (link)
3. 2/19/25 - Build & Modernize Apps with GenAI (link)
4. 3/5/25 - Integrate GenAI into Your DataFlow (link)
5. 3/19/25 - Deploy & Manage GenAI Models (link)
Topics are not limited to the above.
Each session: 2 short talks (by Googlers or experts) + Q&A section.
10
What is a learning path?
A learning path has multiple courses
Each course has videos, recommended reading, quiz & hands-on labs.
You will have at least two weeks to work through the materials
It’s OK if you don’t finish and feel free to study ahead
11
Access to Cloud Skills Boost
● Sign up here: https://www.cloudskillsboost.google/
● By RSVP, you get free access for a few months
● The videos are accessible by default while labs each require a credit
● You can work on each GenAI paths before or after each session
Note: Make sure to sign up on Google Cloud Skills Boost with the same email that you used
for event RSVP.
12
Build with AI
on Google Cloud
Cloud Skills Boost
walkthrough
13
14
Sign In -Google Cloud Skills Boost
15
Explore Paths
Build with AI
on Google Cloud
Beginner:
Intro to GenAI
Learning Path
16
5 courses in the learning path
17
1. Intro to Generative AI (45 minutes)
2. Intro to LLMs (1 hour)
3. Intro to Responsible AI (30 minutes)
4. Prompt Design in Vertex AI (3 hours 45 minutes)
5. Responsible AI: Applying AI Principals with Google Cloud (2 hours)
1. Intro to generative AI
● AI vs ML vs deep learning
● What is Generative AI? LLMs and generative Image models…
● Supervised vs unsupervised learning
18
2. Intro to LLM
19
3. Intro to Responsible AI
20
4. Prompt Design
21
5. Responsible AI: Applying AI Principles with GCloud
1. Be socially beneficial
2. Avoid creating or reinforcing unfair bias
3. Be built and tested for safety
4. Be accountable to people
5. Incorporate privacy design principles
6. Uphold high standards of scientific excellence
7. Be made available for uses that accord with these principles
22
Build with AI
on Google Cloud
Intro to GenAI
Margaret Maynard-Reid, AI/ML GDE
23
AI/ML GDE (Google Developer Expert)
3D artist
Fashion Designer
Instructor of MSIS, UW Foster
Ex MS Design Studio, MSR, MS Bing
About me
margaretmz.art
24
AI, ML, Deep Learning & GenAI
Artificial Intelligence
Machine Learning
Deep Learning
25
25
Generative AI
What is Generative AI?
A type of AI that creates new content with generative models:
26
Text
Image
Video
Audio
Generative AI
Text
Image
Video
Audio
What are Generative Models?
“Generative models: take a machine, observe many samples
from a distribution and generate more samples from that
same distribution”.
- Ian Goodfellow 2016
27
What is
an LLM?
LLMs Explained
[...] [...] [...]
[...]
0.02
0.03
0.9 0.01 0.0 …
Dogs Rain Drops Fish Wind …
and
cats
raining
It’s
Type of Generative Models
● 2014 Generative Adversarial
Networks (GANs)
● 2016 Autoregressive Models
● 2019 Variational autoencoders
(VAEs)
● Flow-based models
● 2020 Diffusion models
● 2022 Diffusion Transformer
29
Source: Lilian Weng blog (link)
Diffusion Models
1. Gradually add gaussian
noise to training data
2. Learn how to reverse the
process to generate
images from noise.
30
Source: Nvidia developer blog (link)
Forward image diffusion
Generative reverse denoise
CLIP: Contrastive Language-Image Pre-training
CLIP is a bridge between NLP and computer
vision, connecting text and Images
It has a text encoder and image encoder,
trained with 400 million image-text pairs.
● DALLE, DALLE-2
● Stable Diffusion
● Imagen, Imagen 2, Imagen 3
Paper: Learning Transferable Visual Models From
Natural Language Supervision
31
Diffusion Transformer
Paper: Scalable Diffusion Models with
Transformers
SoTA models using diffusion
transformer:
● Pixart-a
● SORA
● Stable Diffusion 3
32
The U-Net
33
U-Net architecture (image source: U-Net paper)
2015 paper for medical
imaging segmentation
Used in many popular GenAI
models:
● Pix2Pix
● CycleGAN
● Diffusion Models (DDPM)
● DALL-E
● Midjourney
● Stable Diffusion…
U-Net vs Diffusion Transformer
U-Net
- not crucial to the good
performance of the
diffusion model
- struggle with capturing
long-range dependencies and
global context in the input
data
Diffusion Transformer
- More flexible
- Can use more training data
and larger model parameters
- Transformers can model
long-range dependencies
without the need for deep
networks or large filters,
because of the
self-attention mechanisms
34
Timeline: generative AI in vision
Source: Sora paper
35
Imagen 3
Veo/VideoFX
Thank you!
Connect with me learn more about AI, art & design!
@margaretmz
@margaretmz
@margaretmz
@margaretmz
36
Build with AI
on Google Cloud Prompt Design - By Priti Y.
37
What is Prompt Design?
Prompt Design Workflow
38
Define Objectives and Expected
Outcomes
Create the Prompt Content, Structure,
Components
Test the
Prompt
Identify Areas for Improvement
Refine
Iterate
Iterate
The Components of a Prompt
● Define the Task
● Contextual Information
● Include Few-Shot Examples
● System Instructions
39
Common Pitfalls in Prompt Design
● Vague Instructions
● Not Providing Enough Context
● Poorly Structured Prompts
● Not Using Examples
● Not Assigning a Role or Persona
● Not Breaking Down Complex Tasks
● Not Specifying the Output Format
● Not Iterating on Prompts
● Not Experimenting with Parameters
40
Best Practices for Designing Prompts
● Assign a Role
● Structure Prompts
● Instruct the Model to Explain its Reasoning
● Break Down Complex Tasks
● Experiment with Parameter Values
● Specify the Output Format
● Optimize Image Prompts
● Tailor for Task Type
● Consider the Model’s Limitations
41
Demo
Prompt Design in Vertex AI
42
Thank you!
Let's connect to explore AI Projects/Research and Board Games together!
43
@pritiyadav888
@mentors/priti-yadav
Build with AI
on Google Cloud
Q&A
44
More questions?
Post them on GDG Surrey
Discord server #gen_ai_gcp
45
Scan Me
Have fun studying!
Action items:
● Join discord - post your questions there
● Get access to Cloud Skills Boost credits
● Complete Beginner GenAI path on CSB
● Get started on the 2nd GenAI path on CSB
Next session:
● Feb 5, 2025 - Session #2 - Deep Dive (RSVP)
46

Build with AI on Google Cloud Session #1

  • 1.
    Build with AI onGoogle Cloud Session #1 Intro to GenAI 1/22/2025 Seattle | Surrey | Vancouver | Burnaby
  • 2.
    GDG Seattle 2 Margaret Maynard-Reid YenchiLin Clive Boulton Vishal Pallerla I/O Extended 2019 2024 Build with AI DevFest Seattle 2018 DevFest Seattle 2022 WTM Lightning Talks 2018 Cloud Study Jam 2018 DevFest Seattle 2017 DevFest Seattle 2016 DevFest Seattle 2015 DevFest Seattle 2024 Follow GDG Seattle on LinkedIn
  • 3.
    GDG Surrey 3 Follow GDGSurrey on LinkedIn
  • 4.
    GDG Vancouver Follow GDGSeattle on LinkedIn 4 Follow GDG Vancouver on LinkedIn Join our GDG Vancouver Community Volunteer Interest Form
  • 5.
    GDG Burnaby GDG BurnabyBevy | LinkedIn 5
  • 6.
    Build with AI onGoogle Cloud Agenda ● Study series overview ● Cloud Skills Boost walkthrough ● CSB beginner path repris ● Intro to GenAI on Google Cloud ● Prompt Design ● Q & A - 20 min Seattle | Surrey | Vancouver | Burnaby
  • 7.
    Build with AI onGoogle Cloud Study series overview 7
  • 8.
    Topics for thissession ● Online study series overview ● Intro to GenAI on Google Cloud ● GenAI beginner path ● … 8
  • 9.
    9 Link to Storyon Medium
  • 10.
    Study series overview Follow5 generative AI paths on Google Cloud Skills Boost: 1. 1/22/25 - Beginner: Intro to GenAI (link) 2. 2/5/25 - Generate Smarter GenAI Outputs (link) 3. 2/19/25 - Build & Modernize Apps with GenAI (link) 4. 3/5/25 - Integrate GenAI into Your DataFlow (link) 5. 3/19/25 - Deploy & Manage GenAI Models (link) Topics are not limited to the above. Each session: 2 short talks (by Googlers or experts) + Q&A section. 10
  • 11.
    What is alearning path? A learning path has multiple courses Each course has videos, recommended reading, quiz & hands-on labs. You will have at least two weeks to work through the materials It’s OK if you don’t finish and feel free to study ahead 11
  • 12.
    Access to CloudSkills Boost ● Sign up here: https://www.cloudskillsboost.google/ ● By RSVP, you get free access for a few months ● The videos are accessible by default while labs each require a credit ● You can work on each GenAI paths before or after each session Note: Make sure to sign up on Google Cloud Skills Boost with the same email that you used for event RSVP. 12
  • 13.
    Build with AI onGoogle Cloud Cloud Skills Boost walkthrough 13
  • 14.
    14 Sign In -GoogleCloud Skills Boost
  • 15.
  • 16.
    Build with AI onGoogle Cloud Beginner: Intro to GenAI Learning Path 16
  • 17.
    5 courses inthe learning path 17 1. Intro to Generative AI (45 minutes) 2. Intro to LLMs (1 hour) 3. Intro to Responsible AI (30 minutes) 4. Prompt Design in Vertex AI (3 hours 45 minutes) 5. Responsible AI: Applying AI Principals with Google Cloud (2 hours)
  • 18.
    1. Intro togenerative AI ● AI vs ML vs deep learning ● What is Generative AI? LLMs and generative Image models… ● Supervised vs unsupervised learning 18
  • 19.
  • 20.
    3. Intro toResponsible AI 20
  • 21.
  • 22.
    5. Responsible AI:Applying AI Principles with GCloud 1. Be socially beneficial 2. Avoid creating or reinforcing unfair bias 3. Be built and tested for safety 4. Be accountable to people 5. Incorporate privacy design principles 6. Uphold high standards of scientific excellence 7. Be made available for uses that accord with these principles 22
  • 23.
    Build with AI onGoogle Cloud Intro to GenAI Margaret Maynard-Reid, AI/ML GDE 23
  • 24.
    AI/ML GDE (GoogleDeveloper Expert) 3D artist Fashion Designer Instructor of MSIS, UW Foster Ex MS Design Studio, MSR, MS Bing About me margaretmz.art 24
  • 25.
    AI, ML, DeepLearning & GenAI Artificial Intelligence Machine Learning Deep Learning 25 25 Generative AI
  • 26.
    What is GenerativeAI? A type of AI that creates new content with generative models: 26 Text Image Video Audio Generative AI Text Image Video Audio
  • 27.
    What are GenerativeModels? “Generative models: take a machine, observe many samples from a distribution and generate more samples from that same distribution”. - Ian Goodfellow 2016 27
  • 28.
    What is an LLM? LLMsExplained [...] [...] [...] [...] 0.02 0.03 0.9 0.01 0.0 … Dogs Rain Drops Fish Wind … and cats raining It’s
  • 29.
    Type of GenerativeModels ● 2014 Generative Adversarial Networks (GANs) ● 2016 Autoregressive Models ● 2019 Variational autoencoders (VAEs) ● Flow-based models ● 2020 Diffusion models ● 2022 Diffusion Transformer 29 Source: Lilian Weng blog (link)
  • 30.
    Diffusion Models 1. Graduallyadd gaussian noise to training data 2. Learn how to reverse the process to generate images from noise. 30 Source: Nvidia developer blog (link) Forward image diffusion Generative reverse denoise
  • 31.
    CLIP: Contrastive Language-ImagePre-training CLIP is a bridge between NLP and computer vision, connecting text and Images It has a text encoder and image encoder, trained with 400 million image-text pairs. ● DALLE, DALLE-2 ● Stable Diffusion ● Imagen, Imagen 2, Imagen 3 Paper: Learning Transferable Visual Models From Natural Language Supervision 31
  • 32.
    Diffusion Transformer Paper: ScalableDiffusion Models with Transformers SoTA models using diffusion transformer: ● Pixart-a ● SORA ● Stable Diffusion 3 32
  • 33.
    The U-Net 33 U-Net architecture(image source: U-Net paper) 2015 paper for medical imaging segmentation Used in many popular GenAI models: ● Pix2Pix ● CycleGAN ● Diffusion Models (DDPM) ● DALL-E ● Midjourney ● Stable Diffusion…
  • 34.
    U-Net vs DiffusionTransformer U-Net - not crucial to the good performance of the diffusion model - struggle with capturing long-range dependencies and global context in the input data Diffusion Transformer - More flexible - Can use more training data and larger model parameters - Transformers can model long-range dependencies without the need for deep networks or large filters, because of the self-attention mechanisms 34
  • 35.
    Timeline: generative AIin vision Source: Sora paper 35 Imagen 3 Veo/VideoFX
  • 36.
    Thank you! Connect withme learn more about AI, art & design! @margaretmz @margaretmz @margaretmz @margaretmz 36
  • 37.
    Build with AI onGoogle Cloud Prompt Design - By Priti Y. 37 What is Prompt Design?
  • 38.
    Prompt Design Workflow 38 DefineObjectives and Expected Outcomes Create the Prompt Content, Structure, Components Test the Prompt Identify Areas for Improvement Refine Iterate Iterate
  • 39.
    The Components ofa Prompt ● Define the Task ● Contextual Information ● Include Few-Shot Examples ● System Instructions 39
  • 40.
    Common Pitfalls inPrompt Design ● Vague Instructions ● Not Providing Enough Context ● Poorly Structured Prompts ● Not Using Examples ● Not Assigning a Role or Persona ● Not Breaking Down Complex Tasks ● Not Specifying the Output Format ● Not Iterating on Prompts ● Not Experimenting with Parameters 40
  • 41.
    Best Practices forDesigning Prompts ● Assign a Role ● Structure Prompts ● Instruct the Model to Explain its Reasoning ● Break Down Complex Tasks ● Experiment with Parameter Values ● Specify the Output Format ● Optimize Image Prompts ● Tailor for Task Type ● Consider the Model’s Limitations 41
  • 42.
  • 43.
    Thank you! Let's connectto explore AI Projects/Research and Board Games together! 43 @pritiyadav888 @mentors/priti-yadav
  • 44.
    Build with AI onGoogle Cloud Q&A 44
  • 45.
    More questions? Post themon GDG Surrey Discord server #gen_ai_gcp 45 Scan Me
  • 46.
    Have fun studying! Actionitems: ● Join discord - post your questions there ● Get access to Cloud Skills Boost credits ● Complete Beginner GenAI path on CSB ● Get started on the 2nd GenAI path on CSB Next session: ● Feb 5, 2025 - Session #2 - Deep Dive (RSVP) 46