LinkedIn
Twitter
Build a Multi-Modal GenAI Application: Challenge Lab (bb-ide-genai-004) solution code
(This challenge lab is part of -"Build Real World AI Applications with Gemini and Imagen" Skill Badge
After executing code wait for few mins to complete Tasks as image will be generated in
#Task 1
=========================================================================
#working code with details
#after Task #1 code executed , see beautiful image (image.jpeg)
# by clicking file under explorer in lab screen.
#-----------------------------------------------------------------
#----------------------------------------------------------------------
#Run below code in Terminal --ex: root@581cced7a969:/home/student#
#=================================================
# Set the PROJECT_ID and REGION variables
#============================================
export PROJECT_ID=$(gcloud config get-value project)
export REGION=$(gcloud compute project-info describe --format="value(commonInstanceMetadata.items[google-compute-default-region])")
#=========================================================
# Task #1 code
#===========================================
cat > GenerateImage.py <<EOF_TASK_ONE
import argparse
import vertexai
from vertexai.preview.vision_models import ImageGenerationModel
def generate_bouquet_image(
project_id: str, location: str, output_file: str, prompt: str
) -> vertexai.preview.vision_models.ImageGenerationResponse:
"""Generate an image using a text prompt.
Args:
project_id: Google Cloud project ID, used to initialize Vertex AI.
location: Google Cloud region, used to initialize Vertex AI.
output_file: Local path to the output image file.
prompt: The text prompt describing what you want to see."""
vertexai.init(project=project_id, location=location)
model = ImageGenerationModel.from_pretrained("imagen-3.0-generate-002")
images = model.generate_images(
prompt=prompt,
# Optional parameters
number_of_images=1,
seed=1,
add_watermark=False,
)
images[0].save(location=output_file)
return images
generate_bouquet_image(
project_id='$PROJECT_ID',
location='$REGION',
output_file='image.jpeg',
prompt='Create an image containing a bouquet of 2 sunflowers and 3 roses',
)
EOF_TASK_ONE
#=========================================
# below command executes GenerateImage.py
/usr/bin/python3 GenerateImage.py
#========================================
#Task #2 code
#==============================================
cat > Gentext.py <<EOF_TASK_TWO
import vertexai
from vertexai.generative_models import GenerativeModel, Part, Image
def analyze_bouquet_image(project_id: str, location: str) -> str:
vertexai.init(project=project_id, location=location)
multimodal_model = GenerativeModel("gemini-2.0-flash-001")
response = multimodal_model.generate_content(
[
Part.from_image(Image.load_from_file("image.jpeg")
),
"Generate birthday wishes based on this image?",
]
)
return response.text
project_id = "$PROJECT_ID"
location = "$REGION"
response = analyze_bouquet_image(project_id, location)
print(response)
EOF_TASK_TWO
#=========================================
# below command executes Gentext.py
/usr/bin/python3 Gentext.py
#======end of code===============================
-------------------------------------------------------------------------------------------------------------
Screen shot of image,(Task #1) birthday wishes (Task#2) , 100/100 score
-------------------------------------------------------------------------------------------------------
