Photos | Lunch at the Restaurant
Graham Clark and Sandra Alland join a group of 17 people for lunch at a bustling restaurant during the NCRC weekend 2. The wooden table is adorned with 2 cups and 3 glasses while the group sit on various chairs, including 2 men in hats. Two cars are parked outside the cafe as shelter from the summer heat.
BLIP-2 Description:
a group of people sitting around a tableMetadata
Capture date:
Original Dimensions:
5616w x 3744h - (download 4k)
Usage
Dominant Color:
pc weekend box wood search restaurant rescue transportation glasses sandra house footwear bag court interior food cafeteria housing chair bench ncrc plywood automobile car alland table building electronics shoe handbag outdoors desk john room graham clark cafe cup vehicle architecture machine hat furniture patio accessories dining laptop indoors computer shelter
iso
400
metering mode
5
aperture
f/8
exposure bias
-2.33
focal length
16mm
shutter speed
1/400s
camera make
Canon
camera model
lens model
overall
(17.74%)
curation
(65.00%)
highlight visibility
(5.50%)
behavioral
(70.69%)
failure
(-0.76%)
harmonious color
(-3.47%)
immersiveness
(0.61%)
interaction
(1.00%)
interesting subject
(-72.56%)
intrusive object presence
(-7.23%)
lively color
(-11.07%)
low light
(94.14%)
noise
(-1.71%)
pleasant camera tilt
(-14.10%)
pleasant composition
(-86.08%)
pleasant lighting
(-67.92%)
pleasant pattern
(10.52%)
pleasant perspective
(-20.48%)
pleasant post processing
(-6.52%)
pleasant reflection
(1.87%)
pleasant symmetry
(0.27%)
sharply focused subject
(0.15%)
tastefully blurred
(-2.61%)
well chosen subject
(-20.81%)
well framed subject
(-66.50%)
well timed shot
(-9.46%)
all
(-14.20%)
* NOTE: Amazon Rekognition
detected a celebrity in this image using the
Celebrity Recognition API. The API isn't perfect, but it does give you the MatchConfidence which I display
next to the celebrity's name along with links _↗ to their info.
* WARNING: The title and caption of this image were generated by an AI LLM (gpt-3.5-turbo-0301
from
OpenAI)
based on a
BLIP-2 image-to-text labeling, tags,
location,
people
and album metadata from the image and are
potentially inaccurate, often hilariously so. If you'd like me to adjust anything,
just reach out.