Photos | Rooftop Groupshot in the City
Masamune Wada and Kevin H join a crowd of 18 people on a rooftop, smiling for a photo in front of a towering skyscraper on a sunny day in August 2017.
BLIP-2 Description:
a group of people posing for a photo on a rooftopChronologically Adjacent
Note: You can also navigate with your arrow keys or swiping.
Metadata
Capture date:
Original Dimensions:
3024w x 4032h - (download 4k)
Usage
Dominant Color:
architecture summer jeans pants necklace urban building masamune wada footwear kevin wristwatch hat apple ml furniture outdoor sky plus shoe bag city groupshot iphone bench blue glasses belt llttii metropolis construction jewelry college ham accessories skyscraper office crane handbag august couch photography smile happy crowd apple
iso
20
metering mode
5
aperture
f/1.8
focal length
4mm
shutter speed
1/1244s
camera make
Apple
camera model
lens model
date
2017-08-21T10:22:56.516000-07:00
tzoffset
-25200
tzname
America/Los_Angeles
overall
(57.57%)
curation
(50.00%)
highlight visibility
(2.60%)
behavioral
(90.88%)
failure
(-0.12%)
harmonious color
(4.21%)
immersiveness
(1.03%)
interaction
(2.00%)
interesting subject
(58.25%)
intrusive object presence
(-1.49%)
lively color
(30.18%)
low light
(0.93%)
noise
(-0.56%)
pleasant camera tilt
(-1.64%)
pleasant composition
(0.29%)
pleasant lighting
(8.22%)
pleasant pattern
(19.73%)
pleasant perspective
(7.47%)
pleasant post processing
(-0.98%)
pleasant reflection
(0.33%)
pleasant symmetry
(0.66%)
sharply focused subject
(0.90%)
tastefully blurred
(1.86%)
well chosen subject
(-20.89%)
well framed subject
(26.07%)
well timed shot
(-4.48%)
all
(7.89%)
* 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.