Photos | Urban Metropolis
Lu Haojie walks among a crowd of 65 people, sporting shorts and headgear in the bustling city streets. The scene is set with posters, banners, and tents.
BLIP-2 Description:
a crowd of people walking down a streetChronologically Adjacent
Note: You can also navigate with your arrow keys or swiping.
Metadata
Capture date:
Original Dimensions:
3504w x 2336h - (download 4k)
Usage
bracelet headgear boy necklace urban sponsor fence baseball child footwear cap pedestrian tickets tent hat wristwatch sidewalk field la outdoor road scrip sky city bag shoe restiva party street shirt mel glasses poster shorts metropolis path tofu banner sign sunglasses jewelry block accessories market handbag walking plate part lu haojie back advertisement crowd undershirt
iso
100
metering mode
5
aperture
f/4
exposure bias
-0.67
focal length
17mm
shutter speed
1/1250s
camera make
Canon
camera model
lens model
date
2006-08-14T10:40:48-07:00
tzoffset
-25200
tzname
America/Los_Angeles
overall
(25.12%)
curation
(50.00%)
highlight visibility
(4.51%)
behavioral
(90.74%)
failure
(-0.46%)
harmonious color
(-0.81%)
immersiveness
(0.24%)
interaction
(1.00%)
interesting subject
(-51.71%)
intrusive object presence
(-8.54%)
lively color
(-8.80%)
low light
(30.42%)
noise
(-3.69%)
pleasant camera tilt
(-7.79%)
pleasant composition
(-87.35%)
pleasant lighting
(-50.24%)
pleasant pattern
(5.00%)
pleasant perspective
(-2.76%)
pleasant post processing
(-2.70%)
pleasant reflection
(0.56%)
pleasant symmetry
(0.22%)
sharply focused subject
(0.20%)
tastefully blurred
(-9.12%)
well chosen subject
(-4.33%)
well framed subject
(-71.00%)
well timed shot
(9.02%)
all
(-8.37%)
* 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.