Photos | Late Night Shopping
Tomoaki Satoh and others stand outside a brightly-lit storefront, checking their phones and chatting on a chilly November evening in 2008.
BLIP-2 Description:
people standing outside of a store at nightMetadata
Capture date:
Original Dimensions:
4368w x 2912h - (download 4k)
Usage
Dominant Color:
bodypirong advertisement urban box storefront gun canvas lamp phone flooring wood rekognition_c restaurant architectural materials transportation glasses outdoor poster mobile footwear raw bag path necklace floor cafeteria show city plywood car jewelry carton shop sidewalk building lighting sign electronics shoe handbag back coat kiosk tomoaki srpc cardboard plant cafe metropolis vehicle weapon satoh overcoat sale accessories supplies indoors chitectural walkway art part
Detected Text
iso
3200
metering mode
5
aperture
f/2.8
focal length
16mm
shutter speed
1/200s
camera make
Canon
camera model
lens model
overall
(33.42%)
curation
(50.00%)
highlight visibility
(4.51%)
behavioral
(90.81%)
failure
(-0.37%)
harmonious color
(1.55%)
immersiveness
(0.46%)
interaction
(1.00%)
interesting subject
(-44.26%)
intrusive object presence
(-11.16%)
lively color
(-22.77%)
low light
(69.14%)
noise
(-3.32%)
pleasant camera tilt
(-11.63%)
pleasant composition
(-76.81%)
pleasant lighting
(-42.48%)
pleasant pattern
(6.69%)
pleasant perspective
(-8.86%)
pleasant post processing
(2.44%)
pleasant reflection
(-1.67%)
pleasant symmetry
(0.44%)
sharply focused subject
(0.29%)
tastefully blurred
(-4.75%)
well chosen subject
(-13.57%)
well framed subject
(-47.41%)
well timed shot
(-8.29%)
all
(-8.75%)
* 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.