Photos | Night in the Metropolis
A busy street at night in Tokyo, with a towering building in the background and vehicles speeding past.
BLIP-2 Description:
a street at night with a building in the backgroundChronologically Adjacent
Note: You can also navigate with your arrow keys or swiping.
Metadata
Capture date:
Original Dimensions:
640w x 480h - (download 4k)
Usage
Dominant Color:
Location:
urban building window lane kobe outdoors transportation sidewalk area 法 road outdoor sky tarmac city license traffic land 劑 street japan hardware machine storefront metropolis path bus nature rekognition_c electronics alley vehicle car screen light kiosk monitor night trip darkness town plate nishishinjuku stop 可 computer
flash fired
true
iso
255
metering mode
5
aperture
f/2.9
focal length
6mm
shutter speed
1/30s
camera make
OLYMPUS OPTICAL CO.,LTD
camera model
date
2003-01-07T23:35:51-08:00
tzoffset
-28800
tzname
America/Los_Angeles
overall
(23.06%)
curation
(50.00%)
highlight visibility
(4.36%)
behavioral
(70.47%)
failure
(-2.66%)
harmonious color
(-2.03%)
immersiveness
(2.98%)
interaction
(1.00%)
interesting subject
(-51.86%)
intrusive object presence
(-3.20%)
lively color
(-20.23%)
low light
(99.41%)
noise
(-49.58%)
pleasant camera tilt
(-13.66%)
pleasant composition
(-51.12%)
pleasant lighting
(-70.75%)
pleasant pattern
(9.28%)
pleasant perspective
(-4.60%)
pleasant post processing
(-3.22%)
pleasant reflection
(-7.14%)
pleasant symmetry
(1.05%)
sharply focused subject
(0.12%)
tastefully blurred
(-4.87%)
well chosen subject
(-2.58%)
well framed subject
(-30.13%)
well timed shot
(-1.16%)
all
(-9.58%)
* NOTE: This image was scaled up from its original size using an AI model called GFP-GAN (Generative Facial Prior), which is a
Generative adversartial network that can be used to repair (or upscale in this case) photos, sometimes the results are a little...
weird.
* 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.