Photos | A Metropolis Illuminated
The Tokyo Metropolitan Government Office in Shinjuku, Tokyo, Japan, lights up the night sky in this bustling urban landscape, punctuated by billboards, shops, and a shopping mall. A few cars drive on the road below, while four people stroll the brightly-lit street.
BLIP-2 Description:
a large building with many lightsChronologically 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:
city car high rise outdoors rekognition_c night sky neighborhood downtown sky land area lighting office trip advertisement corner building metropolis tarmac road japan metropolitan nishishinjuku mall shinjuku transportation life nature outdoor shopping urban pal light street billboards vehicle shop architecture night intersection sign
Detected Text
flash fired
true
metering mode
5
aperture
f/2.5
focal length
6mm
shutter speed
1/30s
camera make
CASIO COMPUTER CO.,LTD.
camera model
overall
(41.53%)
curation
(50.00%)
highlight visibility
(4.36%)
behavioral
(70.59%)
failure
(-0.68%)
harmonious color
(1.67%)
immersiveness
(0.44%)
interaction
(1.00%)
interesting subject
(-45.63%)
intrusive object presence
(-2.25%)
lively color
(-16.74%)
low light
(99.90%)
noise
(-11.28%)
pleasant camera tilt
(-9.66%)
pleasant composition
(-46.75%)
pleasant lighting
(-43.95%)
pleasant pattern
(5.03%)
pleasant perspective
(19.12%)
pleasant post processing
(7.16%)
pleasant reflection
(-3.76%)
pleasant symmetry
(1.86%)
sharply focused subject
(0.27%)
tastefully blurred
(-23.28%)
well chosen subject
(10.88%)
well framed subject
(-11.49%)
well timed shot
(5.68%)
all
(-1.37%)
* 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.