Photos | Karen's Cozy Living Room
Karen Maruyama cozies up on her couch with her favorite art pieces and two massive television screens in her San Francisco living room.
BLIP-2 Description:
a living room with a tv and a couchChronologically 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:
Location:
architecture civic bracelet building frame chair mobile furniture rug flooring design art photo frame karen television hardware machine desk shelf indoors pc interior rekognition_c electronics maruyama theater living room jewelry screen table room accessories monitor couch lighting laptop home center tv phone entertainment decor floor computer painting consumer
iso
2000
metering mode
3
aperture
f/2.4
focal length
2mm
latitude
37.78
longitude
-122.42
shutter speed
1/15s
camera make
Apple
camera model
date
2020-04-21T21:57:00.654000-07:00
tzoffset
-25200
tzname
GMT-0700
overall
(32.06%)
curation
(50.00%)
highlight visibility
(4.36%)
behavioral
(70.59%)
failure
(-0.46%)
harmonious color
(3.43%)
immersiveness
(1.78%)
interaction
(1.00%)
interesting subject
(-27.93%)
intrusive object presence
(-12.11%)
lively color
(-17.57%)
low light
(68.31%)
noise
(-1.37%)
pleasant camera tilt
(-10.94%)
pleasant composition
(-46.88%)
pleasant lighting
(-39.45%)
pleasant pattern
(7.93%)
pleasant perspective
(-0.29%)
pleasant post processing
(-7.58%)
pleasant reflection
(0.51%)
pleasant symmetry
(0.85%)
sharply focused subject
(0.24%)
tastefully blurred
(-12.95%)
well chosen subject
(-16.24%)
well framed subject
(-31.30%)
well timed shot
(2.21%)
all
(-5.05%)
* 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.