Photos | Dinner at the Geek Restaurant
Im Won-hee joins a group of 17 people indoors at a restaurant, surrounded by electronics and artwork.
BLIP-2 Description:
a group of people sitting at tables in a restaurantChronologically Adjacent
Note: You can also navigate with your arrow keys or swiping.
Metadata
Capture date:
Original Dimensions:
4368w x 2912h - (download 4k)
Usage
Dominant Color:
machine room furniture desk floor hardwood im won-hee dining dining room hardware screen 牢 car vehicle lamp projection cafe shoe tv transportation court 孢 indoors accessories bag sign jewelry chair pub srpc glasses 陌 cafeteria footwear building 血 geek architecture food monitor interior table dinner painting restaurant 网 computer flooring handbag bracelet box design door art hat electronics plywood wood
iso
3200
metering mode
5
aperture
f/2.8
focal length
16mm
shutter speed
1/25s
camera make
Canon
camera model
lens model
date
2008-07-15T22:30:23-07:00
tzoffset
-25200
tzname
America/Los_Angeles
overall
(32.28%)
curation
(50.00%)
highlight visibility
(4.36%)
behavioral
(70.59%)
failure
(-0.49%)
harmonious color
(2.75%)
immersiveness
(0.46%)
interaction
(1.00%)
interesting subject
(-54.74%)
intrusive object presence
(-14.31%)
lively color
(-38.72%)
low light
(38.31%)
noise
(-2.32%)
pleasant camera tilt
(-13.61%)
pleasant composition
(-89.16%)
pleasant lighting
(-47.05%)
pleasant pattern
(2.91%)
pleasant perspective
(-6.27%)
pleasant post processing
(0.89%)
pleasant reflection
(-0.40%)
pleasant symmetry
(0.34%)
sharply focused subject
(0.15%)
tastefully blurred
(-16.04%)
well chosen subject
(12.37%)
well framed subject
(-57.62%)
well timed shot
(-4.10%)
all
(-9.57%)
* 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.