Photos | A Convivial Evening in Korea
Famed director Cheang Pou-soi with friends, engaged in hearty conversations over dinner in a welcoming Korean restaurant (March, 2024). The table is abuzz with local cuisine, craft beer, and shared laughter, underscoring the beautiful fusion of tradition, culinary exploration and camaraderie.
BLIP-2 Description:
a group of people sitting at a table with drinksMetadata
Capture date:
Original Dimensions:
6000w x 4000h - (download 4k)
Usage
Dominant Color:
couch wood cheang pou-soi plate restaurant glasses stew eek dinner bread court teen interior food cafeteria container hardware drinking table building korea lunch pub goblet tableware electronics dining table boy glass shaker room dish screen cup beverage tabletop architecture meal utensil beer bottle furniture alcohol accessories dining monitor indoors computer part
iso
16000
metering mode
5
aperture
f/2.8
focal length
28mm
shutter speed
1/640s
camera make
Canon
camera model
lens model
overall
(43.46%)
curation
(50.00%)
highlight visibility
(3.82%)
behavioral
(70.44%)
failure
(-0.22%)
harmonious color
(2.92%)
immersiveness
(0.07%)
interaction
(1.00%)
interesting subject
(26.32%)
intrusive object presence
(-45.92%)
lively color
(-29.35%)
low light
(20.87%)
noise
(-1.93%)
pleasant camera tilt
(-5.91%)
pleasant composition
(-83.64%)
pleasant lighting
(-15.50%)
pleasant pattern
(0.85%)
pleasant perspective
(12.47%)
pleasant post processing
(-1.34%)
pleasant reflection
(-1.73%)
pleasant symmetry
(0.29%)
sharply focused subject
(1.22%)
tastefully blurred
(-14.14%)
well chosen subject
(-21.52%)
well framed subject
(28.56%)
well timed shot
(16.56%)
all
(-3.33%)
* 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-4-0613
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.