Photos | Lunchtime at the Sidewalk Cart
Zhang Juanjuan serves a meal to a group of 11 people, including a young boy, at his food cart in the city.
BLIP-2 Description:
a man standing next to a cart with foodChronologically Adjacent
Note: You can also navigate with your arrow keys or swiping.
Metadata
Capture date:
Original Dimensions:
4368w x 2912h - (download 4k)
Usage
tool cafeteria headgear boy urban baseball meal food shovel child footwear cap buffet dish pickup transportation sidewalk hat zhang juanjuan restaurant road outdoor tarmac bag shoe gun city land eating street grilling machine truck cooking indoors lunch path wheel bbq car vehicle kiosk accessories musical instrument presentation fast device automobile guitar walkabout handbag undershirt weapon box
iso
100
metering mode
5
aperture
f/2.8
focal length
16mm
shutter speed
1/1000s
camera make
Canon
camera model
lens model
date
2008-02-29T12:34:51-08:00
tzoffset
-28800
tzname
America/Los_Angeles
overall
(40.28%)
curation
(50.00%)
highlight visibility
(4.36%)
behavioral
(70.68%)
failure
(-0.20%)
harmonious color
(-0.74%)
immersiveness
(0.42%)
interaction
(1.00%)
interesting subject
(-9.31%)
intrusive object presence
(-10.67%)
lively color
(-8.41%)
low light
(8.67%)
noise
(-2.34%)
pleasant camera tilt
(-3.98%)
pleasant composition
(-47.41%)
pleasant lighting
(-13.05%)
pleasant pattern
(2.03%)
pleasant perspective
(9.66%)
pleasant post processing
(-0.99%)
pleasant reflection
(1.31%)
pleasant symmetry
(0.44%)
sharply focused subject
(1.68%)
tastefully blurred
(-5.93%)
well chosen subject
(-41.97%)
well framed subject
(31.10%)
well timed shot
(15.43%)
all
(-0.64%)
* 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.