Photos | Dinner With Friends

Camille Hurel enjoying a night out with two friends at a restaurant in Tbilisi, Georgia. The table is adorned with beautiful tableware and glasses, and the women are surrounded by cozy furniture and warm light.
BLIP-2 Description:
two women sitting at a tableMetadata
Capture date:
Original Dimensions:
2448w x 3264h - (download 4k)
Usage
Dominant Color:
Location:
machine room couch furniture decor dining consumer hardware screen table lamp part lamp home child glass linen court girl indoors accessories beverage ring jewelry pub plate building cafeteria architecture necklace goblet food monitor beer counter utensil interior bar table light mobile cup phone restaurant alcohol meal camille hurel computer drinking glass bracelet wine saucer electronics tableware
iso
500
metering mode
5
aperture
f/2.2
focal length
4mm
latitude
41.69
longitude
44.81
shutter speed
1/15s
camera make
Apple
camera model
lens model
date
2015-05-09T00:47:41.878000+04:00
tzoffset
14400
tzname
Asia/Tbilisi
overall
(25.59%)
curation
(50.00%)
highlight visibility
(4.36%)
behavioral
(70.64%)
failure
(-0.46%)
harmonious color
(1.16%)
immersiveness
(0.05%)
interaction
(1.00%)
interesting subject
(-56.10%)
intrusive object presence
(-5.79%)
lively color
(-25.42%)
low light
(47.34%)
noise
(-2.32%)
pleasant camera tilt
(-3.42%)
pleasant composition
(-79.10%)
pleasant lighting
(-53.81%)
pleasant pattern
(0.95%)
pleasant perspective
(4.26%)
pleasant post processing
(0.79%)
pleasant reflection
(-2.84%)
pleasant symmetry
(0.15%)
sharply focused subject
(0.27%)
tastefully blurred
(-19.87%)
well chosen subject
(-40.01%)
well framed subject
(-9.63%)
well timed shot
(3.33%)
all
(-10.18%)
* 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.