Photos | A Night Out with Friends

Mancho G and Dave B sit with four friends at a table inside a Tbilisi restaurant, surrounded by dining furniture, interior room decor, and consumer electronics while enjoying drinks and good company.
BLIP-2 Description:
a group of people sitting at a table with drinksMetadata
Capture date:
Original Dimensions:
1280w x 960h - (download 4k)
Usage
Dominant Color:
Location:
building beverage optical photography glass restaurant linen furniture cutlery dining speakers meal dining room diner lager couch speaker mobile beer phone decor liquor party equipment table wristwatch architecture indoors dave b g consumer urban glasses spoon fun selfie interior accessories cafeteria mancho portrait music dinner tableware room alcohol eyeglasses dish pub home cup bar drinking glass food counter electronics utensil machine
iso
1000
metering mode
5
aperture
f/2.2
focal length
3mm
latitude
41.69
longitude
44.81
shutter speed
1/15s
camera make
Apple
camera model
lens model
overall
(34.50%)
curation
(68.42%)
highlight visibility
(5.92%)
behavioral
(90.71%)
failure
(-0.68%)
harmonious color
(-0.84%)
immersiveness
(0.05%)
interaction
(1.00%)
interesting subject
(25.34%)
intrusive object presence
(-3.96%)
lively color
(-10.35%)
low light
(57.18%)
noise
(-27.08%)
pleasant camera tilt
(-1.92%)
pleasant composition
(-34.30%)
pleasant lighting
(-42.24%)
pleasant pattern
(5.93%)
pleasant perspective
(-0.42%)
pleasant post processing
(4.80%)
pleasant reflection
(-3.24%)
pleasant symmetry
(0.20%)
sharply focused subject
(0.54%)
tastefully blurred
(-9.65%)
well chosen subject
(-49.95%)
well framed subject
(-0.23%)
well timed shot
(-4.45%)
all
(-5.46%)
* NOTE: This image was scaled up from its original size using an AI model called GFP-GAN (Generative Facial Prior), which is a
Generative adversartial network that can be used to repair (or upscale in this case) photos, sometimes the results are a little...
weird.
* WARNING: The title and caption of this image were generated with AI (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.