Photos | Night Out with Friends
A group of ten people, including six women and four men, enjoying drinks and conversation at a pub. They sit around a dining table with tableware and utensils while surrounded by furniture, including a bar counter and two chairs. The crowd and the alcohol add to the buoyant atmosphere of the restaurant.
BLIP-2 Description:
a group of people sitting at a table with drinksChronologically Adjacent
Note: You can also navigate with your arrow keys or swiping.
Metadata
Capture date:
Original Dimensions:
480w x 640h - (download 4k)
Usage
Dominant Color:
architecture bracelet glass cafeteria bride tableware bartender pub building defcon chair bar footwear beverage wedding microphone hat restaurant furniture counter utensil container shoe alcohol club junglescene indoors glasses dining jewelry table accessories room night device crowd bottle electrical
Detected Text
date
2002-08-29T14:46:29-07:00
tzoffset
-25200
tzname
America/Los_Angeles
overall
(20.34%)
curation
(50.00%)
highlight visibility
(4.36%)
behavioral
(70.61%)
failure
(-1.59%)
harmonious color
(-0.87%)
immersiveness
(0.37%)
interaction
(1.00%)
interesting subject
(-54.15%)
intrusive object presence
(-8.72%)
lively color
(-0.56%)
low light
(98.10%)
noise
(-8.08%)
pleasant camera tilt
(-9.62%)
pleasant composition
(-75.63%)
pleasant lighting
(-52.93%)
pleasant pattern
(7.93%)
pleasant perspective
(-9.02%)
pleasant post processing
(-0.71%)
pleasant reflection
(-0.58%)
pleasant symmetry
(0.29%)
sharply focused subject
(0.24%)
tastefully blurred
(-1.46%)
well chosen subject
(-40.80%)
well framed subject
(-51.22%)
well timed shot
(-8.03%)
all
(-10.81%)
* 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 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.