Photos | Rooftop Portrait in the City
Four individuals strike a pose for a photo on a rooftop overlooking the cityscape, showing off their stylish jackets, blazers, and coats.
BLIP-2 Description:
four people posing for a photo on a rooftopChronologically Adjacent
Note: You can also navigate with your arrow keys or swiping.
Metadata
Capture date:
Original Dimensions:
640w x 480h - (download 4k)
Usage
Dominant Color:
architecture beer glass jeans boy pants formal neighborhood urban hoodie building fence portrait sweater beverage liquor outdoors transportation hat condo road outdoor jacket high rise jason w city street alcohol shirt coat junglescene glasses teen belt metropolis july wear cityscape nature car vehicle suit accessories skyscraper office downtown blazer housing photography cup eric knitwear
Detected Text
date
2002-08-29T14:15:03-07:00
tzoffset
-25200
tzname
America/Los_Angeles
overall
(33.40%)
curation
(68.04%)
highlight visibility
(5.73%)
behavioral
(70.67%)
failure
(-0.49%)
harmonious color
(-1.16%)
immersiveness
(0.56%)
interaction
(1.00%)
interesting subject
(-19.96%)
intrusive object presence
(-12.21%)
lively color
(-7.06%)
low light
(3.71%)
noise
(-7.03%)
pleasant camera tilt
(-7.31%)
pleasant composition
(-44.09%)
pleasant lighting
(-29.35%)
pleasant pattern
(7.45%)
pleasant perspective
(-1.47%)
pleasant post processing
(0.96%)
pleasant reflection
(-0.00%)
pleasant symmetry
(0.39%)
sharply focused subject
(0.54%)
tastefully blurred
(-7.10%)
well chosen subject
(-26.90%)
well framed subject
(2.71%)
well timed shot
(-1.98%)
all
(-3.99%)
* 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.