Photos | Protester Holds Up Sign in Urban Metropolis
A man stands in the middle of a busy city street, holding up a handmade sign during a protest or parade. The surrounding crowd of pedestrians and the urban landscape provide a backdrop for his message.
BLIP-2 Description:
a man holding a sign in the middle of a streetChronologically 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 jeans pants neighborhood urban plant building baseball allies footwear estimated cap pedestrian sidewalk hat tree condo road outdoor handwriting text performance traffic city shoe bag land street un document parade poster cmen metropolis path banner sign light losing accessories recreation handbag priceles walking housing suppos photography protest advertisement crowd old_eecue
date
2003-02-17T17:59:10-08:00
tzoffset
-28800
tzname
America/Los_Angeles
overall
(27.34%)
curation
(50.00%)
highlight visibility
(4.36%)
behavioral
(70.54%)
failure
(-0.98%)
harmonious color
(0.57%)
immersiveness
(1.34%)
interaction
(1.00%)
interesting subject
(-53.42%)
intrusive object presence
(-7.37%)
lively color
(-9.86%)
low light
(9.38%)
noise
(-7.42%)
pleasant camera tilt
(-9.44%)
pleasant composition
(-71.09%)
pleasant lighting
(-42.85%)
pleasant pattern
(7.25%)
pleasant perspective
(-2.42%)
pleasant post processing
(1.88%)
pleasant reflection
(-1.07%)
pleasant symmetry
(0.39%)
sharply focused subject
(0.24%)
tastefully blurred
(-12.50%)
well chosen subject
(-21.00%)
well framed subject
(-55.96%)
well timed shot
(-3.20%)
all
(-7.59%)
* 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.