Photos | March for Change
A group of 31 people walk down a busy city street, holding signs and banners in a protest for change. The crowd consists mostly of adults, with 8 handbags and various other accessories seen among them. Palm trees, plants, and buildings line the street, and traffic lights and road markings can be seen in the background.
BLIP-2 Description:
a group of people walking down the street holding signsChronologically 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 tie formal pants neighborhood urban plant building footwear pedestrian sidewalk hat tree condo road outdoor text performance tarmac city shoe bag traffic land street parade no war metropolis path wear banner sign light accessories recreation handbag walking housing palm protest crowd old_eecue
date
2003-02-17T18:00:00-08:00
tzoffset
-28800
tzname
America/Los_Angeles
overall
(30.62%)
curation
(50.00%)
highlight visibility
(4.36%)
behavioral
(70.56%)
failure
(-0.59%)
harmonious color
(-1.27%)
immersiveness
(2.56%)
interaction
(1.00%)
interesting subject
(-39.72%)
intrusive object presence
(-12.94%)
lively color
(-1.96%)
low light
(2.17%)
noise
(-5.37%)
pleasant camera tilt
(-11.87%)
pleasant composition
(-75.20%)
pleasant lighting
(-34.99%)
pleasant pattern
(11.18%)
pleasant perspective
(-5.80%)
pleasant post processing
(3.99%)
pleasant reflection
(-1.05%)
pleasant symmetry
(0.63%)
sharply focused subject
(0.20%)
tastefully blurred
(-9.30%)
well chosen subject
(-22.27%)
well framed subject
(-60.64%)
well timed shot
(-6.20%)
all
(-6.80%)
* 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.