Photos | Halloween Selfie with a Feline Friend

Amanda Griffin and Lori S strike a pose with their furry companion while celebrating Halloween in San Francisco. Dave B captures the festive moment on his phone.
BLIP-2 Description:
a man and woman in costumes taking a selfie with a catMetadata
Capture date:
Original Dimensions:
3024w x 4032h - (download 4k)
Usage
Dominant Color:
Location:
architecture civic costume door headgear manx cat plant building frame portrait mobile footwear cap outdoors wristwatch hat living furniture dave b pet flooring design balloon wood shoe amanda dog griffin coat glasses indoors dining soccer ball kitten interior rekognition_c electronics canine sport table accessories room lori puppy potted center phone photography football mammal animal floor shelter
iso
250
metering mode
5
aperture
f/2.4
focal length
2mm
latitude
37.78
longitude
-122.42
shutter speed
1/60s
camera make
Apple
camera model
date
2019-10-31T08:57:48.437000-07:00
tzoffset
-25200
tzname
GMT-0700
overall
(41.80%)
curation
(68.37%)
highlight visibility
(5.91%)
behavioral
(90.76%)
failure
(-0.22%)
harmonious color
(4.30%)
immersiveness
(0.10%)
interaction
(4.00%)
interesting subject
(27.54%)
intrusive object presence
(-12.87%)
lively color
(0.46%)
low light
(2.66%)
noise
(-2.39%)
pleasant camera tilt
(-5.70%)
pleasant composition
(-46.51%)
pleasant lighting
(-24.55%)
pleasant pattern
(2.27%)
pleasant perspective
(-0.13%)
pleasant post processing
(-3.17%)
pleasant reflection
(-1.16%)
pleasant symmetry
(0.15%)
sharply focused subject
(1.00%)
tastefully blurred
(-16.75%)
well chosen subject
(-30.93%)
well framed subject
(29.47%)
well timed shot
(27.05%)
all
(-0.31%)
* NOTE: Amazon Rekognition
detected a celebrity in this image using the
Celebrity Recognition API. The API isn't perfect, but it does give you the MatchConfidence which I display
next to the celebrity's name along with links _↗ to their info.
* 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.