Photos | Mall Portrait of a Couple and Friend
A man and woman strike a pose with their friend in a mall, showcasing their urban fashion sense and accessories.
BLIP-2 Description:
a man and woman posing for a picture in a mallChronologically 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:
lighting jacket couch city urban furniture outdoors dating dining jeans photos/reid_speed_ming_fs laughing blouse t-shirt happy part elem old indoors parking belt accessories photography bag shirt beverage jewelry street pants chair pub road night glasses mouth fs ming purple romantic counter portrait bar table shorts junglescene alcohol restaurant jason handbag earring stool rekognition_c bracelet hat speed nature teeth reid necklace coat
Detected Text
date
2002-10-02T01:23:13-07:00
tzoffset
-25200
tzname
America/Los_Angeles
overall
(35.21%)
curation
(65.58%)
highlight visibility
(5.54%)
behavioral
(70.55%)
failure
(-0.34%)
harmonious color
(1.00%)
immersiveness
(0.12%)
interaction
(1.00%)
interesting subject
(5.61%)
intrusive object presence
(-7.45%)
lively color
(-14.09%)
low light
(86.62%)
noise
(-10.74%)
pleasant camera tilt
(-6.60%)
pleasant composition
(-29.10%)
pleasant lighting
(-48.34%)
pleasant pattern
(3.39%)
pleasant perspective
(4.92%)
pleasant post processing
(0.32%)
pleasant reflection
(0.81%)
pleasant symmetry
(0.27%)
sharply focused subject
(0.56%)
tastefully blurred
(-12.67%)
well chosen subject
(-39.55%)
well framed subject
(46.68%)
well timed shot
(5.73%)
all
(-4.09%)
* 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.