Photos | Memories on the Wall
Three friends laughing on the couch while a portrait of a man and woman watches over them in the living room of a city apartment.
BLIP-2 Description:
three people sitting on a couch with a picture of a man and woman on the wallChronologically 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 couch frame cap room urban furniture baseball cap respect dining undershirt wear tie laughing happy cinema old indoors accessories beverage shirt photography baseball formal jewelry pub night glasses building architecture club night life beer counter portrait bar table dining table junglescene painting alcohol restaurant living headgear hat art darkness necklace
Detected Text
date
2002-09-27T12:02:20-07:00
tzoffset
-25200
tzname
America/Los_Angeles
overall
(21.12%)
curation
(50.00%)
highlight visibility
(4.35%)
behavioral
(70.54%)
failure
(-0.90%)
harmonious color
(-4.32%)
immersiveness
(0.17%)
interaction
(1.00%)
interesting subject
(-50.88%)
intrusive object presence
(-3.86%)
lively color
(-3.63%)
low light
(99.71%)
noise
(-17.68%)
pleasant camera tilt
(-9.06%)
pleasant composition
(-52.00%)
pleasant lighting
(-61.87%)
pleasant pattern
(5.37%)
pleasant perspective
(-14.31%)
pleasant post processing
(-1.66%)
pleasant reflection
(-3.78%)
pleasant symmetry
(0.34%)
sharply focused subject
(0.44%)
tastefully blurred
(3.03%)
well chosen subject
(-28.64%)
well framed subject
(-16.61%)
well timed shot
(-6.52%)
all
(-10.41%)
* 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.