Photos | Posing for the Camera on New Year's Eve
Two women strike a pose in front of a city hall sign during their 2003 Japan trip. Accessories and jewelry accent their stylish outfits as they capture the moment with a photobombing friend. Location: Osaka, Japan. Date: December 31, 2002.
BLIP-2 Description:
two women posing for the cameraChronologically Adjacent
Note: You can also navigate with your arrow keys or swiping.
Metadata
Capture date:
Original Dimensions:
480w x 640h - (download 4k)
Usage
Dominant Color:
Location:
urban osaka dress bracelet ring portrait glasses lipstick trip nakanoshima laughing necklace earring teeth jewelry hardware platinum happy blonde sign electronics kita nye_evo_osaka hair japan cosmetics romavcrew screen selfie mouth nye blouse accessories photography photobombing monitor computer evo part
flash fired
true
iso
100
metering mode
5
aperture
f/5.6
focal length
6mm
shutter speed
1/30s
camera make
OLYMPUS OPTICAL CO.,LTD
camera model
overall
(39.11%)
curation
(50.00%)
highlight visibility
(4.35%)
behavioral
(70.32%)
failure
(-0.49%)
harmonious color
(-2.13%)
immersiveness
(0.29%)
interaction
(1.00%)
interesting subject
(9.06%)
intrusive object presence
(-3.30%)
lively color
(11.46%)
low light
(44.82%)
noise
(-5.69%)
pleasant camera tilt
(-2.69%)
pleasant composition
(-23.51%)
pleasant lighting
(-26.56%)
pleasant pattern
(2.88%)
pleasant perspective
(-9.72%)
pleasant post processing
(0.54%)
pleasant reflection
(0.41%)
pleasant symmetry
(0.20%)
sharply focused subject
(7.23%)
tastefully blurred
(-0.55%)
well chosen subject
(-25.22%)
well framed subject
(51.27%)
well timed shot
(6.48%)
all
(-0.34%)
* 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.