Photos | Couch Conversations at Coachella

Hirotoshi Ishii, Natalia Osipova, and Sun Yujun take a break from the festival to chat on the couches in their tent at the Empire Polo Club.
BLIP-2 Description:
a group of people sitting on couches in a tentMetadata
Capture date:
Original Dimensions:
3840w x 5760h - (download 4k)
Usage
Dominant Color:
Location:
lighting couch room furniture chandelier potted floor laptop natalia osipova dining hardware screen saturday lamp plant teen lounge cafe coachella court wristwatch pc waiting indoors accessories bag wood ishii jewelry sun chair glasses hirotoshi building footwear cafeteria architecture food monitor home decor interior light table boy shrub restaurant computer flooring yujun handbag living rekognition_c bracelet design hat electronics shoe
iso
3200
metering mode
5
aperture
f/2.8
focal length
16mm
shutter speed
1/160s
camera make
Canon
camera model
lens model
date
2014-04-12T17:07:35-07:00
tzoffset
-25200
tzname
America/Los_Angeles
overall
(40.16%)
curation
(50.00%)
highlight visibility
(4.36%)
behavioral
(70.65%)
failure
(-0.22%)
harmonious color
(6.32%)
immersiveness
(0.56%)
interaction
(1.00%)
interesting subject
(3.24%)
intrusive object presence
(-22.07%)
lively color
(4.75%)
low light
(31.15%)
noise
(-1.83%)
pleasant camera tilt
(-10.14%)
pleasant composition
(-67.58%)
pleasant lighting
(-14.28%)
pleasant pattern
(11.60%)
pleasant perspective
(5.39%)
pleasant post processing
(1.43%)
pleasant reflection
(5.93%)
pleasant symmetry
(1.32%)
sharply focused subject
(0.61%)
tastefully blurred
(-9.21%)
well chosen subject
(-25.95%)
well framed subject
(-33.79%)
well timed shot
(3.38%)
all
(-0.98%)
* 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.