Photos | Document Collage with Faces of 47 Men
An artistic collage created using Google Photos on the web, featuring the faces of 47 men in a document file format.
BLIP-2 Description:
google photos on the webMetadata
Capture date:
Original Dimensions:
1095w x 987h - (download 4k)
Usage
google coachella size audience search april show type safesearch webpage black exactly shopping mail color view everything seconds crowd reader clip standard drawing fashion related maps file page news message large white icon moderate friday art web full medium sizes oy searches document collage text line results images logo larger videos advanced
Detected Text
0.17 09 1,770,000 17 2009 2010 2011 april advanced art coachella color drawing friday google images large mail message maps moderate news photo reader shopping size safesearch search show standard type videos view web y about and any black clip everything exactly face fashion full icon larger line logo medium more oy related results searches seconds sizes than white
overall
(22.17%)
curation
(25.00%)
highlight visibility
(2.45%)
behavioral
(70.42%)
failure
(-0.17%)
harmonious color
(3.30%)
immersiveness
(0.10%)
interaction
(1.00%)
interesting subject
(-61.43%)
intrusive object presence
(-2.15%)
lively color
(14.07%)
low light
(0.27%)
noise
(-2.71%)
pleasant camera tilt
(-10.80%)
pleasant composition
(-19.59%)
pleasant lighting
(-5.40%)
pleasant pattern
(7.67%)
pleasant perspective
(21.48%)
pleasant post processing
(2.31%)
pleasant reflection
(-3.19%)
pleasant symmetry
(0.98%)
sharply focused subject
(0.78%)
tastefully blurred
(0.69%)
well chosen subject
(-0.21%)
well framed subject
(-3.69%)
well timed shot
(1.30%)
all
(3.03%)
* 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 with AI (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.