BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2024//speaker//TCFUAP
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2024-ECCJAG@pretalx.com
DTSTART;TZID=CET:20240424T103000
DTEND;TZID=CET:20240424T110000
DESCRIPTION:Have you ever wondered how travel e-commerce companies gather p
 hotos of cities? While I can't speak for everyone\, I will demonstrate the
  innovative approach we are using at Flix.\n\nIn recent years\, text-to-te
 xt models like ChatGPT and text-to-image models such as DALL-E 3 have beco
 me increasingly integrated into various industries. The main aim of these 
 initiatives is typically to generate text or images. In our presentation\,
  we propose a slightly different approach to leveraging these models comme
 rcially. Our objective is to gather images for thousands of cities that in
 spire travel. We utilize ChatGPT to tailor prompts for our business requir
 ements\, enabling efficient image retrieval through API queries from free 
 stock image services. Then we apply image-to-text models to confirm the im
 ages' locations. Finally\, we need to adjust the resolution of images for 
 display across various platforms\, such as social media campaigns on Insta
 gram\, email marketing\, and on our website. To achieve this\, we have use
 d an automated cropping service to get images in the required aspect ratio
 s\, followed by Lanczos sampling for downscaling the images. This integrat
 ion of cutting-edge models has resulted in an automated\, highly flexible 
 process that aligns with varied business needs. Our approach is cost-effic
 ient\; processing several hundred cities amounts to only a few euros\, and
  we have utilized commonly available services\, making replication easy fo
 r everyone.
DTSTAMP:20260314T235005Z
LOCATION:A1
SUMMARY:FlixBus CitySnap: How we use GenAI and not only to collect captivat
 ing images for cities and confirm their locations - Andrei Chernov
URL:https://pretalx.com/pyconde-pydata-2024/talk/ECCJAG/
END:VEVENT
END:VCALENDAR