BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.in.pycon.org//2025//ZNVLP9
BEGIN:VTIMEZONE
TZID:IST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:IST
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-2025-PFJVQJ@cfp.in.pycon.org
DTSTART;TZID=IST:20250914T121000
DTEND;TZID=IST:20250914T124000
DESCRIPTION:As a developer trying to iterate on SDXL prompts and schedulers
 \, I found script-based tools painful to debug. ComfyUI addresses this cha
 llenge by offering a powerful\, modular\, and open-source visual programmi
 ng environment tailored for AI image generation and experimentation. This 
 session will introduce ComfyUI as a serious developer tool for building\, 
 debugging\, and optimizing Stable Diffusion pipelines. With node-based exe
 cution graphs\, real-time previews\, and complete control over every param
 eter and model component\, ComfyUI enables reproducibility\, rapid prototy
 ping\, and extensibility for technical users. We’ll explore how develope
 rs can build custom inference workflows\, integrate APIs\, deploy on cloud
  GPUs\, and contribute custom nodes to the growing ecosystem. Whether you'
 re optimizing inference\, conducting A/B testing\, or building a generativ
 e AI backend\, this session shows why ComfyUI is an essential tool for ML 
 practitioners and engineers.
DTSTAMP:20260816T230338Z
LOCATION:Track 3
SUMMARY:Engineering Custom Diffusion Workflows with ComfyUI: A Developer's 
 Guide - Shreya Kommuri\, Siddhi Kommuri
URL:https://cfp.in.pycon.org/2025/talk/PFJVQJ/
END:VEVENT
END:VCALENDAR