BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070249Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T101500
DTEND;TZID=Australia/Melbourne:20231215T102500
UID:siggraphasia_SIGGRAPH Asia 2023_sess135_papers_964@linklings.com
SUMMARY:Face0: Instantaneously Conditioning a Text-to-Image Model on a Fac
 e
DESCRIPTION:Technical Papers, TOG\n\nDani Valevski, Danny Lumen, Yossi Mat
 ias, and Yaniv Leviathan (Google Research)\n\nWe present Face0, a novel wa
 y to instantaneously condition a text-to-image generation model on a face,
  in sample time, without any optimization procedures such as fine-tuning o
 r inversions. We augment a dataset of annotated images with embeddings of 
 the included faces and train an image generation model, on the augmented d
 ataset. Once trained, our system is practically identical at inference tim
 e to the underlying base model, and is therefore able to generate images, 
 given a user-supplied face image and a prompt, in just a couple of seconds
 . Our method achieves pleasing results, is remarkably simple, extremely fa
 st, and equips the underlying model with new capabilities, like controllin
 g the generated images both via text or via direct manipulation of the inp
 ut face embeddings. In addition, when using a fixed random vector instead 
 of a face embedding from a user supplied image, our method essentially sol
 ves the problem of consistent character generation across images. Finally,
  while requiring further research, we hope that our method, which decouple
 s the model’s textual biases from its biases on faces, might be a step tow
 ards some mitigation of biases in future text-to-image models.\n\nRegistra
 tion Category: Full Access\n\nSession Chair: Chongyang Ma (ByteDance)
URL:https://asia.siggraph.org/2023/full-program?id=papers_964&sess=sess135
END:VEVENT
END:VCALENDAR