BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250522T212943Z
LOCATION:Mile High 1
DTSTART;TZID=America/Denver:20240801T105500
DTEND;TZID=America/Denver:20240801T110500
UID:siggraph_SIGGRAPH 2024_sess147_papers_249@linklings.com
SUMMARY:I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models
DESCRIPTION:Xun Guo (University of Science and Technology of China); Mingw
 u Zheng, Liang Hou, Yuan Gao, Yufan Deng, Pengfei Wan, and Di Zhang (Kuais
 hou Technology); Yufan Liu and Weiming Hu (Institute of Automation, Chines
 e Academy of Sciences); Zhengjun Zha (University of Science and Technology
  of China); and Haibin Huang and Chongyang Ma (Kuaishou Technology)\n\nWe 
 propose I2V-Adapter, a lightweight adapter module for Image-to-Video gener
 ation. Our method achieves excellent performance in general I2V scenarios 
 and is also compatible with various plugins from the Stable Diffusion open
 -source community. Additionally, we propose Frame-Similarity-Prior to cont
 rol the motion intensity in videos generated by the I2V model.\n\nInterest
  Area: Research & Education\n\nRecording: Livestreamed, Recorded\n\nRegist
 ration Category: Full Conference, Full Conference Supporter, Virtual Acces
 s, Exhibitor Full Conference, Thursday\n\nSession Chair: Lin Gao (Universi
 ty of Chinese Academy of Sciences)\n\n
END:VEVENT
END:VCALENDAR