A presentation slide titled "AnimateDiff" discusses the transformation of domain-specific text-to-image (T2I) models into text-to-video (T2V) models. The slide highlights that domain-specific (personalized) models are widely available for images and lists finetuning methodologies such as LoRA and DreamBooth. It also mentions communities like Hugging Face and CivitAI. The task is to turn these image models into T2V models without specific finetuning. An example image from CivitAI showcases various character portraits. The slide references a paper by Guo et al. titled "AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning," published in arXiv in 2023, with copyright credited to Mike Shou, NUS. The presentation appears to be taking place in a conference or seminar room, with attendees viewing the slide.
Text transcribed from the image:
Animate Diff
Transform domain-specific T21 models to T2V models
•
•
Domain-specific (personalized) models are widely available for image
•
Domain-specific finetuning methodologies: LORA, DreamBooth...
Communities: Hugging Face, CivitAl...
Task: turn these image models into T2V models, without specific finetuning
CIVITAI
MOST DOWNLOADED
ALL DIMACTER LIKE CELEBRITY CONCEPT GOTHING
TOOL BUILDINGS VEHICLE OECTS ANIMAL ACTION ASSETS
THX
RealCARTOON
3D,
ON OF LIKE PAR
Cyfarfalite
Cute TERR style)
OLE OF A F
OLE OF AIR 2
Guo et al., "Animate Diff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning," arXiv 2023.
QA
MORING FASC
MONTH 9
[Ouickpoint) Tolly
Q10 On 1 ta
RealCARTOON
Copyright Mike Shou, NUS
1: