The image displays a presentation slide titled "AnimateDiff," focusing on transforming domain-specific text-to-image (T2I) models to text-to-video (T2V) models. The slide highlights that domain-specific (personalized) models for images are widely available and notes the use of finetuning methodologies like LoRA and DreamBooth. It also mentions the communities Hugging Face and CivitAI, which offer these models. The main task outlined is converting these image models into video models without specific finetuning. The slide includes a screenshot of a variety of personalized character images, likely demonstrating the type of models discussed. This presentation appears to be part of a technical conference or educational seminar, with the audience shown in the bottom right-hand corner. The research referenced is from Guo et al., “AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning,” arXiv 2023, with copyright attributed to Mike Shou from NUS.
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: