TY  - JOUR
TI  - AnimateDiff: Animate Your Personalized Text-to-Image Models without Specific Tuning
AU  - Guo, Y.
AU  - Yang, C.
AU  - Rao, A.
AU  - Liang, Z.
AU  - Wang, Y.
AU  - Qiao, Y.
AU  - Agrawala, M.
AU  - Lin, D.
AU  - Dai, B.
PY  - 2024
DA  - 2024/01/16/
JO  - ICLR 2024 (spotlight)
AB  - AnimateDiff, accepted as a spotlight at ICLR 2024, introduces a plug-in motion module that can animate any personalised Stable Diffusion model without requiring model-specific retraining. By separating appearance (handled by the base model) from motion (handled by the shared motion module), it enables character-consistent generated animation with a wide range of visual styles. The framework became the entry-point architecture for AI video in animation curricula and underpins thousands of node-based workflows used in teaching labs globally.
KW  - generative-ai
KW  - video-generation
KW  - motion-synthesis
KW  - character-animation
KW  - production-practice
UR  - https://arxiv.org/abs/2307.04725
LA  - en
ER  -