AnimateDiff
First page
Paper summary
Animates frozen text-to-image diffusion models via a plug-in motion modeling module.
Ask this paper
01
Motion module: Adds a motion modeling module on top of frozen T2I models that learns to produce temporally coherent frame sequences.
02
Model-agnostic: Works with any personalized T2I checkpoint (LoRAs, DreamBooth fine-tunes) without retraining - animating existing Stable Diffusion models.
03
Community adoption: Became the dominant open-source video generation tool in late 2023, powering countless community animations on ComfyUI and WebUI.
04
Open video generation: Established the architectural pattern (frozen image model + learned motion module) that many subsequent open video models followed.