metadata

license: mit
language:
  - en
library_name: diffusers
pipeline_tag: image-to-video

Model Card for Model ID

Repository: [ https://github.com/alibaba/animate-anything]
Paper [optional]: [ https://arxiv.org/abs/2311.12886]
Demo [optional]: [ https://animationai.github.io/AnimateAnything/]

Given an input image, this model can animate the image under the guidance of text prompt, motion brush, and motion strength.

Model Details

Given a random size and random aspect ratio image, this model generate 2s videos in 8fps. The resolution of generated video is equivalent to 512x512.