Downloads · 30 days
0
animate-anything-v1.02
zyand/animate-anything-v1.02
animate-anything-v1.02 is a image-to-video model from zyand. Use it for the image-to-video task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as mit.
Given an input image, this model can animate the image under the guidance of text prompt, motion brush, and motion strength.
Access
Public
Updated Dec 22, 2023
Repo size
—
Likes
11
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 67%
At a glance
- Task
- Image-to-Video
- Library
- diffusers
- License
- mit
- Access
- Public
- Created
- Dec 19, 2023
- Updated
- Dec 22, 2023
- SHA
- 6b19289d
Model card
From the Hugging Face model README
Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->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.
Model Sources [optional]
<!-- Provide the basic links for the model. -->- Repository: [https://github.com/alibaba/animate-anything]
- Paper [optional]: [https://arxiv.org/abs/2311.12886]
- Demo [optional]: [https://animationai.github.io/AnimateAnything/]
- Task
- Image-to-Video
- Library
- diffusers
- License
- mit
- Languages
- en
- Created
- Dec 19, 2023
- Updated
- Dec 22, 2023