We are a community of AI video and image synthesis developers, enthusiasts, and artists.
We have created a notebook and two prominent sd-webui extensions using state of the art text2image and text2video models and continue to improve their functionality daily.
It’s free, it’s amazing, and you can use it to make cool stuff with AI.
—
There are two main software pieces:
1) Deforum — an extensive script for 2D and 3D animations, supporting keyframable sequences, dynamic math parameters (even inside the prompts), dynamic masking, depth estimation and warping. It has support for additional tools such as OpticalFlow, ZoeDepth and ControlNet.
2) sd-webui-text2video — the implementation of text2video diffusion models, including ModelScope and VideoCrafter, with various additional features and hacks on top of these models, such as the vid2vid mode and ‘in-framing’ allowing the model to animate existing pictures or to make seamless video loops.
—
In this community you will find the top level AI-animation devs, tirelessly working on bringing forth the newest tools and you will get the chance to try them from the first hands, before the others!
