Text-to-Video Generation Models
15 repos
Tools and model variants for generating animated video from text descriptions, built on diffusion-based architectures. The cluster centers on EasyAnimate, a family of models available in different sizes (7B and 12B parameters) with multiple control variants including standard inference, in-painting, and ControlNet-style spatial control. These repositories share the diffusers framework and safetensors model serialization as common infrastructure, enabling efficient video synthesis across different hardware and use cases.
Python · 1
diffusers ·80
safetensors ·80
