In this Workflow you can create Text to video using TORA Model,

The Cool Features of Tora

Tora’s strength comes from three key parts:

1. Trajectory Extractor (TE)
2. Spatial-Temporal Diffusion Transformer (ST-DiT)
3. Motion-Guidance Fuser (MGF)

Tora can make videos up to 720p with 204 frames, giving you short and long videos that look great. Older models couldn’t handle long videos as well, but Tora is next-level.

Tutorial:  https://www.youtube.com/watch?v=vUDqk72osfc

Workflow Credit:  https://comfyuiblog.com/comfyui-tora-text-to-video-workflow/