I create this workflow, Having 12GM VRAM, Render very fast, if you have 8 gb or less select model of CogVideoX-Fun 2b instead of 5b

CogVideoX-Fun is a modified pipeline based on the CogVideoX structure, designed to provide more flexibility in generation. It can be used to create AI images and videos, as well as to train baseline models and Lora models for Diffusion Transformer. We support predictions directly from the already trained CogVideoX-Fun model, allowing the generation of videos at different resolutions, approximately 6 seconds long with 8 fps (1 to 49 frames). Users can also train their own baseline models and Lora models to achieve certain style transformations.

What's New:

• Create code! Now supporting Windows and Linux. Supports 2b and 5b models. Supports video generation at any resolution from 256x256x49 to 1024x1024x49. [ 2024.09.18

https://www.youtube.com/watch?v=OpWua6XQ_I0

Credit:  https://comfyuiblog.com/image-to-video-with-cogvideox-fun-working-in-low-vram/