A Simple Guide to Creating Video and Audio with ComfyUI

0

ComfyUI is a powerful tool that allows users to convert images into videos and text into audio. With this tool, anyone can create creative multimedia content. In this article, we will walk you through the steps of using ComfyUI to generate videos and audio. Follow along to easily leverage ComfyUI for your projects.

1. Creating Videos with ComfyUI

Converting Images to Videos

ComfyUI makes it simple to convert images into videos. You need two models to do this: one is the 14-frame video model, and the other is the 25-frame video model. These models should be placed in the checkpoint folder of ComfyUI.

Requirements:
Simple Workflow:
  • Prepare the initial image.
  • Load the image into the ComfyUI interface.
  • Generate the video using the 14-frame model.

Download Workflow JSON

You can also create a video by generating an initial image using SDXL and then passing it to the 25-frame model. Refer to the link below.

Example of video creation using SDXL

Download Workflow JSON

Key Parameters Explained:
  • video_frames: Number of video frames to generate
  • motion_bucket_id: The higher the number, the more movement is added to the video
  • fps: Frame rate; a higher number results in a smoother video
  • augmentation level: Controls the amount of noise added to the initial image; the higher the level, the less the video resembles the initial image

VideoLinearCFGGuidance is a node that improves sampling between frames. It gradually increases the cfg value from the first frame to the last.

2. Creating Audio with ComfyUI

Using the Stable Audio Open 1.0 Model

ComfyUI is also useful for generating audio from text. The Stable Audio Open 1.0 model can be used for this purpose.

Required Model Files:
  • t5_base.safetensors
  • stable_audio_open_1.0.safetensors

These model files should be saved in the clip and checkpoints folders of ComfyUI, respectively.

Simple Workflow:
  • Load the required model files into the ComfyUI interface.
  • Download the sample audio file below and load or drag it into ComfyUI.

Download Sample Audio

This example makes it easy to follow the process of generating audio from text.

Conclusion

ComfyUI is a powerful tool for converting images and text into videos and audio. By following this guide, you can easily create various multimedia content. It will greatly help you realize your creative ideas.

References: ComfyUI, “Video Examples”

Leave a Reply