Mochi is a new state-of-the-art local video model for generating short clips. What if you want to tell a story by chaining a few together? You can easily do that with this Mochi movie workflow, which generates and combines 4 Mochi video clips to form a long video. The movie is generated from text and created in ComfyUI.
See an example of a Midwest-style movie below.
You must be a member of this site to download this workflow.
Table of Contents
Software
We will use ComfyUI, an alternative to AUTOMATIC1111. You can use it on Windows, Mac, or Google Colab. If you prefer using a ComfyUI service, Think Diffusion offers our readers an extra 20% credit.
Read the ComfyUI beginner’s guide if you are new to ComfyUI. See the Quick Start Guide if you are new to AI images and videos.
Take the ComfyUI course to learn how to use ComfyUI step-by-step.
Step-by-step guide
Step 0: Update ComfyUI
This workflow does not require any custom nodes. But before loading the workflow, make sure your ComfyUI is up-to-date. The easiest way to do this is to use ComfyUI Manager.
Click the Manager button on the top toolbar.
Select Update ComfyUI.
Restart ComfyUI.
Step 1: Load the ComfyUI workflow
Download the workflow JSON file below. Log in and download the workflow below.
Drag and drop it to ComfyUI to load.
Step 2: Download the Mochi FP8 checkpoint
Download the Mochi checkpoint model and put it in the folder ComfyUI > models > checkpoint
Step 3: Generate video
Press Queue Prompt to generate the video. This is the MP4 video:
Customization
Prompts
Change the prompts of the video clips to customize the video. For example, change the prompt in the Clip 1 group to change the first video.
Tips:
- Use action words to describe how the subject should move. E.g. Run, walk, drinking coffee.
- Use camera words to describe the camera’s motion. E.g. Zoom in, zoom out.
Video length
Adjust the length parameter in the Empty Mochi Latent Video node to change the length of each clip.
