🎥 Video demo link
This workflow is based in the SDXL Animation Guide Using Hotshot-XL from Inner-Reflections.
Read their article to understand what are the requirements and how to use the different workflows.
You can watch this tutorial to see how the workflow works.
Workflow development and tutorials not only take part of my time, but also consume resources. Please consider a donation or to use the services of one of my affiliate links:
🚨 Use Runpod and I will get credits! 🤗
Run ComfyUI without installation with:
I assume that you have installed ComfyUI and have ComfyUI Manager, so the different custom nodes can be used. Except for HotShotXL, the rest of the models can be installed using ComfyUI Manager.
Assets to run the workflow
The workflow can be run with any images and frames you want to use. If you want to follow the tutorial, you will need to download the different files in the attachments on the top right:
Unzip the zip files and place them in the input folder
I could not upload Frames_24FPS in one single file <30 MB to be uploaded in Civit.ai. Unzip both files, the combine the files in a single folder.
Models
The only model you have to download and copy manually is HotShot XL motion model:
Download one of the HotShotXL model. Copy the model in ComfyUI>custom nodes>AnimateDiff-Evolved>models
You will need also to install the checkpoint (SDXL), ControlNets (OpenPose and Depth maps, SDXL), IP Adapter (SDXL vit-h) and Clipvision (for IP Adapter SD1.5). These can be downloaded using the ComfyUI Manager
Running the workflow and installing custom nodes
Start ComfyUI and frag and drop the Morphing face workflow over the ComfyUI canvas.
If custom nodes are missing, go to the Manager and Install Missing Custom Nodes.
Go to the Manager and click on Update ComfyUI
It is also recommended to click on Fetch Updates and Update All, to also update the versions of the nodes.
After all the updates, restart ComfyUI
At this moment, you should be able to run the workflow.