This ComfyUI animation text to video workflow from Alien Machine AI integrates SDXL models into the image to video workflow for CogVideoX-Fun 5b or 2b including the version 1.1 model.
This gives you a single ComfyUI workflow to generate your image and make it into something animated. It is running for me on NVIDIA 3090 hardware successfully.
I have included detailed Notes in the workflow to explain what is happening and give the defaults where applicable, to make it easier to experiment and learn from the ComfyUI animation workflow featuring CogVideoX-Fun and SDXL.
Reference https://github.com/aigc-apps/CogVideoX-Fun/blob/main/comfyui/README.md
Install Custom Nodes
cd ComfyUI/custom_nodes/
# Git clone the cogvideox_fun itself
git clone https://github.com/aigc-apps/CogVideoX-Fun.git
# Git clone the video outout node
git clone https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite.git
cd CogVideoX-Fun/
python install.py
2. Using git-lfs Download CogVideoX-Fun-V1.1-5b-InP model repos from huggingface into (make new directory) ComfyUI/models/CogVideoX_Fun/