Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The ImageOnlyCheckpointSave node saves a checkpoint file containing a model, CLIP vision encoder, and VAE. It creates a safetensors file with the specified filename prefix and stores it in the output directory. This node is specifically designed for saving image-related model components together in a single checkpoint file.

Inputs

ParameterData TypeRequiredRangeDescription
modelMODELYes-The model to be saved in the checkpoint
clip_visionCLIP_VISIONYes-The CLIP vision encoder to be saved in the checkpoint
vaeVAEYes-The VAE (Variational Autoencoder) to be saved in the checkpoint
filename_prefixSTRINGYes-The prefix for the output filename (default: “checkpoints/ComfyUI”)
promptPROMPTNo-Hidden parameter for workflow prompt data
extra_pnginfoEXTRA_PNGINFONo-Hidden parameter for additional PNG metadata

Outputs

Output NameData TypeDescription
--This node does not return any outputs