ComfyUI > Nodes > ComfyUI > ImageOnlyCheckpointSave

ComfyUI Node: ImageOnlyCheckpointSave

Class Name

ImageOnlyCheckpointSave

Category
_for_testing
Author
ComfyAnonymous (Account age: 598days)
Extension
ComfyUI
Latest Updated
2024-08-12
Github Stars
45.85K

How to Install ComfyUI

Install this extension via the ComfyUI Manager by searching for ComfyUI
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • High-speed GPU machines
  • 200+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 50+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

ImageOnlyCheckpointSave Description

Facilitates saving image-based model checkpoints with metadata and filename prefix for efficient organization and management.

ImageOnlyCheckpointSave:

The ImageOnlyCheckpointSave node is designed to facilitate the saving of model checkpoints specifically for image-based models. This node is particularly useful for AI artists who work with image generation models and need to save their progress or configurations at various stages. By using this node, you can ensure that your model, along with its associated components like CLIP Vision and VAE, is saved with a specific filename prefix. This helps in organizing and managing different versions of your models efficiently. The node also supports saving additional metadata such as prompts and extra PNG information, making it a comprehensive tool for checkpoint management in image-based AI projects.

ImageOnlyCheckpointSave Input Parameters:

model

This parameter represents the image generation model that you want to save. It is a required input and ensures that the core model is included in the checkpoint. The model is essential for reproducing the same results when the checkpoint is loaded later.

clip_vision

The clip_vision parameter refers to the CLIP Vision model component. This is also a required input and is crucial for tasks that involve visual understanding and processing. Including this component in the checkpoint ensures that all visual features and capabilities are preserved.

vae

The vae parameter stands for Variational Autoencoder, which is another required input. The VAE is important for encoding and decoding images, and saving it along with the model ensures that the image generation process remains consistent.

filename_prefix

This parameter allows you to specify a prefix for the checkpoint filename. It is a required input and helps in organizing your saved checkpoints. The default value is "checkpoints/ComfyUI", but you can customize it to suit your project needs.

prompt

The prompt parameter is an optional input that allows you to save the text prompt used during the model's training or generation process. This can be useful for documentation and reproducibility purposes.

extra_pnginfo

The extra_pnginfo parameter is another optional input that lets you save additional PNG metadata. This can include any extra information you want to associate with the checkpoint, providing more context and details for future reference.

ImageOnlyCheckpointSave Output Parameters:

This node does not produce any direct output parameters. Its primary function is to save the specified model and its components to a checkpoint file.

ImageOnlyCheckpointSave Usage Tips:

  • Ensure that all required parameters (model, clip_vision, vae, and filename_prefix) are provided to avoid errors during the checkpoint saving process.
  • Use descriptive and organized filename prefixes to easily manage and locate your saved checkpoints.
  • Take advantage of the prompt and extra_pnginfo parameters to save additional context and metadata, which can be helpful for future reference and reproducibility.

ImageOnlyCheckpointSave Common Errors and Solutions:

"Invalid model input"

  • Explanation: This error occurs when the model parameter is not provided or is invalid.
  • Solution: Ensure that you have selected a valid image generation model before attempting to save the checkpoint.

"Invalid clip_vision input"

  • Explanation: This error occurs when the clip_vision parameter is not provided or is invalid.
  • Solution: Make sure to include a valid CLIP Vision model component in the input parameters.

"Invalid vae input"

  • Explanation: This error occurs when the vae parameter is not provided or is invalid.
  • Solution: Verify that a valid VAE component is included in the input parameters.

"Filename prefix not specified"

  • Explanation: This error occurs when the filename_prefix parameter is not provided.
  • Solution: Provide a valid filename prefix to ensure the checkpoint is saved correctly.

"Failed to save checkpoint"

  • Explanation: This error can occur due to various reasons such as file permission issues or invalid output directory.
  • Solution: Check the output directory permissions and ensure that the specified path is valid and accessible.

ImageOnlyCheckpointSave Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI
RunComfy

© Copyright 2024 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals.