Image Only Checkpoint Loader (img2vid model)
.jpg)
Documentation
- Class name:
ImageOnlyCheckpointLoader - Category:
loaders/video_models - Output node:
False
This node specializes in loading checkpoints specifically for image-based models within video generation workflows. It efficiently retrieves and configures the necessary components from a given checkpoint, focusing on image-related aspects of the model.
Input types
| Field | Comfy dtype | Description |
|---|---|---|
ckpt_name | COMBO[STRING] | Specifies the name of the checkpoint to load, crucial for identifying and retrieving the correct checkpoint file from a predefined list. |
Output types
| Field | Comfy dtype | Description |
|---|---|---|
model | MODEL | Returns the main model loaded from the checkpoint, configured for image processing within video generation contexts. |
clip_vision | CLIP_VISION | Provides the CLIP vision component from the checkpoint, tailored for image understanding and feature extraction. |
vae | VAE | Delivers the Variational Autoencoder (VAE) component, essential for image manipulation and generation tasks. |