CreateHookModelAsLora - ComfyUI Built-in Node Documentation

This node creates a hook model as a LoRA (Low-Rank Adaptation) by loading checkpoint weights and applying strength adjustments to both the model and CLIP components. It allows you to apply LoRA-style modifications to existing models through a hook-based approach, enabling fine-tuning and adaptation without permanent model changes. The node can combine with previous hooks and caches loaded weights for efficiency.

Inputs

Parameter	Description	Data Type	Required	Range
`ckpt_name`	The checkpoint file to load weights from (select from available checkpoints)	STRING	Yes	Multiple options available
`strength_model`	The strength multiplier applied to the model weights (default: 1.0)	FLOAT	Yes	-20.0 to 20.0
`strength_clip`	The strength multiplier applied to the CLIP weights (default: 1.0)	FLOAT	Yes	-20.0 to 20.0
`prev_hooks`	Optional previous hooks to combine with the newly created LoRA hooks	HOOKS	No	-

Parameter Constraints:

The ckpt_name parameter loads checkpoints from the available checkpoints folder
Both strength parameters accept values from -20.0 to 20.0 with 0.01 step increments
When prev_hooks is not provided, the node creates a new hook group
The node caches loaded weights to avoid reloading the same checkpoint multiple times

Outputs

Output Name	Description	Data Type
`HOOKS`	The created LoRA hooks, combined with any previous hooks if provided	HOOKS

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 8c0dd6b2e8e99e1d7dbc864aa802c0713842fb0d4ee018ea5cbedfb7896a770d

​Inputs

​Outputs

Inputs

Outputs