SP_FluxFastMergePatchFP8 [Experimental]

SP-Nodesoutput node

This node, after running, modifies the ComfyUI system function to speed up model merging/applying LoRA on the GPU. The speed can increase by up to two times. To apply the patch, simply run this node. Important: - This patch is only useful for FP8 models. - To UNDO the patch, you need to restart ComfyUI. - This patch is useless if you are using GGUF-Unet models.

Pack: SP-Nodes

custom_nodes.ComfyUI-SP-Nodes

Inputs (2)

Name	Type	Required
info	STRING	required
optional	*	optional

Outputs (1)

Name	Type
*	*