A question that seriously affects speed is: Will the backend reload the checkpoint when loading different LORA generated images?

When executing different LORAs with the same checkpoint, the backend will reload the checkpoint, which takes several times longer to generate the graph. Can we not force the same checkpoint to be loaded?

example：
got prompt
100%|████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:04<00:00, 1.93it/s]
Starting restore_face with codeformer_fidelity: 0.5
Prompt executed in 10.85 seconds
got prompt
Requested to load SDXLClipModel
Loading 1 new model
Requested to load SDXL
Loading 1 new model
100%|████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:03<00:00, 2.08it/s]
Starting restore_face with codeformer_fidelity: 0.5
Prompt executed in 40.08 seconds