live mode initiation process is very slow

[carmo2011]

when choose live mode and start live preview, the loading process very slow.
it seems to be paused after the backend showed "got prompt" and "model_type EPS" .
Several minutes later, it started to excute other procedures.
Could anyone help with this issue?thans!

got prompt
model_type EPS
Using xformers attention in VAE
Using xformers attention in VAE
clip missing: ['clip_l.logit_scale', 'clip_l.transformer.text_projection.weight']
Requested to load SDXLClipModel
Loading 1 new model
E:\software\ComfyUI-aki-v1.1\comfy\ldm\modules\attention.py:345: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:263.)
out = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=mask, dropout_p=0.0, is_causal=False)
Requested to load AutoencoderKL
Loading 1 new model
Requested to load SDXL
Loading 1 new model
Prompt executed in 198.61 seconds

[Acly]

The log doesn't look unusual, although xformers is persumably something you have enabled manually? Maybe try without it?

[carmo2011]

I'm not sure whether enable something manually. How to disable it(xformers as you said or other settings)? thanks!