[Bug]: Speed has become slower after the update

[ddysDDYS]

Checklist

• [ ] The issue exists after disabling all extensions
• [ ] The issue exists on a clean installation of webui
• [ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
• [ ] The issue exists in the current version of the webui
• [ ] The issue has not been reported before recently
• [ ] The issue has been reported before but has not been fixed yet

What happened?

Speed has become slower after the update

Steps to reproduce the problem

。。。。。。

What should have happened?

。。。。。。

What browsers do you use to access the UI ?

Microsoft Edge

Sysinfo

Console logs

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: f0.0.18v1.10.0RC-latest-277-g0af28699
Commit hash: 0af28699c45c1c5bf9cb6818caac6ce881123131
Installing requirements
loading WD14-tagger reqs from C:\Users\20389\Desktop\sdxl\webui\extensions\stable-diffusion-webui-wd14-tagger\requirements.txt
Checking WD14-tagger requirements.
Launching Web UI with arguments:
Total VRAM 4096 MB, total RAM 16282 MB
Trying to enable lowvram mode because your GPU seems to have 4GB or less. If you don't want this use: --always-normal-vram
CUDA Stream Activated:  False
2024-07-15 10:45:07.074896: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-07-15 10:45:08.439882: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
Using pytorch cross attention
ControlNet preprocessor location: C:\Users\20389\Desktop\sdxl\webui\models\ControlNetPreprocessor
sd-webui-prompt-all-in-one background API service started successfully.
== WD14 tagger /gpu:0, uname_result(system='Windows', node='DESKTOP-FSA0B0S', release='10', version='10.0.19044', machine='AMD64') ==
Loading model tPonynai3_v55.safetensors [89e7c7518c] (1 out of 1)
Loading weights [89e7c7518c] from C:\Users\20389\Desktop\sdxl\webui\models\Stable-diffusion\tPonynai3_v55.safetensors
2024-07-15 10:45:19,514 - ControlNet - INFO - ControlNet UI callback registered.
Running on local URL:  http://127.0.0.1:7860
model_type EPS
UNet ADM Dimension 2816

To create a public link, set `share=True` in `launch()`.
Startup time: 43.9s (prepare environment: 18.4s, import torch: 5.3s, import gradio: 1.3s, setup paths: 6.1s, initialize shared: 0.2s, other imports: 0.9s, load scripts: 5.6s, create ui: 1.0s, gradio launch: 3.1s, app_started_callback: 1.7s).
clip missing: ['clip_l.text_projection', 'clip_l.logit_scale', 'clip_g.transformer.text_model.embeddings.position_ids']
Model loaded in 20.9s (load weights from disk: 1.3s, forge instantiate config: 1.4s, forge load real models: 15.9s, forge finalize: 0.1s, load textual inversion embeddings: 0.1s, calculate empty prompt: 2.0s).
[LORA] Loaded C:\Users\20389\Desktop\sdxl\webui\models\Lora\Hyper-SDXL-12steps-CFG-lora.safetensors for SDXL-UNet with 788 keys at weight 1.0
[LORA] Loaded C:\Users\20389\Desktop\sdxl\webui\models\Lora\Hyper-SDXL-12steps-CFG-lora.safetensors for SDXL-CLIP with 0 keys at weight 1.0
 54%|██████████████████████████████████████████████████████████████████████████████████████████████▏                                                                                | 7/13 [05:04<06:13, 62.24s/it]
 62%|███████████████████████████████████████████████████████████████████████████████████████████████████████████▋                                                                   | 8/13 [06:39<06:03, 72.63s/it]
 69%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏                                                     | 9/13 [08:13<05:17, 79.38s/it]
 77%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊                                        | 10/13 [09:49<04:12, 84.24s/it]
 85%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏                          | 11/13 [11:23<02:54, 87.39s/it]

Additional information

No response

[Panchovix]

Some reports have been coming from that, so I will maintain 2 branches. The slower one has upstream comfy changes,

To have the past speeds, do

git fetch origin

git checkout main

git pull

For more info, see here: https://github.com/Panchovix/stable-diffusion-webui-reForge/discussions/20