[Bug]: Fooocus inpaint does not work

### Checklist

- [ ] The issue exists after disabling all extensions
- [X] 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
- [X] The issue exists in the current version of the webui
- [X] The issue has not been reported before recently
- [X] The issue has been reported before but has not been fixed yet

### What happened?

Fooocus inpaint, The resulting results change very little


### Steps to reproduce the problem


long_hair,
Steps: 7, Sampler: DPM++ SDE Karras, CFG scale: 1.5, Seed: 2368543817, Size: 712x1024, Model hash: 7eb187c0d0, Model: dreamshaperXL_v2TurboDpmppSDE, Denoising strength: 1, Clip skip: 2, ControlNet 0: "Module: inpaint_only, Model: inpaint_v26.fooocus [be360607], Weight: 1, Resize Mode: Crop and Resize, Processor Res: 0.5, Threshold A: 0.5, Threshold B: 0.5, Guidance Start: 0, Guidance End: 0.5, Pixel Perfect: False, Control Mode: ControlNet is more important, Hr Option: Both", Mask blur: 4, Masked content: fill, Version: f0.0.12-latest-155-gd81e353d

Time taken: 11.2 sec.

### What should have happened?


### What browsers do you use to access the UI ?

Microsoft Edge

### Sysinfo

[sysinfo-2024-02-14-17-31.json](https://github.com/lllyasviel/stable-diffusion-webui-forge/files/14284320/sysinfo-2024-02-14-17-31.json)

### Console logs

```Shell
/root/stable-diffusion-webui-forge
Python 3.10.8 (main, Nov 24 2022, 14:13:03) [GCC 11.2.0]
Version: f0.0.12-latest-155-gd81e353d
Commit hash: d81e353d8928147bbd973068d0efbb2802affe0f
Launching Web UI with arguments: --port=6006 --theme=dark --no-half --xformers
Total VRAM 20188 MB, total RAM 257808 MB
xformers version: 0.0.23.post1
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3080 : native
VAE dtype: torch.bfloat16
/root/miniconda3/lib/python3.10/site-packages/pytorch_lightning/utilities/distributed.py:258: LightningDeprecationWarning: `pytorch_lightning.utilities.distributed.rank_zero_only` has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from `pytorch_lightning.utilities` instead.
rank_zero_deprecation(
Using xformers cross attention
ControlNet preprocessor location: /root/stable-diffusion-webui-forge/models/ControlNetPreprocessor
sd-webui-prompt-all-in-one background API service started successfully.
Loading weights [7eb187c0d0] from /root/stable-diffusion-webui-forge/models/Stable-diffusion/dreamshaperXL_v2TurboDpmppSDE.safetensors
2024-02-15 01:27:54,992 - ControlNet - INFO - ControlNet UI callback registered.
Running on local URL: http://127.0.0.1:6006
model_type EPS
UNet ADM Dimension 2816
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE

To create a public link, set `share=True` in `launch()`.
Startup time: 19.4s (prepare environment: 3.1s, import torch: 8.6s, other imports: 0.6s, load scripts: 3.0s, create ui: 1.2s, gradio launch: 2.4s, app_started_callback: 0.4s).
extra {'cond_stage_model.clip_l.transformer.text_model.embeddings.position_ids', 'cond_stage_model.clip_g.transformer.text_model.embeddings.position_ids', 'cond_stage_model.clip_l.logit_scale', 'cond_stage_model.clip_l.text_projection'}
left over keys: dict_keys(['conditioner.embedders.0.logit_scale', 'conditioner.embedders.0.text_projection'])
To load target model SDXLClipModel
Begin to load 1 model
Moving model(s) has taken 0.34 seconds
Model loaded in 6.4s (load weights from disk: 1.5s, forge load real models: 3.6s, load VAE: 0.2s, calculate empty prompt: 1.0s).
To load target model AutoencoderKL
Begin to load 1 model
To load target model SDXL
Begin to load 1 model
Moving model(s) has taken 0.91 seconds
0%| | 0/7 [00:00

No source file or test is named. Reproduce the issue with the listed SDXL model and settings, then trace the ControlNet `inpaint_only` path and `FooocusInpaintPatcher` shown in the logs. Done means Fooocus inpainting produces a result that meaningfully follows the mask and requested prompt.

Written by the indexing model from the issue text.