[Bug]: Send to IMG2IMG doesn't copy CFG

### Checklist

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

### What happened?

When I generate in TEXT2IMG and send the output to IMG2IMG, the used CFG (but not STEPS!) changes to the default of 7.

### Steps to reproduce the problem

For example I do TEXT2IMG with 6 steps and 1.5 CFG, then I send it to IMG2IMG and the steps will be set to 6, but CFG will be set to 7 (=standard value).

### What should have happened?

After sending to IMG2IMG the CFG should be set to 1.5 there.

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

Mozilla Firefox

### Sysinfo

[sysinfo-2024-03-28-17-26.json](https://github.com/lllyasviel/stable-diffusion-webui-forge/files/14793444/sysinfo-2024-03-28-17-26.json)

### Console logs

```Shell
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: f0.0.17v1.8.0rc-latest-276-g29be1da7
Commit hash: 29be1da7cf2b5dccfc70fbdd33eb35c56a31ffb7
Launching Web UI with arguments:
Total VRAM 12288 MB, total RAM 32694 MB
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3060 : native
Hint: your device supports --pin-shared-memory for potential speed improvements.
Hint: your device supports --cuda-malloc for potential speed improvements.
Hint: your device supports --cuda-stream for potential speed improvements.
VAE dtype: torch.bfloat16
CUDA Stream Activated: False
Using pytorch cross attention
*** "Disable all extensions" option was set, will not load any extensions ***
Loading weights [fdbe56354b] from C:\programs\SD-Forge\webui\models\Stable-diffusion\Lightning\dreamshaperXL_lightningDPMSDE.safetensors
Running on local URL: http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 9.2s (prepare environment: 2.0s, import torch: 3.4s, import gradio: 0.9s, setup paths: 0.8s, initialize shared: 0.1s, other imports: 0.6s, load scripts: 0.6s, create ui: 0.3s, gradio launch: 0.5s).
model_type EPS
UNet ADM Dimension 2816
Using pytorch attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using pytorch attention in VAE
extra {'cond_stage_model.clip_g.transformer.text_model.embeddings.position_ids', 'cond_stage_model.clip_l.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
[Memory Management] Current Free GPU Memory (MB) = 11246.857421875
[Memory Management] Model Memory (MB) = 2144.3546981811523
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 8078.502723693848
Moving model(s) has taken 0.52 seconds
Model loaded in 5.6s (load weights from disk: 0.4s, forge instantiate config: 1.1s, forge load real models: 2.9s, load VAE: 0.4s, calculate empty prompt: 0.7s).
token_merging_ratio = 0.3
To load target model SDXL
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 11210.64794921875
[Memory Management] Model Memory (MB) = 4897.086494445801
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 5289.561454772949
Moving model(s) has taken 1.14 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 6/6 [00:07<00:00, 1.29s/it]
To load target model AutoencoderKL███████████████████████████████████████████████████████| 6/6 [00:06<00:00, 1.23s/it]
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 6147.52197265625
[Memory Management] Model Memory (MB) = 159.55708122253418
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 4963.964891433716
Moving model(s) has taken 0.14 seconds
Cleanup minimal inference memory.
Total progress: 100%|████████████████████████████████████████████████████████████████████| 6/6 [00:11<00:00, 1.84s/it]
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]██| 6/6 [00:11<00:00, 1.23s/it]
```

### Additional information

This is happening in AUTO1111 too, but this behaviour doesn't make sense to me.

Reproduce the issue by generating in TEXT2IMG with 6 steps and 1.5 CFG, then sending the result to IMG2IMG. Trace the parameter transfer between the two UI tabs; done means IMG2IMG retains the original CFG value while preserving the existing steps behavior.

Written by the indexing model from the issue text.