[Bug]: code stop running

### 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?

i2i+CN
after change model checkpoint,log shows"CloseCode.ABNORMAL_CLOSURE"
then all thing wrong, webui can not generate anything. change other model the same, no running

Calculating sha256 for /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/Comicbabes.safetensors: b1f44a5ea9134af03e959a47aef1c957faccdb80fcd6b03621142af26f32b233
Loading weights [b1f44a5ea9] from /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/Comicbabes.safetensors
model_type EPS
UNet ADM Dimension 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['model_ema.decay', 'model_ema.num_updates'])
To load target model SD1ClipModel
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 10467.8427734375
[Memory Management] Model Memory (MB) = 454.2076225280762
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 8989.635150909424
Moving model(s) has taken 0.10 seconds
Model loaded in 12.3s (unload existing model: 1.4s, calculate hash: 9.7s, forge load real models: 0.9s, load VAE: 0.2s, calculate empty prompt: 0.1s).
CloseCode.ABNORMAL_CLOSURE
CloseCode.ABNORMAL_CLOSURE
Calculating sha256 for /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/Anything Ink_Ink.safetensors: a1535d0a42ce4f8822ed034c15aeff62cc515836e388511d294645d11db8c10d
Loading weights [a1535d0a42] from /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/Anything Ink_Ink.safetensors
model_type EPS
UNet ADM Dimension 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['model_ema.decay', 'model_ema.num_updates'])
To load target model SD1ClipModel
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 10467.8427734375
[Memory Management] Model Memory (MB) = 454.2076225280762
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 8989.635150909424
Moving model(s) has taken 0.08 seconds
Model loaded in 8.9s (unload existing model: 0.5s, calculate hash: 7.1s, load weights from disk: 0.2s, forge load real models: 0.9s).
CloseCode.ABNORMAL_CLOSURE
Calculating sha256 for /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/3D角色IP 迪士尼风格_v2.0.safetensors: 4183c4c04b906c91fcf4dad9081bfa7b3307fa0a288ab0db6017d1ccd7b5d59f
Loading weights [4183c4c04b] from /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/3D角色IP 迪士尼风格_v2.0.safetensors
model_type EPS
UNet ADM Dimension 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['model_ema.decay', 'model_ema.num_updates'])
To load target model SD1ClipModel
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 10467.8427734375
[Memory Management] Model Memory (MB) = 454.2076225280762
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 8989.635150909424
Moving model(s) has taken 0.10 seconds
Model loaded in 8.5s (unload existing model: 0.5s, calculate hash: 6.8s, forge load real models: 0.8s, load VAE: 0.2s, calculate empty prompt: 0.1s).
Loading weights [3c9d7fca8b] from /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/DESIGN | 3D可爱化模型_V3.1.safetensors
model_type EPS
UNet ADM Dimension 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['alphas_cumprod', 'alphas_cumprod_prev', 'betas', 'log_one_minus_alphas_cumprod', 'posterior_log_variance_clipped', 'posterior_mean_coef1', 'posterior_mean_coef2', 'posterior_variance', 'sqrt_alphas_cumprod', 'sqrt_one_minus_alphas_cumprod', 'sqrt_recip_alphas_cumprod', 'sqrt_recipm1_alphas_cumprod'])
To load target model SD1ClipModel
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 10467.8427734375
[Memory Management] Model Memory (MB) = 454.2076225280762
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 8989.635150909424
Moving model(s) has taken 0.10 seconds
Model loaded in 1.4s (unload existing model: 0.5s, forge load real models: 0.6s, calculate empty prompt: 0.1s).

### Steps to reproduce the problem

i2i
controlnet
change a new model checkpoint

### What should have happened?

should run generation

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

_No response_

### Sysinfo

version: [f0.0.16v1.8.0rc-latest-268-gb59deaa3](https://github.com/lllyasviel/stable-diffusion-webui-forge/commit/b59deaa382bf5c968419eff4559f7d06fc0e76e7)  •  python: 3.10.8  •  torch: 2.1.2+cu121  •  xformers: 0.0.23.post1  •  gradio: 3.41.2  •  checkpoint: [3c9d7fca8b](https://google.com/search?q=3c9d7fca8b8167f393a78ad3ae9e2ee1cc61ed5c1d5e8e00ca0880c4afca1b75)

### Console logs

```Shell
Calculating sha256 for /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/Comicbabes.safetensors: b1f44a5ea9134af03e959a47aef1c957faccdb80fcd6b03621142af26f32b233
Loading weights [b1f44a5ea9] from /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/Comicbabes.safetensors
model_type EPS
UNet ADM Dimension 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['model_ema.decay', 'model_ema.num_updates'])
To load target model SD1ClipModel
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 10467.8427734375
[Memory Management] Model Memory (MB) = 454.2076225280762
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 8989.635150909424
Moving model(s) has taken 0.10 seconds
Model loaded in 12.3s (unload existing model: 1.4s, calculate hash: 9.7s, forge load real models: 0.9s, load VAE: 0.2s, calculate empty prompt: 0.1s).
CloseCode.ABNORMAL_CLOSURE
CloseCode.ABNORMAL_CLOSURE
Calculating sha256 for /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/Anything Ink_Ink.safetensors: a1535d0a42ce4f8822ed034c15aeff62cc515836e388511d294645d11db8c10d
Loading weights [a1535d0a42] from /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/Anything Ink_Ink.safetensors
model_type EPS
UNet ADM Dimension 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['model_ema.decay', 'model_ema.num_updates'])
To load target model SD1ClipModel
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 10467.8427734375
[Memory Management] Model Memory (MB) = 454.2076225280762
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 8989.635150909424
Moving model(s) has taken 0.08 seconds
Model loaded in 8.9s (unload existing model: 0.5s, calculate hash: 7.1s, load weights from disk: 0.2s, forge load real models: 0.9s).
CloseCode.ABNORMAL_CLOSURE
Calculating sha256 for /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/3D角色IP 迪士尼风格_v2.0.safetensors: 4183c4c04b906c91fcf4dad9081bfa7b3307fa0a288ab0db6017d1ccd7b5d59f
Loading weights [4183c4c04b] from /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/3D角色IP 迪士尼风格_v2.0.safetensors
model_type EPS
UNet ADM Dimension 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['model_ema.decay', 'model_ema.num_updates'])
To load target model SD1ClipModel
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 10467.8427734375
[Memory Management] Model Memory (MB) = 454.2076225280762
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 8989.635150909424
Moving model(s) has taken 0.10 seconds
Model loaded in 8.5s (unload existing model: 0.5s, calculate hash: 6.8s, forge load real models: 0.8s, load VAE: 0.2s, calculate empty prompt: 0.1s).
Loading weights [3c9d7fca8b] from /root/autodl-tmp/stable-diffusion-webui-forge/models/Stable-diffusion/DESIGN | 3D可爱化模型_V3.1.safetensors
model_type EPS
UNet ADM Dimension 0
Using xformers attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using xformers attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['alphas_cumprod', 'alphas_cumprod_prev', 'betas', 'log_one_minus_alphas_cumprod', 'posterior_log_variance_clipped', 'posterior_mean_coef1', 'posterior_mean_coef2', 'posterior_variance', 'sqrt_alphas_cumprod', 'sqrt_one_minus_alphas_cumprod', 'sqrt_recip_alphas_cumprod', 'sqrt_recipm1_alphas_cumprod'])
To load target model SD1ClipModel
Begin to load 1 model
[Memory Management] Current Free GPU Memory (MB) = 10467.8427734375
[Memory Management] Model Memory (MB) = 454.2076225280762
[Memory Management] Minimal Inference Memory (MB) = 1024.0
[Memory Management] Estimated Remaining GPU Memory (MB) = 8989.635150909424
Moving model(s) has taken 0.10 seconds
Model loaded in 1.4s (unload existing model: 0.5s, forge load real models: 0.6s, calculate empty prompt: 0.1s).
```

### Additional information

_No response_

Start by reproducing the i2i and ControlNet flow while changing checkpoints, using the reported CloseCode.ABNORMAL_CLOSURE console output and the listed version, Python, torch, xformers, and Gradio environment. Trace the checkpoint-change entry point and identify why generation stops; done means generation completes normally after switching models.

Written by the indexing model from the issue text.