Program crashed without any error.

Nobody has claimed this yet.

Every change of model is guaranteed to crash.

There are three event logs:
1--------------------------------------------------------------------
```
- System

- Provider

[ Name] Application Error
[ Guid] {a0e9b465-b939-57d7-b27d-95d8e925ff57}

EventID 1000

Version 0

Level 2

Task 100

Opcode 0

Keywords 0x8000000000000000

- TimeCreated

[ SystemTime] 2024-12-22T16:47:33.4726944Z

EventRecordID 3132

Correlation

- Execution

[ ProcessID] 20764
[ ThreadID] 4624

Channel Application

Computer DESKTOP-M6PT3DK

- Security

[ UserID] S-1-5-21-2813930871-2606586048-1739218376-1001

- EventData

AppName python.exe
AppVersion 3.11.10150.1013
AppTimeStamp 66fe4698
ModuleName c10.dll
ModuleVersion 0.0.0.0
ModuleTimeStamp 67185b07
ExceptionCode c0000005
FaultingOffset 000000000006ce14
ProcessId 0xa0f0
ProcessCreationTime 0x1db549103630e39
AppPath C:\Users\ZQH\Environment\miniconda3\envs\python_3_11\python.exe
ModulePath C:\Users\ZQH\Environment\miniconda3\envs\python_3_11\Lib\site-packages\torch\lib\c10.dll
IntegratorReportId 4ae36010-e852-4e1f-b6d0-b9ba8d2e03e7
PackageFullName
PackageRelativeAppId
```
2--------------------------------------------------------------------
```
- System

- Provider

[ Name] Windows Error Reporting
[ Guid] {0ead09bd-2157-539a-8d6d-c87f95b64d70}

EventID 1001

Version 0

Level 4

Task 0

Opcode 0

Keywords 0x8000000000000000

- TimeCreated

[ SystemTime] 2024-12-22T16:47:36.0959059Z

EventRecordID 3133

Correlation

- Execution

[ ProcessID] 20764
[ ThreadID] 4624

Channel Application

Computer DESKTOP-M6PT3DK

- Security

[ UserID] S-1-5-21-2813930871-2606586048-1739218376-1001

- EventData

Bucket
BucketType 0
EventName APPCRASH
Response 不可用
CabId 0
P1 python.exe
P2 3.11.10150.1013
P3 66fe4698
P4 c10.dll
P5 0.0.0.0
P6 67185b07
P7 c0000005
P8 000000000006ce14
P9
P10
AttachedFiles
StorePath \\?\C:\ProgramData\Microsoft\Windows\WER\ReportQueue\AppCrash_python.exe_3d17561ea4b17f4a20205dd2cccfc164f5395d7a_ff1c9bc1_451387d9-2b5d-4609-979c-9dc8447c7b9e
AnalysisSymbol
Rechecking 0
ReportId 4ae36010-e852-4e1f-b6d0-b9ba8d2e03e7
ReportStatus 4
HashedBucket
CabGuid 0

```
3--------------------------------------------------------------------
```
- System

- Provider

[ Name] Windows Error Reporting
[ Guid] {0ead09bd-2157-539a-8d6d-c87f95b64d70}

EventID 1001

Version 0

Level 4

Task 0

Opcode 0

Keywords 0x8000000000000000

- TimeCreated

[ SystemTime] 2024-12-22T16:47:38.2831740Z

EventRecordID 3134

Correlation

- Execution

[ ProcessID] 42072
[ ThreadID] 40492

Channel Application

Computer DESKTOP-M6PT3DK

- Security

[ UserID] S-1-5-18

- EventData

Bucket 2271627961727997476
BucketType 4
EventName APPCRASH
Response 不可用
CabId 0
P1 python.exe
P2 3.11.10150.1013
P3 66fe4698
P4 c10.dll
P5 0.0.0.0
P6 67185b07
P7 c0000005
P8 000000000006ce14
P9
P10
AttachedFiles \\?\C:\ProgramData\Microsoft\Windows\WER\Temp\WER.15014216-2415-416f-8f3f-a07f402be804.tmp.WERInternalMetadata.xml
StorePath \\?\C:\ProgramData\Microsoft\Windows\WER\ReportArchive\AppCrash_python.exe_3d17561ea4b17f4a20205dd2cccfc164f5395d7a_ff1c9bc1_451387d9-2b5d-4609-979c-9dc8447c7b9e
AnalysisSymbol
Rechecking 0
ReportId 4ae36010-e852-4e1f-b6d0-b9ba8d2e03e7
ReportStatus 268435456
HashedBucket 5143647b6488f2f19f86719878a45624
CabGuid 0

```

((((((((((There are no errors in the output of the program.))))))))))
```
Launching Web UI with arguments: --xformers --autolaunch --skip-prepare-environment --cuda-malloc --cuda-stream
Using cudaMallocAsync backend.
Total VRAM 16376 MB, total RAM 32557 MB
pytorch version: 2.5.1+cu124
xformers version: 0.0.28.post3
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4070 Ti SUPER : cudaMallocAsync
VAE dtype preferences: [torch.bfloat16, torch.float32] -> torch.bfloat16
CUDA Using Stream: True
Using xformers cross attention
Using xformers attention for VAE
ControlNet preprocessor location: D:\Workspace\Python\stable-diffusion-webui-forge\models\ControlNetPreprocessor
D:\Workspace\Python\stable-diffusion-webui-forge\modules_forge\patch_basic.py:38: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
result = original_loader(*args, **kwargs)
Loading additional modules ... done.
2024-12-23 00:46:36,364 - ControlNet - INFO - ControlNet UI callback registered.
Model selected: {'checkpoint_info': {'filename': 'D:\\Workspace\\Python\\stable-diffusion-webui-forge\\models\\Stable-diffusion\\AnythingXL_xl.safetensors', 'hash': '3a68e6c2'}, 'additional_modules': ['D:\\Workspace\\Python\\stable-diffusion-webui-forge\\models\\VAE\\artWaifu_v10.safetensors', 'D:\\Workspace\\Python\\stable-diffusion-webui-forge\\models\\VAE\\sdxl_vae.safetensors'], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Running on local URL: http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 24.4s (launcher: 0.4s, import torch: 9.7s, initialize shared: 0.4s, other imports: 0.4s, load scripts: 1.8s, initialize google blockly: 8.4s, create ui: 2.2s, gradio launch: 0.9s).
Environment vars changed: {'stream': False, 'inference_memory': 1024.0, 'pin_shared_memory': False}
[GPU Setting] You will use 93.75% GPU memory (15351.00 MB) to load weights, and use 6.25% GPU memory (1024.00 MB) to do matrix computation.
Loading Model: {'checkpoint_info': {'filename': 'D:\\Workspace\\Python\\stable-diffusion-webui-forge\\models\\Stable-diffusion\\AnythingXL_xl.safetensors', 'hash': '3a68e6c2'}, 'additional_modules': ['D:\\Workspace\\Python\\stable-diffusion-webui-forge\\models\\VAE\\artWaifu_v10.safetensors', 'D:\\Workspace\\Python\\stable-diffusion-webui-forge\\models\\VAE\\sdxl_vae.safetensors'], 'unet_storage_dtype': None}
[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done.
StateDict Keys: {'unet': 1680, 'vae': 250, 'text_encoder': 197, 'text_encoder_2': 518, 'ignore': 0}
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
IntegratedAutoencoderKL Unexpected: ['model_ema.decay', 'model_ema.num_updates']
K-Model Created: {'storage_dtype': torch.float16, 'computation_dtype': torch.float16}
D:\Workspace\Python\stable-diffusion-webui-forge\modules_forge\patch_basic.py:38: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
result = original_loader(*args, **kwargs)
Model loaded in 1.4s (unload existing model: 0.2s, forge model load: 1.2s).
[Unload] Trying to free 3051.58 MB for cuda:0 with 0 models keep loaded ... Done.
[Memory Management] Target: JointTextEncoder, Free GPU: 15076.78 MB, Model Require: 1559.68 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 12493.11 MB, All loaded to GPU.
Moving model(s) has taken 1.56 seconds
[Unload] Trying to free 1024.00 MB for cuda:0 with 1 models keep loaded ... Current free memory is 13272.46 MB ... Done.
[Unload] Trying to free 7656.40 MB for cuda:0 with 0 models keep loaded ... Current free memory is 13271.60 MB ... Done.
[Memory Management] Target: KModel, Free GPU: 13271.60 MB, Model Require: 4897.05 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7350.55 MB, All loaded to GPU.
Moving model(s) has taken 4.09 seconds
100%|##################################################################################| 20/20 [00:05<00:00, 3.87it/s]
[Unload] Trying to free 4495.36 MB for cuda:0 with 0 models keep loaded ... Current free memory is 8352.73 MB ... Done.
[Memory Management] Target: IntegratedAutoencoderKL, Free GPU: 8352.73 MB, Model Require: 159.56 MB, Previously Loaded: 0.00 MB, Inference Require: 1024.00 MB, Remaining: 7169.17 MB, All loaded to GPU.
Moving model(s) has taken 0.11 seconds
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:05<00:00, 3.64it/s]
Model selected: {'checkpoint_info': {'filename': 'D:\\Workspace\\Python\\stable-diffusion-webui-forge\\models\\Stable-diffusion\\AnythingXL_xl.safetensors', 'hash': '3a68e6c2'}, 'additional_modules': ['D:\\Workspace\\Python\\stable-diffusion-webui-forge\\models\\VAE\\sdxl_vae.safetensors'], 'unet_storage_dtype': None}
Using online LoRAs in FP16: False
Loading Model: {'checkpoint_info': {'filename': 'D:\\Workspace\\Python\\stable-diffusion-webui-forge\\models\\Stable-diffusion\\AnythingXL_xl.safetensors', 'hash': '3a68e6c2'}, 'additional_modules': ['D:\\Workspace\\Python\\stable-diffusion-webui-forge\\models\\VAE\\sdxl_vae.safetensors'], 'unet_storage_dtype': None}
```

Start by reproducing a model change with the listed Python, PyTorch, xformers, CUDA, and Windows details, then inspect the model-loading sequence and modules_forge/patch_basic.py:38. Compare the application logs with the c10.dll crash information. Done means changing models no longer terminates the process, or the failure is reported with a useful error.

Written by the indexing model from the issue text.