Spaces - General Image Processing & Applications - IDM-VTON: Virtual Try-On - Error on Launch

Nobody has claimed this yet.

I just performed a fresh installation of the latest Forge Gradio Package (CUDA 12.1 + Pytorch 2.3.1).

When installing `IDM-VTON: Virtual Try-On with your image and garment image`, an error is raised in the console for a missing **diffusion_pytorch_model.safetensors**:

```
_[Unload] Trying to free all memory for cuda:0 with 0 models keep loaded ... Done._
**An error occurred while trying to fetch yisol/IDM-VTON: yisol/IDM-VTON does not appear to have a file named diffusion_pytorch_model.safetensors.**
_Loading pipeline components..._
```

I have reinstalled and uninstalled the package, but the error still persists. I have checked for solutions but couldn't find any relevant forum posts or discussions explaining how to fix it.

Does anyone know who the creator of this Space is? How can I reach someone to help resolve this issue?

Error log when trying to run:
```
Traceback (most recent call last):
File "C:\webui_forge_cu121_torch231.7\system\python\lib\site-packages\gradio\queueing.py", line 536, in process_events
response = await route_utils.call_process_api(
File "C:\webui_forge_cu121_torch231.7\system\python\lib\site-packages\gradio\route_utils.py", line 285, in call_process_api
output = await app.get_blocks().process_api(
File "C:\webui_forge_cu121_torch231.7\system\python\lib\site-packages\gradio\blocks.py", line 1923, in process_api
result = await self.call_function(
File "C:\webui_forge_cu121_torch231.7\system\python\lib\site-packages\gradio\blocks.py", line 1508, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
File "C:\webui_forge_cu121_torch231.7\system\python\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "C:\webui_forge_cu121_torch231.7\system\python\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "C:\webui_forge_cu121_torch231.7\system\python\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
result = context.run(func, *args)
File "C:\webui_forge_cu121_torch231.7\system\python\lib\site-packages\gradio\utils.py", line 818, in wrapper
response = f(*args, **kwargs)
File "C:\webui_forge_cu121_torch231.7\system\python\lib\site-packages\gradio\utils.py", line 818, in wrapper
response = f(*args, **kwargs)
File "C:\webui_forge_cu121_torch231.7\webui\spaces.py", line 169, in wrapper
result = func(*args, **kwargs)
File "C:\webui_forge_cu121_torch231.7\webui\extensions-builtin\forge_space_idm_vton\forge_app.py", line 171, in start_tryon
keypoints = openpose_model(human_img.resize((384, 512)))
File "C:\webui_forge_cu121_torch231.7\webui\extensions-builtin\forge_space_idm_vton\huggingface_space_mirror\preprocess\openpose\run_openpose.py", line 51, in __call__
subset = pose['bodies']['subset'][0][:18]
IndexError: list index out of range
```

Start at webui/extensions-builtin/forge_space_idm_vton/forge_app.py, especially start_tryon, then inspect huggingface_space_mirror/preprocess/openpose/run_openpose.py and its __call__ entry point. Reproduce the IDM-VTON launch and trace both the missing diffusion_pytorch_model.safetensors message and the IndexError. Done means the Space launches without these errors.

Written by the indexing model from the issue text.