[bug]: Can't upscale anything. Keep getting "KeyError: 'middle_block_out.0.weight'" error

[evanerichards]

Is there an existing issue for this problem?

• [X] I have searched the existing issues

Operating system

Windows

GPU vendor

Nvidia (CUDA)

GPU model

RTX 3090

GPU VRAM

24GB

Version number

v5.0.0.rc1

Browser

Firefox 130.0.1 (64-bit)

Python dependencies

No response

What happened

have a newly installed version of Invoke v5.0.0.rc1. I take a simple image and try to upscale but I receive this error message: have a newly installed version of Invoke v5.0.0.rc1. I take a simple image and try to upscale but I receive this error message:

[2024-09-23 15:05:39,510]::[InvokeAI]::ERROR --> Error while invoking session 9f8db22a-dc2e-4fef-b19b-5e9672a7e259, invocation d3477dbe-f38e-4ea6-b5bb-bc1c3232d273 (denoise_latents): 'middle_block_out.0.weight'
[2024-09-23 15:05:39,511]::[InvokeAI]::ERROR --> Traceback (most recent call last):
 File "E:\invokeai\.venv\lib\site-packages\invokeai\app\services\session_processor\session_processor_default.py", line 129, in run_node
   output = invocation.invoke_internal(context=context, services=self._services)
 File "E:\invokeai\.venv\lib\site-packages\invokeai\app\invocations\baseinvocation.py", line 290, in invoke_internal
   output = self.invoke(context)
 File "E:\invokeai\.venv\lib\site-packages\invokeai\app\invocations\denoise_latents.py", line 790, in invoke
   return self._old_invoke(context)
 File "E:\invokeai\.venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
   return func(*args, **kwargs)
 File "C:\Users\evane\AppData\Local\Programs\Python\Python310\lib\contextlib.py", line 79, in inner
   return func(*args, **kwds)
 File "E:\invokeai\.venv\lib\site-packages\invokeai\app\invocations\denoise_latents.py", line 1022, in _old_invoke
   controlnet_data = self.prep_control_data(
 File "E:\invokeai\.venv\lib\site-packages\invokeai\app\invocations\denoise_latents.py", line 437, in prep_control_data
   control_model = exit_stack.enter_context(context.models.load(control_info.control_model))
 File "E:\invokeai\.venv\lib\site-packages\invokeai\app\services\shared\invocation_context.py", line 369, in load
   return self._services.model_manager.load.load_model(model, _submodel_type)
 File "E:\invokeai\.venv\lib\site-packages\invokeai\app\services\model_load\model_load_default.py", line 70, in load_model
   ).load_model(model_config, submodel_type)
 File "E:\invokeai\.venv\lib\site-packages\invokeai\backend\model_manager\load\load_default.py", line 56, in load_model
   locker = self._load_and_cache(model_config, submodel_type)
 File "E:\invokeai\.venv\lib\site-packages\invokeai\backend\model_manager\load\load_default.py", line 77, in _load_and_cache
   loaded_model = self._load_model(config, submodel_type)
 File "E:\invokeai\.venv\lib\site-packages\invokeai\backend\model_manager\load\model_loaders\controlnet.py", line 31, in _load_model
   return ControlNetModel.from_single_file(
 File "E:\invokeai\.venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn
   return fn(*args, **kwargs)
 File "E:\invokeai\.venv\lib\site-packages\diffusers\loaders\controlnet.py", line 124, in from_single_file
   component = create_diffusers_controlnet_model_from_ldm(
 File "E:\invokeai\.venv\lib\site-packages\diffusers\loaders\single_file_utils.py", line 973, in create_diffusers_controlnet_model_from_ldm
   diffusers_format_controlnet_checkpoint = convert_controlnet_checkpoint(checkpoint, diffusers_config)
 File "E:\invokeai\.venv\lib\site-packages\diffusers\loaders\single_file_utils.py", line 937, in convert_controlnet_checkpoint
   new_checkpoint["controlnet_mid_block.weight"] = controlnet_state_dict.pop("middle_block_out.0.weight")
KeyError: 'middle_block_out.0.weight'

What you expected to happen

I expected the photo to be upres'd

How to reproduce the problem

Start the app, try to upscale.

Additional context

No response

Discord username

No response