I'd guess it's picking up algorithm-type 'deis' from the default scheduler for the model which is DEISMultistepScheduler, and using that in the scheduler config for the DPM schedulers.
DEISMultistepScheduler however doesn't have a final_sigmas_type parameter so it's using the default 'zero' value for final_sigmas_type from the DPM schedulers which is not compatible with the deis algorithm type.

It's probably going to need a check for this in the code which picks other f the values to change (algorithm type would seem most sensible to me, so DPM using its default value) unless the InvokeAI team give us a way of changing the scheduler parameters.

Just confirming that this is happening with dreamshaper 9 inpaint and the Orthodox Christian Iconography LoRA if you wanna test.
https://civitai.com/models/146025/orthodox-christian-iconography-artstyle-lora

I had a similar issue and attempted to fix by updating the below files. afterwards, i can see the image generating in the UI but as soon as it reaches 100%, the entire images turns black.

1. changed from zero to sigma_min
   file: C:\Users\vvv\invokeai.venv\Lib\site-packages\diffusers\schedulers\scheduling_dpmsolver_multistep.py
   line 210: final_sigmas_type: Optional[str] = "sigma_min", # "zero", "sigma_min"

2. changed from duis to sigma_min
   file: C:\Users\vidur\invokeai.venv\Lib\site-packages\diffusers\schedulers\scheduling_deis_multistep.py
   line 171: self.register_to_config(algorithm_type="sigma_min")

This was the error message in UI for me:
Server Error ValueError: final_sigmas_type zero is not supported for algorithm_type deis. Please choose sigma_min instead

and error message in CMD:
[2024-10-28 10:18:34,793]::[uvicorn.access]::INFO --> 127.0.0.1:54900 - "GET /api/v1/queue/default/current HTTP/1.1" 200 [2024-10-28 10:18:37,335]::[InvokeAI]::ERROR --> Error while invoking session 2e06cf0b-58c8-499e-9cea-3e44eb4ed688, invocation e4256eaf-053b-4f33-adfb-8b0cb1b5faef (denoise_latents): final_sigmas_type zero is not supported for algorithm_type deis. Please choose sigma_min instead. [2024-10-28 10:18:37,337]::[InvokeAI]::ERROR --> Traceback (most recent call last): File "C:\Users\vvv\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 "C:\Users\vvv\invokeai\.venv\lib\site-packages\invokeai\app\invocations\baseinvocation.py", line 290, in invoke_internal output = self.invoke(context) File "C:\Users\vvv\invokeai\.venv\lib\site-packages\invokeai\app\invocations\denoise_latents.py", line 792, in invoke return self._old_invoke(context) File "C:\Users\vvv\invokeai\.venv\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context return func(*args, **kwargs) File "C:\Python310\lib\contextlib.py", line 79, in inner return func(*args, **kwds) File "C:\Users\vvv\invokeai\.venv\lib\site-packages\invokeai\app\invocations\denoise_latents.py", line 1001, in _old_invoke scheduler = get_scheduler( File "C:\Users\vvv\invokeai\.venv\lib\site-packages\invokeai\app\invocations\denoise_latents.py", line 106, in get_scheduler scheduler = scheduler_class.from_config(scheduler_config) File "C:\Users\vvv\invokeai\.venv\lib\site-packages\diffusers\configuration_utils.py", line 259, in from_config model = cls(**init_dict) File "C:\Users\vvv\invokeai\.venv\lib\site-packages\diffusers\configuration_utils.py", line 653, in inner_init init(self, *args, **init_kwargs) File "C:\Users\vvv\invokeai\.venv\lib\site-packages\diffusers\schedulers\scheduling_dpmsolver_multistep.py", line 268, in __init__ raise ValueError( ValueError: final_sigmas_type zero is not supported for algorithm_type deis. Please choose sigma_min instead.

Hi got this problem too

I have the same issue

Same issue.

Same issue