InvokeAI icon indicating copy to clipboard operation
InvokeAI copied to clipboard

[bug]: img2img fails with refiner and seamless

Open maryhipp opened this issue 1 year ago • 1 comments

Is there an existing issue for this problem?

  • [X] I have searched the existing issues

Operating system

Windows

GPU vendor

Nvidia (CUDA)

GPU model

No response

GPU VRAM

No response

Version number

4.0rc

Browser

chrome

Python dependencies

No response

What happened

If you try to invoke img2img with refiner and seamless enabled, you get an error

ERROR:InvocationServices:Error in session processor: Traceback (most recent call last):
  File "C:\Users\mary\dev\Invoke\invoke-worker\invoke_worker\app\services\cloud_session_processor.py", line 402, in __process
    self._invocation = self._queue_item.session.next()
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\mary\invokeai\.venv\Lib\site-packages\invokeai\app\services\shared\graph.py", line 824, in next
    self._prepare_inputs(next_node)
  File "C:\Users\mary\invokeai\.venv\Lib\site-packages\invokeai\app\services\shared\graph.py", line 1077, in _prepare_inputs
    setattr(
  File "C:\Users\mary\invokeai\.venv\Lib\site-packages\pydantic\main.py", line 792, in __setattr__
    self.__pydantic_validator__.validate_assignment(self, name, value)
pydantic_core._pydantic_core.ValidationError: 1 validation error for ImageToLatentsInvocation
vae
  Input should be a valid dictionary or instance of VAEField [type=model_type, input_value=None, input_type=NoneType]
    For further information visit https://errors.pydantic.dev/2.6/v/model_type
    ```

### What you expected to happen

No error

### How to reproduce the problem

_No response_

### Additional context

_No response_

### Discord username

_No response_

maryhipp avatar Mar 19 '24 19:03 maryhipp

Also fails with txt2imag on LatentsToImage invocation

maryhipp avatar Mar 19 '24 20:03 maryhipp