[bug]: [4.0.0rc1] using TAESD as VAE throws error

[grunblatt-git]

Is there an existing issue for this problem?

• I have searched the existing issues

Operating system

macOS

GPU vendor

Apple Silicon (MPS)

GPU model

No response

GPU VRAM

24

Version number

4.0.0rc1

Browser

Chrome

Python dependencies

No response

What happened

When selecting TAESD (https://huggingface.co/madebyollin/taesd) as VAE Invoke throws the following error after image generation (before saving the image to the gallery).

[InvokeAI]::ERROR --> Traceback (most recent call last):
  File "invokeai/.venv/lib/python3.10/site-packages/invokeai/app/services/session_processor/session_processor_default.py", line 160, in _process
    outputs = self._invocation.invoke_internal(
  File "invokeai/.venv/lib/python3.10/site-packages/invokeai/app/invocations/baseinvocation.py", line 289, in invoke_internal
    return self.invoke(context)
  File "invokeai/.venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "invokeai/.venv/lib/python3.10/site-packages/invokeai/app/invocations/latent.py", line 840, in invoke
    assert isinstance(vae_info.model, (UNet2DConditionModel, AutoencoderKL))
AssertionError

What you expected to happen

Images can be generated with TAESD

How to reproduce the problem

(Re)install TAESD by pasting importing madebyollin/taesd from the model editor. Choose TAESD as VAE.
Optionally set VAE Precision to FP16 (this was required in Invoke v3.x.x to use taesd)

Additional context

Uninstalling and reinstalling taesd did not change the behavior

Discord username

No response

[Harvester62]

This issue has been fixed in main development branch and in the upcoming v4.0.0: #5936

[grunblatt-git]

fixed in 4.0.0rc2