[bug]: Black Images NVIDIA T1000 8GB

[creakyrock08847]

[bug]: Black Images NVIDIA T1000 8GB

[psychedelicious]

Did it work previously? If so, what was the last app version where it worked?

This line is interesting:

/home/invokeuser/venv/lib/python3.10/site-packages/diffusers/image_processor.py:90: RuntimeWarning: invalid value encountered in cast
  images = (images * 255).round().astype("uint8")

That's in the VaeImageProcessor class, as it tries to convert the numpy image into a PIL image. This code hasn't been changed in some time, but maybe something around it has been.

[creakyrock08847]

Did it work previously? If so, what was the last app version where it worked?

This line is interesting:

/home/invokeuser/venv/lib/python3.10/site-packages/diffusers/image_processor.py:90: RuntimeWarning: invalid value encountered in cast
  images = (images * 255).round().astype("uint8")

That's in the VaeImageProcessor class, as it tries to convert the numpy image into a PIL image. This code hasn't been changed in some time, but maybe something around it has been.

It has never worked.

[psychedelicious]

Ok. I believe this issue is related to the GPU and its supported precision settings.

Let's try forcing fp32 precision for the whole app.

In the invokeai.yaml file, add a Device: section if it doesn't already exist. Then, add precision: float32 under it:

InvokeAI:
  Device:
    precision: float32

You could also try precision: autocast.

Do either of those fix the issue?