lightning-diffusion-component icon indicating copy to clipboard operation
lightning-diffusion-component copied to clipboard

Results 7 lightning-diffusion-component issues
Sort by recently updated
recently updated
newest added

Fixing example. Since this is using the datatypes from lightning, we need to merge the PR to [lightning](https://github.com/Lightning-AI/lightning/pull/16018) before merging this This is using PythonServer directly, instead of base diffusion,...

When running the `dreambooth.py` component locally, it fails when serving the model locally. ```python /home/thomas/Dreambooth_app/.venv/lib/python3.8/site-packages/torch/utils/checkpoint.py:25: UserWarning: None of the inputs have requires_grad=True. Gradients will be None warnings.warn("None of the inputs...

As a user, I want weights management to be completely abstracted away within the Diffusion Component.

enhancement

When running the `dreambooth_component.py` in the cloud with the following command: ```python lightning run app dreambooth_component.py --setup --cloud ``` It seems the script took almost 20 min from DeepSpeed compilation...

bug