Spaces:
Running
on
Zero
API code failure
I used the code shown at API documentation
GonzaloMG/marigold-e2e-ft-depth but got this error:
gradio_client.exceptions.AppError: The upstream Gradio app has raised an exception but has not enabled verbose error reporting. To enable, set show_error=True in launch().
Hi,
The Gradio demo may crash if you provide RGB images that are too large to fit in memory during depth computation. We recommend resizing the input to the native Stable Diffusion resolution, with a maximum height or width of 768px.
This demo is intended as a lightweight interface for quick testing on the Hugging Face website.
For fast and reliable generation of depth or normals using our E2E-FT model, we provide a quick inference script in the official repository. It only requires diffusers and minimal setup.
Let us know if you run into any issues!