mirror of
https://github.com/invoke-ai/InvokeAI.git
synced 2026-02-08 01:54:58 -05:00
Tensors with diffusers no longer have to be multiples of 8. This broke Perlin noise generation. We now generate noise for the next largest multiple of 8 and return a cropped result. Fixes #2674.
16 KiB
16 KiB