From f75b8aa9dd4a982dacaa94b9fd3bddcdcb821632 Mon Sep 17 00:00:00 2001 From: dg845 <58458699+dg845@users.noreply.github.com> Date: Mon, 21 Aug 2023 18:42:06 -0700 Subject: [PATCH] [docs] Add note in UniDiffusers Doc about PyTorch 1.X numerical stability issue (#4703) * Add note regarding UniDiffuser pipeline numerical stability issues on PyTorch 1.X * Use the doc-builder warning tag. --- docs/source/en/api/pipelines/unidiffuser.md | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/docs/source/en/api/pipelines/unidiffuser.md b/docs/source/en/api/pipelines/unidiffuser.md index ff8f4e7c6e..cc59b16871 100644 --- a/docs/source/en/api/pipelines/unidiffuser.md +++ b/docs/source/en/api/pipelines/unidiffuser.md @@ -20,6 +20,12 @@ The abstract from the [paper](https://arxiv.org/abs/2303.06555) is: You can find the original codebase at [thu-ml/unidiffuser](https://github.com/thu-ml/unidiffuser) and additional checkpoints at [thu-ml](https://huggingface.co/thu-ml). + + +There is currently an issue on PyTorch 1.X where the output images are all black or the pixel values become `NaNs`. This issue can be mitigated by switching to PyTorch 2.X. + + + This pipeline was contributed by [dg845](https://github.com/dg845). ❤️ ## Usage Examples