AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-10-23 09:09:01 +03:00
Code Activity

make style

Browse Source
This commit is contained in:
Patrick von Platen
2023-03-01 16:20:52 +00:00
parent a03d41f344
commit a4bc76ce75
1 changed files with 5 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
src/diffusers/models/autoencoder_kl.py
View File

@@ -191,12 +191,11 @@ class AutoencoderKL(ModelMixin, ConfigMixin):
r"""Encode a batch of images using a tiled encoder.
Args:
When this option is enabled, the VAE will split the input tensor into tiles to compute encoding in several
steps. This is useful to keep memory use constant regardless of image size. The end result of tiled encoding is
steps. This is useful to keep memory use constant regardless of image size. The end result of tiled encoding is:
different from non-tiled encoding due to each tile using a different encoder. To avoid tiling artifacts, the
tiles overlap and are blended together to form a smooth output. You may still see tile-sized changes in the
look of the output, but they should be much less noticeable.
x (`torch.FloatTensor`): Input batch of images.
return_dict (`bool`, *optional*, defaults to `True`):
x (`torch.FloatTensor`): Input batch of images. return_dict (`bool`, *optional*, defaults to `True`):
Whether or not to return a [`AutoencoderKLOutput`] instead of a plain tuple.
"""
# Split the image into 512x512 tiles and encode them separately.
@@ -234,12 +233,12 @@ class AutoencoderKL(ModelMixin, ConfigMixin):
r"""Decode a batch of images using a tiled decoder.
Args:
When this option is enabled, the VAE will split the input tensor into tiles to compute decoding in several
steps. This is useful to keep memory use constant regardless of image size. The end result of tiled decoding is
steps. This is useful to keep memory use constant regardless of image size. The end result of tiled decoding is:
different from non-tiled decoding due to each tile using a different decoder. To avoid tiling artifacts, the
tiles overlap and are blended together to form a smooth output. You may still see tile-sized changes in the
look of the output, but they should be much less noticeable.
z (`torch.FloatTensor`): Input batch of latent vectors.
return_dict (`bool`, *optional*, defaults to `True`):
z (`torch.FloatTensor`): Input batch of latent vectors. return_dict (`bool`, *optional*, defaults to
`True`):
Whether or not to return a [`DecoderOutput`] instead of a plain tuple.
"""
# Split z into overlapping 64x64 tiles and decode them separately.