Skip to content

fix crash if tiling mode is enabled #12521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
+21 −6
Open

fix crash if tiling mode is enabled #12521

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0cc20ee
fix crash in tiling mode is enabled
sywangyi Oct 21, 2025
d777895
fmt
sywangyi Oct 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 21 additions & 6 deletions src/diffusers/models/autoencoders/autoencoder_kl_wan.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1355,9 +1355,18 @@ def tiled_decode(self, z: torch.Tensor, return_dict: bool = True) -> Union[Decod
tile_latent_min_width = self.tile_sample_min_width // self.spatial_compression_ratio
tile_latent_stride_height = self.tile_sample_stride_height // self.spatial_compression_ratio
tile_latent_stride_width = self.tile_sample_stride_width // self.spatial_compression_ratio

blend_height = self.tile_sample_min_height - self.tile_sample_stride_height
blend_width = self.tile_sample_min_width - self.tile_sample_stride_width
tile_sample_stride_height = self.tile_sample_stride_height
tile_sample_stride_width = self.tile_sample_stride_width
if self.config.patch_size is not None:
sample_height = sample_height // self.config.patch_size
sample_width = sample_width // self.config.patch_size
tile_sample_stride_height = tile_sample_stride_height // self.config.patch_size
tile_sample_stride_width = tile_sample_stride_width // self.config.patch_size
blend_height = self.tile_sample_min_height // self.config.patch_size - tile_sample_stride_height
blend_width = self.tile_sample_min_width // self.config.patch_size - tile_sample_stride_width
else:
blend_height = self.tile_sample_min_height - tile_sample_stride_height
blend_width = self.tile_sample_min_width - tile_sample_stride_width

# Split z into overlapping tiles and decode them separately.
# The tiles have an overlap to avoid seams between tiles.
Expand All @@ -1371,7 +1380,9 @@ def tiled_decode(self, z: torch.Tensor, return_dict: bool = True) -> Union[Decod
self._conv_idx = [0]
tile = z[:, :, k : k + 1, i : i + tile_latent_min_height, j : j + tile_latent_min_width]
tile = self.post_quant_conv(tile)
decoded = self.decoder(tile, feat_cache=self._feat_map, feat_idx=self._conv_idx)
decoded = self.decoder(
tile, feat_cache=self._feat_map, feat_idx=self._conv_idx, first_chunk=(k == 0)
)
time.append(decoded)
row.append(torch.cat(time, dim=2))
rows.append(row)
Expand All @@ -1387,11 +1398,15 @@ def tiled_decode(self, z: torch.Tensor, return_dict: bool = True) -> Union[Decod
tile = self.blend_v(rows[i - 1][j], tile, blend_height)
if j > 0:
tile = self.blend_h(row[j - 1], tile, blend_width)
result_row.append(tile[:, :, :, : self.tile_sample_stride_height, : self.tile_sample_stride_width])
result_row.append(tile[:, :, :, :tile_sample_stride_height, :tile_sample_stride_width])
result_rows.append(torch.cat(result_row, dim=-1))

dec = torch.cat(result_rows, dim=3)[:, :, :, :sample_height, :sample_width]

if self.config.patch_size is not None:
dec = unpatchify(dec, patch_size=self.config.patch_size)

dec = torch.clamp(dec, min=-1.0, max=1.0)

if not return_dict:
return (dec,)
return DecoderOutput(sample=dec)
Expand Down