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

Merged

yiyixuxu merged 3 commits into huggingface:main from sywangyi:wan2.2_fix_tile

Oct 28, 2025

Merged

fix crash if tiling mode is enabled #12521

Changes from 1 commit

Commits

Show all changes

Select commit Hold shift + click to select a range

fix crash in tiling mode is enabled

sywangyi Oct 21, 2025

sywangyi Oct 21, 2025

Merge branch 'main' into wan2.2_fix_tile

sayakpaul Oct 28, 2025

File filter

Filter by extension

Conversations

Jump to

Jump to file

Failed to load files.

Loading

Diff view

Diff view

25 changes: 19 additions & 6 deletions src/diffusers/models/autoencoders/autoencoder_kl_wan.py

Show comments 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 +1380,7 @@ 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 +1396,15 @@ 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

Loading