Skip to content

Fix: update type hints for Tuple parameters across multiple files to support variable-length tuples #12544

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 3 commits into
base: main
Choose a base branch
from
Open

Fix: update type hints for Tuple parameters across multiple files to support variable-length tuples #12544

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
77eaf32
Fix: update type hints for Tuple parameters across multiple files to …
cesaryuan Oct 26, 2025
aba2793
Apply style fixes
github-actions[bot] Oct 28, 2025
0719bbe
Merge branch 'main' into fix-types
yiyixuxu Oct 28, 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
2 changes: 1 addition & 1 deletion examples/community/img2img_inpainting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ def check_size(image, height, width):
raise ValueError(f"Image size should be {height}x{width}, but got {h}x{w}")


def overlay_inner_image(image, inner_image, paste_offset: Tuple[int] = (0, 0)):
def overlay_inner_image(image, inner_image, paste_offset: Tuple[int, ...] = (0, 0)):
inner_image = inner_image.convert("RGBA")
image = image.convert("RGB")

Expand Down
12 changes: 6 additions & 6 deletions examples/community/matryoshka.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1966,16 +1966,16 @@ def __init__(
center_input_sample: bool = False,
flip_sin_to_cos: bool = True,
freq_shift: int = 0,
down_block_types: Tuple[str] = (
down_block_types: Tuple[str, ...] = (
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D",
),
mid_block_type: Optional[str] = "UNetMidBlock2DCrossAttn",
up_block_types: Tuple[str] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
up_block_types: Tuple[str, ...] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
only_cross_attention: Union[bool, Tuple[bool]] = False,
block_out_channels: Tuple[int] = (320, 640, 1280, 1280),
block_out_channels: Tuple[int, ...] = (320, 640, 1280, 1280),
layers_per_block: Union[int, Tuple[int]] = 2,
downsample_padding: int = 1,
mid_block_scale_factor: float = 1,
Expand Down Expand Up @@ -2294,10 +2294,10 @@ def __init__(

def _check_config(
self,
down_block_types: Tuple[str],
up_block_types: Tuple[str],
down_block_types: Tuple[str, ...],
up_block_types: Tuple[str, ...],
only_cross_attention: Union[bool, Tuple[bool]],
block_out_channels: Tuple[int],
block_out_channels: Tuple[int, ...],
layers_per_block: Union[int, Tuple[int]],
cross_attention_dim: Union[int, Tuple[int]],
transformer_layers_per_block: Union[int, Tuple[int], Tuple[Tuple[int]]],
Expand Down
6 changes: 3 additions & 3 deletions examples/community/pipeline_faithdiff_stable_diffusion_xl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -438,16 +438,16 @@ def __init__(
center_input_sample: bool = False,
flip_sin_to_cos: bool = True,
freq_shift: int = 0,
down_block_types: Tuple[str] = (
down_block_types: Tuple[str, ...] = (
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D",
),
mid_block_type: Optional[str] = "UNetMidBlock2DCrossAttn",
up_block_types: Tuple[str] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
up_block_types: Tuple[str, ...] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
only_cross_attention: Union[bool, Tuple[bool]] = False,
block_out_channels: Tuple[int] = (320, 640, 1280, 1280),
block_out_channels: Tuple[int, ...] = (320, 640, 1280, 1280),
layers_per_block: Union[int, Tuple[int]] = 2,
downsample_padding: int = 1,
mid_block_scale_factor: float = 1,
Expand Down
14 changes: 7 additions & 7 deletions src/diffusers/models/autoencoders/autoencoder_dc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,7 @@ def get_block(
attention_head_dim: int,
norm_type: str,
act_fn: str,
qkv_mutliscales: Tuple[int] = (),
qkv_mutliscales: Tuple[int, ...] = (),
):
if block_type == "ResBlock":
block = ResBlock(in_channels, out_channels, norm_type, act_fn)
Expand Down Expand Up @@ -206,8 +206,8 @@ def __init__(
latent_channels: int,
attention_head_dim: int = 32,
block_type: Union[str, Tuple[str]] = "ResBlock",
block_out_channels: Tuple[int] = (128, 256, 512, 512, 1024, 1024),
layers_per_block: Tuple[int] = (2, 2, 2, 2, 2, 2),
block_out_channels: Tuple[int, ...] = (128, 256, 512, 512, 1024, 1024),
layers_per_block: Tuple[int, ...] = (2, 2, 2, 2, 2, 2),
qkv_multiscales: Tuple[Tuple[int, ...], ...] = ((), (), (), (5,), (5,), (5,)),
downsample_block_type: str = "pixel_unshuffle",
out_shortcut: bool = True,
Expand Down Expand Up @@ -292,8 +292,8 @@ def __init__(
latent_channels: int,
attention_head_dim: int = 32,
block_type: Union[str, Tuple[str]] = "ResBlock",
block_out_channels: Tuple[int] = (128, 256, 512, 512, 1024, 1024),
layers_per_block: Tuple[int] = (2, 2, 2, 2, 2, 2),
block_out_channels: Tuple[int, ...] = (128, 256, 512, 512, 1024, 1024),
layers_per_block: Tuple[int, ...] = (2, 2, 2, 2, 2, 2),
qkv_multiscales: Tuple[Tuple[int, ...], ...] = ((), (), (), (5,), (5,), (5,)),
norm_type: Union[str, Tuple[str]] = "rms_norm",
act_fn: Union[str, Tuple[str]] = "silu",
Expand Down Expand Up @@ -440,8 +440,8 @@ def __init__(
decoder_block_types: Union[str, Tuple[str]] = "ResBlock",
encoder_block_out_channels: Tuple[int, ...] = (128, 256, 512, 512, 1024, 1024),
decoder_block_out_channels: Tuple[int, ...] = (128, 256, 512, 512, 1024, 1024),
encoder_layers_per_block: Tuple[int] = (2, 2, 2, 3, 3, 3),
decoder_layers_per_block: Tuple[int] = (3, 3, 3, 3, 3, 3),
encoder_layers_per_block: Tuple[int, ...] = (2, 2, 2, 3, 3, 3),
decoder_layers_per_block: Tuple[int, ...] = (3, 3, 3, 3, 3, 3),
encoder_qkv_multiscales: Tuple[Tuple[int, ...], ...] = ((), (), (), (5,), (5,), (5,)),
decoder_qkv_multiscales: Tuple[Tuple[int, ...], ...] = ((), (), (), (5,), (5,), (5,)),
upsample_block_type: str = "pixel_shuffle",
Expand Down
6 changes: 3 additions & 3 deletions src/diffusers/models/autoencoders/autoencoder_kl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,9 +78,9 @@ def __init__(
self,
in_channels: int = 3,
out_channels: int = 3,
down_block_types: Tuple[str] = ("DownEncoderBlock2D",),
up_block_types: Tuple[str] = ("UpDecoderBlock2D",),
block_out_channels: Tuple[int] = (64,),
down_block_types: Tuple[str, ...] = ("DownEncoderBlock2D",),
up_block_types: Tuple[str, ...] = ("UpDecoderBlock2D",),
block_out_channels: Tuple[int, ...] = (64,),
layers_per_block: int = 1,
act_fn: str = "silu",
latent_channels: int = 4,
Expand Down
6 changes: 3 additions & 3 deletions src/diffusers/models/autoencoders/autoencoder_kl_cogvideox.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -995,19 +995,19 @@ def __init__(
self,
in_channels: int = 3,
out_channels: int = 3,
down_block_types: Tuple[str] = (
down_block_types: Tuple[str, ...] = (
"CogVideoXDownBlock3D",
"CogVideoXDownBlock3D",
"CogVideoXDownBlock3D",
"CogVideoXDownBlock3D",
),
up_block_types: Tuple[str] = (
up_block_types: Tuple[str, ...] = (
"CogVideoXUpBlock3D",
"CogVideoXUpBlock3D",
"CogVideoXUpBlock3D",
"CogVideoXUpBlock3D",
),
block_out_channels: Tuple[int] = (128, 256, 256, 512),
block_out_channels: Tuple[int, ...] = (128, 256, 256, 512),
latent_channels: int = 16,
layers_per_block: int = 3,
act_fn: str = "silu",
Expand Down
2 changes: 1 addition & 1 deletion src/diffusers/models/autoencoders/autoencoder_kl_hunyuan_video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -653,7 +653,7 @@ def __init__(
"HunyuanVideoUpBlock3D",
"HunyuanVideoUpBlock3D",
),
block_out_channels: Tuple[int] = (128, 256, 512, 512),
block_out_channels: Tuple[int, ...] = (128, 256, 512, 512),
layers_per_block: int = 2,
act_fn: str = "silu",
norm_num_groups: int = 32,
Expand Down
2 changes: 1 addition & 1 deletion src/diffusers/models/autoencoders/autoencoder_kl_hunyuanimage_refiner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -601,7 +601,7 @@ def __init__(
in_channels: int = 3,
out_channels: int = 3,
latent_channels: int = 32,
block_out_channels: Tuple[int] = (128, 256, 512, 1024, 1024),
block_out_channels: Tuple[int, ...] = (128, 256, 512, 1024, 1024),
layers_per_block: int = 2,
spatial_compression_ratio: int = 16,
temporal_compression_ratio: int = 4,
Expand Down
4 changes: 2 additions & 2 deletions src/diffusers/models/autoencoders/autoencoder_kl_mochi.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -688,8 +688,8 @@ def __init__(
self,
in_channels: int = 15,
out_channels: int = 3,
encoder_block_out_channels: Tuple[int] = (64, 128, 256, 384),
decoder_block_out_channels: Tuple[int] = (128, 256, 512, 768),
encoder_block_out_channels: Tuple[int, ...] = (64, 128, 256, 384),
decoder_block_out_channels: Tuple[int, ...] = (128, 256, 512, 768),
latent_channels: int = 12,
layers_per_block: Tuple[int, ...] = (3, 3, 4, 6, 3),
act_fn: str = "silu",
Expand Down
2 changes: 1 addition & 1 deletion src/diffusers/models/autoencoders/autoencoder_kl_qwenimage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -679,7 +679,7 @@ def __init__(
self,
base_dim: int = 96,
z_dim: int = 16,
dim_mult: Tuple[int] = [1, 2, 4, 4],
dim_mult: Tuple[int, ...] = (1, 2, 4, 4),
num_res_blocks: int = 2,
attn_scales: List[float] = [],
temperal_downsample: List[bool] = [False, True, True],
Expand Down
6 changes: 3 additions & 3 deletions src/diffusers/models/autoencoders/autoencoder_kl_temporal_decoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ def __init__(
self,
in_channels: int = 4,
out_channels: int = 3,
block_out_channels: Tuple[int] = (128, 256, 512, 512),
block_out_channels: Tuple[int, ...] = (128, 256, 512, 512),
layers_per_block: int = 2,
):
super().__init__()
Expand Down Expand Up @@ -172,8 +172,8 @@ def __init__(
self,
in_channels: int = 3,
out_channels: int = 3,
down_block_types: Tuple[str] = ("DownEncoderBlock2D",),
block_out_channels: Tuple[int] = (64,),
down_block_types: Tuple[str, ...] = ("DownEncoderBlock2D",),
block_out_channels: Tuple[int, ...] = (64,),
layers_per_block: int = 1,
latent_channels: int = 4,
sample_size: int = 32,
Expand Down
2 changes: 1 addition & 1 deletion 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 @@ -971,7 +971,7 @@ def __init__(
base_dim: int = 96,
decoder_base_dim: Optional[int] = None,
z_dim: int = 16,
dim_mult: Tuple[int] = [1, 2, 4, 4],
dim_mult: Tuple[int, ...] = (1, 2, 4, 4),
num_res_blocks: int = 2,
attn_scales: List[float] = [],
temperal_downsample: List[bool] = [False, True, True],
Expand Down
20 changes: 10 additions & 10 deletions src/diffusers/models/controlnets/controlnet_xs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -293,14 +293,14 @@ def __init__(
self,
conditioning_channels: int = 3,
conditioning_channel_order: str = "rgb",
conditioning_embedding_out_channels: Tuple[int] = (16, 32, 96, 256),
conditioning_embedding_out_channels: Tuple[int, ...] = (16, 32, 96, 256),
time_embedding_mix: float = 1.0,
learn_time_embedding: bool = False,
num_attention_heads: Union[int, Tuple[int]] = 4,
block_out_channels: Tuple[int] = (4, 8, 16, 16),
base_block_out_channels: Tuple[int] = (320, 640, 1280, 1280),
block_out_channels: Tuple[int, ...] = (4, 8, 16, 16),
base_block_out_channels: Tuple[int, ...] = (320, 640, 1280, 1280),
cross_attention_dim: int = 1024,
down_block_types: Tuple[str] = (
down_block_types: Tuple[str, ...] = (
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
Expand Down Expand Up @@ -436,7 +436,7 @@ def from_unet(
time_embedding_mix: int = 1.0,
conditioning_channels: int = 3,
conditioning_channel_order: str = "rgb",
conditioning_embedding_out_channels: Tuple[int] = (16, 32, 96, 256),
conditioning_embedding_out_channels: Tuple[int, ...] = (16, 32, 96, 256),
):
r"""
Instantiate a [`ControlNetXSAdapter`] from a [`UNet2DConditionModel`].
Expand Down Expand Up @@ -529,14 +529,14 @@ def __init__(
self,
# unet configs
sample_size: Optional[int] = 96,
down_block_types: Tuple[str] = (
down_block_types: Tuple[str, ...] = (
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D",
),
up_block_types: Tuple[str] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
block_out_channels: Tuple[int] = (320, 640, 1280, 1280),
up_block_types: Tuple[str, ...] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
block_out_channels: Tuple[int, ...] = (320, 640, 1280, 1280),
norm_num_groups: Optional[int] = 32,
cross_attention_dim: Union[int, Tuple[int]] = 1024,
transformer_layers_per_block: Union[int, Tuple[int]] = 1,
Expand All @@ -550,10 +550,10 @@ def __init__(
# additional controlnet configs
time_embedding_mix: float = 1.0,
ctrl_conditioning_channels: int = 3,
ctrl_conditioning_embedding_out_channels: Tuple[int] = (16, 32, 96, 256),
ctrl_conditioning_embedding_out_channels: Tuple[int, ...] = (16, 32, 96, 256),
ctrl_conditioning_channel_order: str = "rgb",
ctrl_learn_time_embedding: bool = False,
ctrl_block_out_channels: Tuple[int] = (4, 8, 16, 16),
ctrl_block_out_channels: Tuple[int, ...] = (4, 8, 16, 16),
ctrl_num_attention_heads: Union[int, Tuple[int]] = 4,
ctrl_max_norm_num_groups: int = 32,
):
Expand Down
2 changes: 1 addition & 1 deletion src/diffusers/models/transformers/transformer_hunyuan_video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -895,7 +895,7 @@ def __init__(
text_embed_dim: int = 4096,
pooled_projection_dim: int = 768,
rope_theta: float = 256.0,
rope_axes_dim: Tuple[int] = (16, 56, 56),
rope_axes_dim: Tuple[int, ...] = (16, 56, 56),
image_condition_type: Optional[str] = None,
) -> None:
super().__init__()
Expand Down
2 changes: 1 addition & 1 deletion src/diffusers/models/transformers/transformer_hunyuan_video_framepack.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,7 +139,7 @@ def __init__(
text_embed_dim: int = 4096,
pooled_projection_dim: int = 768,
rope_theta: float = 256.0,
rope_axes_dim: Tuple[int] = (16, 56, 56),
rope_axes_dim: Tuple[int, ...] = (16, 56, 56),
image_condition_type: Optional[str] = None,
has_image_proj: int = False,
image_proj_dim: int = 1152,
Expand Down
2 changes: 1 addition & 1 deletion src/diffusers/models/transformers/transformer_hunyuanimage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -689,7 +689,7 @@ def __init__(
text_embed_dim: int = 3584,
text_embed_2_dim: Optional[int] = None,
rope_theta: float = 256.0,
rope_axes_dim: Tuple[int] = (64, 64),
rope_axes_dim: Tuple[int, ...] = (64, 64),
use_meanflow: bool = False,
) -> None:
super().__init__()
Expand Down
2 changes: 1 addition & 1 deletion src/diffusers/models/transformers/transformer_skyreels_v2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -570,7 +570,7 @@ class SkyReelsV2Transformer3DModel(
@register_to_config
def __init__(
self,
patch_size: Tuple[int] = (1, 2, 2),
patch_size: Tuple[int, ...] = (1, 2, 2),
num_attention_heads: int = 16,
attention_head_dim: int = 128,
in_channels: int = 16,
Expand Down
2 changes: 1 addition & 1 deletion src/diffusers/models/transformers/transformer_wan.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -560,7 +560,7 @@ class WanTransformer3DModel(
@register_to_config
def __init__(
self,
patch_size: Tuple[int] = (1, 2, 2),
patch_size: Tuple[int, ...] = (1, 2, 2),
num_attention_heads: int = 40,
attention_head_dim: int = 128,
in_channels: int = 16,
Expand Down
2 changes: 1 addition & 1 deletion src/diffusers/models/transformers/transformer_wan_vace.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -182,7 +182,7 @@ class WanVACETransformer3DModel(
@register_to_config
def __init__(
self,
patch_size: Tuple[int] = (1, 2, 2),
patch_size: Tuple[int, ...] = (1, 2, 2),
num_attention_heads: int = 40,
attention_head_dim: int = 128,
in_channels: int = 16,
Expand Down
8 changes: 4 additions & 4 deletions src/diffusers/models/unets/unet_1d.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,11 +86,11 @@ def __init__(
flip_sin_to_cos: bool = True,
use_timestep_embedding: bool = False,
freq_shift: float = 0.0,
down_block_types: Tuple[str] = ("DownBlock1DNoSkip", "DownBlock1D", "AttnDownBlock1D"),
up_block_types: Tuple[str] = ("AttnUpBlock1D", "UpBlock1D", "UpBlock1DNoSkip"),
mid_block_type: Tuple[str] = "UNetMidBlock1D",
down_block_types: Tuple[str, ...] = ("DownBlock1DNoSkip", "DownBlock1D", "AttnDownBlock1D"),
up_block_types: Tuple[str, ...] = ("AttnUpBlock1D", "UpBlock1D", "UpBlock1DNoSkip"),
mid_block_type: str = "UNetMidBlock1D",
out_block_type: str = None,
block_out_channels: Tuple[int] = (32, 32, 64),
block_out_channels: Tuple[int, ...] = (32, 32, 64),
act_fn: str = None,
norm_num_groups: int = 8,
layers_per_block: int = 1,
Expand Down
12 changes: 6 additions & 6 deletions src/diffusers/models/unets/unet_2d_condition.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -177,16 +177,16 @@ def __init__(
center_input_sample: bool = False,
flip_sin_to_cos: bool = True,
freq_shift: int = 0,
down_block_types: Tuple[str] = (
down_block_types: Tuple[str, ...] = (
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"CrossAttnDownBlock2D",
"DownBlock2D",
),
mid_block_type: Optional[str] = "UNetMidBlock2DCrossAttn",
up_block_types: Tuple[str] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
up_block_types: Tuple[str, ...] = ("UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"),
only_cross_attention: Union[bool, Tuple[bool]] = False,
block_out_channels: Tuple[int] = (320, 640, 1280, 1280),
block_out_channels: Tuple[int, ...] = (320, 640, 1280, 1280),
layers_per_block: Union[int, Tuple[int]] = 2,
downsample_padding: int = 1,
mid_block_scale_factor: float = 1,
Expand Down Expand Up @@ -486,10 +486,10 @@ def __init__(

def _check_config(
self,
down_block_types: Tuple[str],
up_block_types: Tuple[str],
down_block_types: Tuple[str, ...],
up_block_types: Tuple[str, ...],
only_cross_attention: Union[bool, Tuple[bool]],
block_out_channels: Tuple[int],
block_out_channels: Tuple[int, ...],
layers_per_block: Union[int, Tuple[int]],
cross_attention_dim: Union[int, Tuple[int]],
transformer_layers_per_block: Union[int, Tuple[int], Tuple[Tuple[int]]],
Expand Down
2 changes: 1 addition & 1 deletion src/diffusers/models/unets/unet_kandinsky3.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ def __init__(
groups: int = 32,
attention_head_dim: int = 64,
layers_per_block: Union[int, Tuple[int]] = 3,
block_out_channels: Tuple[int] = (384, 768, 1536, 3072),
block_out_channels: Tuple[int, ...] = (384, 768, 1536, 3072),
cross_attention_dim: Union[int, Tuple[int]] = 4096,
encoder_hid_dim: int = 4096,
):
Expand Down
Loading
Loading