Fix: update type hints for Tuple parameters across multiple files to support...

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

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

* Apply style fixes

---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

examples/community/img2img_inpainting.py

@@ -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")
 

examples/community/matryoshka.py

@@ -1966,16 +1966,21 @@ class MatryoshkaUNet2DConditionModel(
         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,
@@ -2294,10 +2299,10 @@ class MatryoshkaUNet2DConditionModel(
 
     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]]],

examples/community/pipeline_faithdiff_stable_diffusion_xl.py

@@ -438,16 +438,21 @@ class UNet2DConditionModel(OriginalUNet2DConditionModel, ConfigMixin, UNet2DCond
         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,

src/diffusers/models/autoencoders/autoencoder_dc.py

@@ -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)
@@ -206,8 +206,8 @@ class Encoder(nn.Module):
         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,
@@ -292,8 +292,8 @@ class Decoder(nn.Module):
         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",
@@ -440,8 +440,8 @@ class AutoencoderDC(ModelMixin, AutoencoderMixin, ConfigMixin, FromOriginalModel
         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",

src/diffusers/models/autoencoders/autoencoder_kl.py

@@ -78,9 +78,9 @@ class AutoencoderKL(ModelMixin, AutoencoderMixin, ConfigMixin, FromOriginalModel
         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,

src/diffusers/models/autoencoders/autoencoder_kl_cogvideox.py

@@ -995,19 +995,19 @@ class AutoencoderKLCogVideoX(ModelMixin, AutoencoderMixin, ConfigMixin, FromOrig
         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",

src/diffusers/models/autoencoders/autoencoder_kl_hunyuan_video.py

@@ -653,7 +653,7 @@ class AutoencoderKLHunyuanVideo(ModelMixin, AutoencoderMixin, ConfigMixin):
             "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,

src/diffusers/models/autoencoders/autoencoder_kl_hunyuanimage_refiner.py

@@ -601,7 +601,7 @@ class AutoencoderKLHunyuanImageRefiner(ModelMixin, ConfigMixin):
         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,

src/diffusers/models/autoencoders/autoencoder_kl_mochi.py

@@ -688,8 +688,8 @@ class AutoencoderKLMochi(ModelMixin, AutoencoderMixin, ConfigMixin):
         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",

src/diffusers/models/autoencoders/autoencoder_kl_qwenimage.py

@@ -679,7 +679,7 @@ class AutoencoderKLQwenImage(ModelMixin, AutoencoderMixin, ConfigMixin, FromOrig
         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],

src/diffusers/models/autoencoders/autoencoder_kl_temporal_decoder.py

@@ -31,7 +31,7 @@ class TemporalDecoder(nn.Module):
         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__()
@@ -172,8 +172,8 @@ class AutoencoderKLTemporalDecoder(ModelMixin, AutoencoderMixin, ConfigMixin):
         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,

src/diffusers/models/autoencoders/autoencoder_kl_wan.py

@@ -971,7 +971,7 @@ class AutoencoderKLWan(ModelMixin, AutoencoderMixin, ConfigMixin, FromOriginalMo
         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],

src/diffusers/models/controlnets/controlnet_xs.py

@@ -293,14 +293,14 @@ class ControlNetXSAdapter(ModelMixin, ConfigMixin):
         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",
@@ -436,7 +436,7 @@ class ControlNetXSAdapter(ModelMixin, ConfigMixin):
         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`].
@@ -529,14 +529,19 @@ class UNetControlNetXSModel(ModelMixin, ConfigMixin):
         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,
@@ -550,10 +555,10 @@ class UNetControlNetXSModel(ModelMixin, ConfigMixin):
         # 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,
     ):

src/diffusers/models/transformers/transformer_hunyuan_video.py

@@ -914,7 +914,7 @@ class HunyuanVideoTransformer3DModel(ModelMixin, ConfigMixin, PeftAdapterMixin,
         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__()

src/diffusers/models/transformers/transformer_hunyuan_video_framepack.py

@@ -139,7 +139,7 @@ class HunyuanVideoFramepackTransformer3DModel(
         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,

src/diffusers/models/transformers/transformer_hunyuanimage.py

@@ -689,7 +689,7 @@ class HunyuanImageTransformer2DModel(ModelMixin, ConfigMixin, PeftAdapterMixin,
         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__()

src/diffusers/models/transformers/transformer_skyreels_v2.py

@@ -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,

src/diffusers/models/transformers/transformer_wan.py

@@ -563,7 +563,7 @@ 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,

src/diffusers/models/transformers/transformer_wan_vace.py

@@ -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,

src/diffusers/models/unets/unet_1d.py

@@ -86,11 +86,11 @@ class UNet1DModel(ModelMixin, ConfigMixin):
         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,