fix: Fixed type annotations for compatability with python 3.8 (#7648)

* Fixed type annotations for compatability with python 3.8

* Add required imports.

examples/community/pipeline_sdxl_style_aligned.py

@@ -151,7 +151,7 @@ def concat_first(feat: torch.Tensor, dim: int = 2, scale: float = 1.0) -> torch.
     return torch.cat((feat, feat_style), dim=dim)
 
 
-def calc_mean_std(feat: torch.Tensor, eps: float = 1e-5) -> tuple[torch.Tensor, torch.Tensor]:
+def calc_mean_std(feat: torch.Tensor, eps: float = 1e-5) -> Tuple[torch.Tensor, torch.Tensor]:
     feat_std = (feat.var(dim=-2, keepdims=True) + eps).sqrt()
     feat_mean = feat.mean(dim=-2, keepdims=True)
     return feat_mean, feat_std

examples/community/pipeline_stable_diffusion_xl_controlnet_adapter_inpaint.py

@@ -17,7 +17,7 @@
 
 import inspect
 from collections.abc import Callable
-from typing import Any, List, Optional, Union
+from typing import Any, Dict, List, Optional, Tuple, Union
 
 import numpy as np
 import PIL
@@ -1211,8 +1211,8 @@ def prepare_control_image(
     @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
         self,
-        prompt: Optional[Union[str, list[str]]] = None,
-        prompt_2: Optional[Union[str, list[str]]] = None,
+        prompt: Optional[Union[str, List[str]]] = None,
+        prompt_2: Optional[Union[str, List[str]]] = None,
         image: Optional[Union[torch.Tensor, PIL.Image.Image]] = None,
         mask_image: Optional[Union[torch.Tensor, PIL.Image.Image]] = None,
         adapter_image: PipelineImageInput = None,
@@ -1224,11 +1224,11 @@ def __call__(
         denoising_start: Optional[float] = None,
         denoising_end: Optional[float] = None,
         guidance_scale: float = 5.0,
-        negative_prompt: Optional[Union[str, list[str]]] = None,
-        negative_prompt_2: Optional[Union[str, list[str]]] = None,
+        negative_prompt: Optional[Union[str, List[str]]] = None,
+        negative_prompt_2: Optional[Union[str, List[str]]] = None,
         num_images_per_prompt: Optional[int] = 1,
         eta: float = 0.0,
-        generator: Optional[Union[torch.Generator, list[torch.Generator]]] = None,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
         latents: Optional[Union[torch.FloatTensor]] = None,
         prompt_embeds: Optional[torch.FloatTensor] = None,
         negative_prompt_embeds: Optional[torch.FloatTensor] = None,
@@ -1238,12 +1238,12 @@ def __call__(
         return_dict: bool = True,
         callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
         callback_steps: int = 1,
-        cross_attention_kwargs: Optional[dict[str, Any]] = None,
+        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
         guidance_rescale: float = 0.0,
-        original_size: Optional[tuple[int, int]] = None,
-        crops_coords_top_left: Optional[tuple[int, int]] = (0, 0),
-        target_size: Optional[tuple[int, int]] = None,
-        adapter_conditioning_scale: Optional[Union[float, list[float]]] = 1.0,
+        original_size: Optional[Tuple[int, int]] = None,
+        crops_coords_top_left: Optional[Tuple[int, int]] = (0, 0),
+        target_size: Optional[Tuple[int, int]] = None,
+        adapter_conditioning_scale: Optional[Union[float, List[float]]] = 1.0,
         cond_tau: float = 1.0,
         aesthetic_score: float = 6.0,
         negative_aesthetic_score: float = 2.5,

src/diffusers/pipelines/stable_video_diffusion/pipeline_stable_video_diffusion.py

@@ -637,7 +637,7 @@ def _filter2d(input, kernel):
 
     height, width = tmp_kernel.shape[-2:]
 
-    padding_shape: list[int] = _compute_padding([height, width])
+    padding_shape: List[int] = _compute_padding([height, width])
     input = torch.nn.functional.pad(input, padding_shape, mode="reflect")
 
     # kernel and input tensor reshape to align element-wise or batch-wise params