up

LICENSE

@@ -144,7 +144,7 @@
       agreed to in writing, Licensor provides the Work (and each
       Contributor provides its Contributions) on an "AS IS" BASIS,
       WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
+      implied, including, without limitation, Any warranties or conditions
       of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
       PARTICULAR PURPOSE. You are solely responsible for determining the
       appropriateness of using or redistributing the Work and assume any

docs/source/en/using-diffusers/custom_pipeline_overview.md

@@ -121,7 +121,7 @@ from showone_unet_3d_condition import ShowOneUNet3DConditionModel
 unet = ShowOneUNet3DConditionModel.from_pretrained(pipeline_id, subfolder="unet")
 ```
 
-3. Load the custom pipeline code (already implemented in [pipeline_t2v_base_pixel.py](https://huggingface.co/sayakpaul/show-1-base-with-code/blob/main/pipeline_t2v_base_pixel.py)). This script contains a custom `TextToVideoIFPipeline` class for generating videos from text. Like the custom UNet, any code required for `TextToVideIFPipeline` should be placed in `pipeline_t2v_base_pixel.py`.
+3. Load the custom pipeline code (already implemented in [pipeline_t2v_base_pixel.py](https://huggingface.co/sayakpaul/show-1-base-with-code/blob/main/pipeline_t2v_base_pixel.py)). This script contains a custom `TextToVideoIFPipeline` class for generating videos from text. Like the custom UNet, Any code required for `TextToVideIFPipeline` should be placed in `pipeline_t2v_base_pixel.py`.
 
 Initialize `TextToVideoIFPipeline` with `ShowOneUNet3DConditionModel`.
 

docs/source/en/using-diffusers/other-formats.md

@@ -103,7 +103,7 @@ model = UNet2DConditionModel.from_single_file(ckpt_path, upcast_attention=True)
 
 ### Local files
 
-The [`~loaders.FromSingleFileMixin.from_single_file`] method attempts to configure a pipeline or model by inferring the model type from the keys in the checkpoint file. For example, any single file checkpoint based on the Stable Diffusion XL base model is configured from [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0).
+The [`~loaders.FromSingleFileMixin.from_single_file`] method attempts to configure a pipeline or model by inferring the model type from the keys in the checkpoint file. For example, Any single file checkpoint based on the Stable Diffusion XL base model is configured from [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0).
 
 If you're working with local files, download the config files with the [`~huggingface_hub.snapshot_download`] method and the model checkpoint with [`~huggingface_hub.hf_hub_download`]. These files are downloaded to your [cache directory](https://huggingface.co/docs/huggingface_hub/en/guides/manage-cache), but you can download them to a specific directory with the `local_dir` argument.
 

examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py

@@ -945,7 +945,7 @@ class TokenEmbeddingsHandler:
             new_token_embeddings = embeds.weight.data[train_ids]
 
             # New tokens for each text encoder are saved under "clip_l" (for text_encoder 0),
-            # Note: When loading with diffusers, any name can work - simply specify in inference
+            # Note: When loading with diffusers, Any name can work - simply specify in inference
             tensors[idx_to_text_encoder_name[idx]] = new_token_embeddings
             # tensors[f"text_encoders_{idx}"] = new_token_embeddings
 

examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py

@@ -801,7 +801,7 @@ class TokenEmbeddingsHandler:
 
             # New tokens for each text encoder are saved under "clip_l" (for text_encoder 0), "clip_g" (for
             # text_encoder 1) to keep compatible with the ecosystem.
-            # Note: When loading with diffusers, any name can work - simply specify in inference
+            # Note: When loading with diffusers, Any name can work - simply specify in inference
             tensors[idx_to_text_encoder_name[idx]] = new_token_embeddings
             # tensors[f"text_encoders_{idx}"] = new_token_embeddings
 

examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py

@@ -966,7 +966,7 @@ class TokenEmbeddingsHandler:
 
             # New tokens for each text encoder are saved under "clip_l" (for text_encoder 0), "clip_g" (for
             # text_encoder 1) to keep compatible with the ecosystem.
-            # Note: When loading with diffusers, any name can work - simply specify in inference
+            # Note: When loading with diffusers, Any name can work - simply specify in inference
             tensors[idx_to_text_encoder_name[idx]] = new_token_embeddings
             # tensors[f"text_encoders_{idx}"] = new_token_embeddings
 

examples/research_projects/sdxl_flax/README.md

@@ -231,7 +231,7 @@ images = generate(prompt, neg_prompt)
 print(f"First inference in {time.time() - start}")
 ```
 
-From this point forward, any calls to generate should result in a faster inference
+From this point forward, Any calls to generate should result in a faster inference
 time and it won't change.
 
 ```python

examples/research_projects/sdxl_flax/sdxl_single_aot.py

@@ -131,7 +131,7 @@ neg_prompt = "cartoon, illustration, animation. face. male, female"
 images = generate(prompt, neg_prompt)
 print(f"First inference in {time.time() - start}")
 
-# 9. From this point forward, any calls to generate should result in a faster inference
+# 9. From this point forward, Any calls to generate should result in a faster inference
 # time and it won't change.
 start = time.time()
 prompt = "photo of a rhino dressed suit and tie sitting at a table in a bar with a bar stools, award winning photography, Elke vogelsang"

src/diffusers/modular_pipelines/modular_pipeline.py

@@ -1616,7 +1616,7 @@ class ModularPipeline(ConfigMixin, PushToHubMixin):
             params[input_param.name] = input_param.default
         return params
 
-    def get_default_blocks_name(self, config_dict: Optional[dict[str, any]]) -> Optional[str]:
+    def get_default_blocks_name(self, config_dict: Optional[dict[str, Any]]) -> Optional[str]:
         return self.default_blocks_name
 
     @classmethod

src/diffusers/pipelines/audioldm2/modeling_audioldm2.py

@@ -13,6 +13,7 @@
 # limitations under the License.
 
 from dataclasses import dataclass
+from typing import Any
 
 import torch
 import torch.nn as nn
@@ -27,10 +28,7 @@ from ...models.attention_processor import (
     AttnAddedKVProcessor,
     AttnProcessor,
 )
-from ...models.embeddings import (
-    TimestepEmbedding,
-    Timesteps,
-)
+from ...models.embeddings import TimestepEmbedding, Timesteps
 from ...models.modeling_utils import ModelMixin
 from ...models.resnet import Downsample2D, ResnetBlock2D, Upsample2D
 from ...models.transformers.transformer_2d import Transformer2DModel
@@ -619,7 +617,7 @@ class AudioLDM2UNet2DConditionModel(ModelMixin, AttentionMixin, ConfigMixin, UNe
         class_labels: torch.Tensor | None = None,
         timestep_cond: torch.Tensor | None = None,
         attention_mask: torch.Tensor | None = None,
-        cross_attention_kwargs: dict[str, any] | None = None,
+        cross_attention_kwargs: dict[str, Any] | None = None,
         encoder_attention_mask: torch.Tensor | None = None,
         return_dict: bool = True,
         encoder_hidden_states_1: torch.Tensor | None = None,
@@ -1029,7 +1027,7 @@ class CrossAttnDownBlock2D(nn.Module):
         temb: torch.Tensor | None = None,
         encoder_hidden_states: torch.Tensor | None = None,
         attention_mask: torch.Tensor | None = None,
-        cross_attention_kwargs: dict[str, any] | None = None,
+        cross_attention_kwargs: dict[str, Any] | None = None,
         encoder_attention_mask: torch.Tensor | None = None,
         encoder_hidden_states_1: torch.Tensor | None = None,
         encoder_attention_mask_1: torch.Tensor | None = None,
@@ -1191,7 +1189,7 @@ class UNetMidBlock2DCrossAttn(nn.Module):
         temb: torch.Tensor | None = None,
         encoder_hidden_states: torch.Tensor | None = None,
         attention_mask: torch.Tensor | None = None,
-        cross_attention_kwargs: dict[str, any] | None = None,
+        cross_attention_kwargs: dict[str, Any] | None = None,
         encoder_attention_mask: torch.Tensor | None = None,
         encoder_hidden_states_1: torch.Tensor | None = None,
         encoder_attention_mask_1: torch.Tensor | None = None,
@@ -1341,7 +1339,7 @@ class CrossAttnUpBlock2D(nn.Module):
         res_hidden_states_tuple: tuple[torch.Tensor, ...],
         temb: torch.Tensor | None = None,
         encoder_hidden_states: torch.Tensor | None = None,
-        cross_attention_kwargs: dict[str, any] | None = None,
+        cross_attention_kwargs: dict[str, Any] | None = None,
         upsample_size: int | None = None,
         attention_mask: torch.Tensor | None = None,
         encoder_attention_mask: torch.Tensor | None = None,

src/diffusers/pipelines/deprecated/versatile_diffusion/modeling_text_unet.py

@@ -1042,7 +1042,7 @@ class UNetFlatConditionModel(ModelMixin, ConfigMixin):
         class_labels: torch.Tensor | None = None,
         timestep_cond: torch.Tensor | None = None,
         attention_mask: torch.Tensor | None = None,
-        cross_attention_kwargs: dict[str, any] | None = None,
+        cross_attention_kwargs: dict[str, Any] | None = None,
         added_cond_kwargs: dict[str, torch.Tensor] | None = None,
         down_block_additional_residuals: tuple[torch.Tensor] | None = None,
         mid_block_additional_residual: torch.Tensor | None = None,
@@ -1698,7 +1698,7 @@ class CrossAttnDownBlockFlat(nn.Module):
         temb: torch.Tensor | None = None,
         encoder_hidden_states: torch.Tensor | None = None,
         attention_mask: torch.Tensor | None = None,
-        cross_attention_kwargs: dict[str, any] | None = None,
+        cross_attention_kwargs: dict[str, Any] | None = None,
         encoder_attention_mask: torch.Tensor | None = None,
         additional_residuals: torch.Tensor | None = None,
     ) -> tuple[torch.Tensor, tuple[torch.Tensor, ...]]:

src/diffusers/training_utils.py

@@ -436,7 +436,7 @@ def wrap_with_fsdp(
     offload: bool = True,
     use_orig_params: bool = True,
     limit_all_gathers: bool = True,
-    fsdp_kwargs: dict[str, any] | None = None,
+    fsdp_kwargs: dict[str, Any] | None = None,
     transformer_layer_cls: set[type[torch.nn.Module]] | None = None,
 ) -> FSDP:
     """
@@ -496,8 +496,8 @@ class EMAModel:
         inv_gamma: float | int = 1.0,
         power: float | int = 2 / 3,
         foreach: bool = False,
-        model_cls: any | None = None,
-        model_config: dict[str, any] | None = None,
+        model_cls: Any | None = None,
+        model_config: dict[str, Any] | None = None,
         **kwargs,
     ):
         """

tests/pipelines/hunyuan_video/test_hunyuan_image2video.py

@@ -371,13 +371,13 @@ class HunyuanVideoImageToVideoPipelineFastTests(
 
     # TODO(aryan): Create a dummy gemma model with smol vocab size
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_consistent(self):
         pass
 
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_single_identical(self):
         pass

tests/pipelines/hunyuan_video/test_hunyuan_skyreels_image2video.py

@@ -333,13 +333,13 @@ class HunyuanSkyreelsImageToVideoPipelineFastTests(
 
     # TODO(aryan): Create a dummy gemma model with smol vocab size
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_consistent(self):
         pass
 
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_single_identical(self):
         pass

tests/pipelines/hunyuan_video/test_hunyuan_video.py

@@ -346,13 +346,13 @@ class HunyuanVideoPipelineFastTests(
 
     # TODO(aryan): Create a dummy gemma model with smol vocab size
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_consistent(self):
         pass
 
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_single_identical(self):
         pass

tests/pipelines/hunyuan_video/test_hunyuan_video_framepack.py

@@ -392,13 +392,13 @@ class HunyuanVideoFramepackPipelineFastTests(
 
     # TODO(aryan): Create a dummy gemma model with smol vocab size
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_consistent(self):
         pass
 
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_single_identical(self):
         pass

tests/pipelines/pag/test_pag_sana.py

@@ -325,13 +325,13 @@ class SanaPAGPipelineFastTests(PipelineTesterMixin, unittest.TestCase):
 
     # TODO(aryan): Create a dummy gemma model with smol vocab size
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_consistent(self):
         pass
 
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_single_identical(self):
         pass

tests/pipelines/sana/test_sana.py

@@ -290,13 +290,13 @@ class SanaPipelineFastTests(PipelineTesterMixin, unittest.TestCase):
 
     # TODO(aryan): Create a dummy gemma model with smol vocab size
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_consistent(self):
         pass
 
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_single_identical(self):
         pass

tests/pipelines/sana/test_sana_controlnet.py

@@ -309,13 +309,13 @@ class SanaControlNetPipelineFastTests(PipelineTesterMixin, unittest.TestCase):
 
     # TODO(aryan): Create a dummy gemma model with smol vocab size
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_consistent(self):
         pass
 
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_single_identical(self):
         pass

tests/pipelines/sana/test_sana_sprint.py

@@ -283,13 +283,13 @@ class SanaSprintPipelineFastTests(PipelineTesterMixin, unittest.TestCase):
 
     # TODO(aryan): Create a dummy gemma model with smol vocab size
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_consistent(self):
         pass
 
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_single_identical(self):
         pass

tests/pipelines/sana/test_sana_sprint_img2img.py

@@ -295,13 +295,13 @@ class SanaSprintImg2ImgPipelineFastTests(PipelineTesterMixin, unittest.TestCase)
 
     # TODO(aryan): Create a dummy gemma model with smol vocab size
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_consistent(self):
         pass
 
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_single_identical(self):
         pass

tests/pipelines/sana_video/test_sana_video.py

@@ -185,13 +185,13 @@ class SanaVideoPipelineFastTests(PipelineTesterMixin, unittest.TestCase):
 
     # TODO(aryan): Create a dummy gemma model with smol vocab size
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_consistent(self):
         pass
 
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_single_identical(self):
         pass

tests/pipelines/sana_video/test_sana_video_i2v.py

@@ -196,13 +196,13 @@ class SanaImageToVideoPipelineFastTests(PipelineTesterMixin, unittest.TestCase):
 
     # TODO(aryan): Create a dummy gemma model with smol vocab size
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_consistent(self):
         pass
 
     @unittest.skip(
-        "A very small vocab size is used for fast tests. So, any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
+        "A very small vocab size is used for fast tests. So, Any kind of prompt other than the empty default used in other tests will lead to a embedding lookup error. This test uses a long prompt that causes the error."
     )
     def test_inference_batch_single_identical(self):
         pass