pre-commit check

Author: JiayiZhangA

fastvideo/configs/configs.py

@@ -9,29 +9,6 @@
 logger = init_logger(__name__)
 
 
-class DatasetType(str, Enum):
-    """
-    Enumeration for different dataset types.
-    """
-    HF = "hf"
-    MERGED = "merged"
-
-    @classmethod
-    def from_string(cls, value: str) -> "DatasetType":
-        """Convert string to DatasetType enum."""
-        try:
-            return cls(value.lower())
-        except ValueError:
-            raise ValueError(
-                f"Invalid dataset type: {value}. Must be one of: {', '.join([m.value for m in cls])}"
-            ) from None
-
-    @classmethod
-    def choices(cls) -> list[str]:
-        """Get all available choices as strings for argparse."""
-        return [dataset_type.value for dataset_type in cls]
-
-
 class DatasetType(str, Enum):
     """
     Enumeration for different dataset types.

fastvideo/configs/models/encoders/clip.py

@@ -80,8 +80,7 @@ class CLIPTextConfig(TextEncoderConfig):
             "truncation": True,
             "max_length": 77,
             "return_tensors": "pt"
-        }
-    )
+        })
     num_hidden_layers_override: int | None = None
     require_post_norm: bool | None = None
     prefix: str = "clip"

fastvideo/pipelines/preprocess/hunyuan/hunyuan_preprocess_pipelines.py

@@ -9,13 +9,8 @@
 
 class PreprocessPipelineI2V(ComposedPipelineBase):
     _required_config_modules = [
-        "image_encoder", 
-        "image_processor", 
-        "text_encoder", 
-        "tokenizer",
-        "text_encoder_2",
-        "tokenizer_2",
-        "vae"
+        "image_encoder", "image_processor", "text_encoder", "tokenizer",
+        "text_encoder_2", "tokenizer_2", "vae"
     ]
 
     def create_pipeline_stages(self, fastvideo_args: FastVideoArgs):
@@ -58,12 +53,9 @@ def create_pipeline_stages(self, fastvideo_args: FastVideoArgs):
 
 class PreprocessPipelineT2V(ComposedPipelineBase):
     _required_config_modules = [
-        "text_encoder",
-        "tokenizer",
-        "text_encoder_2",
-        "tokenizer_2",
-        "vae"
+        "text_encoder", "tokenizer", "text_encoder_2", "tokenizer_2", "vae"
     ]
+
     def create_pipeline_stages(self, fastvideo_args: FastVideoArgs):
         assert fastvideo_args.preprocess_config is not None
         self.add_stage(stage_name="text_transform_stage",
@@ -73,27 +65,27 @@ def create_pipeline_stages(self, fastvideo_args: FastVideoArgs):
                            seed=fastvideo_args.preprocess_config.seed,
                        ))
         # llama_tokenizer_kwargs = {
-        #     "padding": "max_length", 
-        #     "truncation": True, 
-        #     "max_length": 256, 
+        #     "padding": "max_length",
+        #     "truncation": True,
+        #     "max_length": 256,
         #     "return_tensors": "pt"
         # }
         # clip_tokenizer_kwargs = {
-        #     "padding": "max_length", 
-        #     "truncation": True, 
-        #     "max_length": 77, 
+        #     "padding": "max_length",
+        #     "truncation": True,
+        #     "max_length": 77,
         #     "return_tensors": "pt"
         # }
         # if len(fastvideo_args.pipeline_config.text_encoder_configs) >= 2:
         #     fastvideo_args.pipeline_config.text_encoder_configs[0].tokenizer_kwargs = llama_tokenizer_kwargs
         #     fastvideo_args.pipeline_config.text_encoder_configs[1].tokenizer_kwargs = clip_tokenizer_kwargs
         text_encoders = [
-            self.get_module("text_encoder"),  
-            self.get_module("text_encoder_2")  
+            self.get_module("text_encoder"),
+            self.get_module("text_encoder_2")
         ]
         tokenizers = [
-            self.get_module("tokenizer"),      
-            self.get_module("tokenizer_2")   
+            self.get_module("tokenizer"),
+            self.get_module("tokenizer_2")
         ]
 
         self.add_stage(stage_name="prompt_encoding_stage",

fastvideo/workflow/preprocess/components.py

@@ -78,8 +78,8 @@ def __call__(self, batch: dict[str, Any]) -> bool:
 
     def _validate_data_type(self, batch: dict[str, Any]) -> bool:
         """Validate basic validity of data items"""
-        return not (batch["caption"] is None or batch["caption"] == ""
-                    or "fps" not in batch or batch["fps"] is None or batch["fps"] <= 0
+        return not (batch["caption"] is None or batch["caption"] == "" or "fps"
+                    not in batch or batch["fps"] is None or batch["fps"] <= 0
                     or batch["num_frames"] is None or batch["num_frames"] <= 0)
 
     def _validate_resolution(self, batch: dict[str, Any]) -> bool:
@@ -399,7 +399,6 @@ def _default_file_writer_fn(self, args_tuple: tuple) -> int:
         return written_count
 
 
-
 def build_dataset(preprocess_config: PreprocessConfig, split: str) -> Dataset:
     if preprocess_config.dataset_type == DatasetType.HF:
         dataset = load_dataset(preprocess_config.dataset_path, split=split)