Allow to set config params directly in init (huggingface#1419)

* fix

* fix deprecated kwargs logic

* add tests

* finish

Author: patrickvonplaten

src/diffusers/configuration_utils.py

@@ -80,14 +80,18 @@ class ConfigMixin:
         - **config_name** (`str`) -- A filename under which the config should stored when calling
           [`~ConfigMixin.save_config`] (should be overridden by parent class).
         - **ignore_for_config** (`List[str]`) -- A list of attributes that should not be saved in the config (should be
-          overridden by parent class).
-        - **has_compatibles** (`bool`) -- Whether the class has compatible classes (should be overridden by parent
-          class).
+          overridden by subclass).
+        - **has_compatibles** (`bool`) -- Whether the class has compatible classes (should be overridden by subclass).
+        - **_deprecated_kwargs** (`List[str]`) -- Keyword arguments that are deprecated. Note that the init function
+          should only have a `kwargs` argument if at least one argument is deprecated (should be overridden by
+          subclass).
     """
     config_name = None
     ignore_for_config = []
     has_compatibles = False
 
+    _deprecated_kwargs = []
+
     def register_to_config(self, **kwargs):
         if self.config_name is None:
             raise NotImplementedError(f"Make sure that {self.__class__} has defined a class name `config_name`")
@@ -195,10 +199,10 @@ def from_config(cls, config: Union[FrozenDict, Dict[str, Any]] = None, return_un
         if "dtype" in unused_kwargs:
             init_dict["dtype"] = unused_kwargs.pop("dtype")
 
-        if "predict_epsilon" in unused_kwargs and "prediction_type" not in init_dict:
-            deprecate("remove this", "0.10.0", "remove")
-            predict_epsilon = unused_kwargs.pop("predict_epsilon")
-            init_dict["prediction_type"] = "epsilon" if predict_epsilon else "sample"
+        # add possible deprecated kwargs
+        for deprecated_kwarg in cls._deprecated_kwargs:
+            if deprecated_kwarg in unused_kwargs:
+                init_dict[deprecated_kwarg] = unused_kwargs.pop(deprecated_kwarg)
 
         # Return model and optionally state and/or unused_kwargs
         model = cls(**init_dict)
@@ -526,7 +530,6 @@ def inner_init(self, *args, **kwargs):
         # Ignore private kwargs in the init.
         init_kwargs = {k: v for k, v in kwargs.items() if not k.startswith("_")}
         config_init_kwargs = {k: v for k, v in kwargs.items() if k.startswith("_")}
-        init(self, *args, **init_kwargs)
         if not isinstance(self, ConfigMixin):
             raise RuntimeError(
                 f"`@register_for_config` was applied to {self.__class__.__name__} init method, but this class does "
@@ -553,6 +556,7 @@ def inner_init(self, *args, **kwargs):
         )
         new_kwargs = {**config_init_kwargs, **new_kwargs}
         getattr(self, "register_to_config")(**new_kwargs)
+        init(self, *args, **init_kwargs)
 
     return inner_init
 

src/diffusers/models/unet_2d_blocks.py

@@ -254,7 +254,6 @@ def __init__(
         attn_num_head_channels=1,
         attention_type="default",
         output_scale_factor=1.0,
-        **kwargs,
     ):
         super().__init__()
 
@@ -336,7 +335,6 @@ def __init__(
         cross_attention_dim=1280,
         dual_cross_attention=False,
         use_linear_projection=False,
-        **kwargs,
     ):
         super().__init__()
 

src/diffusers/pipelines/versatile_diffusion/modeling_text_unet.py

@@ -1039,7 +1039,6 @@ def __init__(
         cross_attention_dim=1280,
         dual_cross_attention=False,
         use_linear_projection=False,
-        **kwargs,
     ):
         super().__init__()
 

src/diffusers/schedulers/scheduling_ddim.py

@@ -113,6 +113,7 @@ class DDIMScheduler(SchedulerMixin, ConfigMixin):
     """
 
     _compatibles = _COMPATIBLE_STABLE_DIFFUSION_SCHEDULERS.copy()
+    _deprecated_kwargs = ["predict_epsilon"]
 
     @register_to_config
     def __init__(

src/diffusers/schedulers/scheduling_ddim_flax.py

@@ -116,6 +116,7 @@ class FlaxDDIMScheduler(FlaxSchedulerMixin, ConfigMixin):
     """
 
     _compatibles = _FLAX_COMPATIBLE_STABLE_DIFFUSION_SCHEDULERS.copy()
+    _deprecated_kwargs = ["predict_epsilon"]
 
     @property
     def has_state(self):

src/diffusers/schedulers/scheduling_ddpm.py

@@ -105,6 +105,7 @@ class DDPMScheduler(SchedulerMixin, ConfigMixin):
     """
 
     _compatibles = _COMPATIBLE_STABLE_DIFFUSION_SCHEDULERS.copy()
+    _deprecated_kwargs = ["predict_epsilon"]
 
     @register_to_config
     def __init__(

src/diffusers/schedulers/scheduling_ddpm_flax.py

@@ -109,6 +109,7 @@ class FlaxDDPMScheduler(FlaxSchedulerMixin, ConfigMixin):
     """
 
     _compatibles = _FLAX_COMPATIBLE_STABLE_DIFFUSION_SCHEDULERS.copy()
+    _deprecated_kwargs = ["predict_epsilon"]
 
     @property
     def has_state(self):

src/diffusers/schedulers/scheduling_dpmsolver_multistep.py

@@ -117,6 +117,7 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
     """
 
     _compatibles = _COMPATIBLE_STABLE_DIFFUSION_SCHEDULERS.copy()
+    _deprecated_kwargs = ["predict_epsilon"]
 
     @register_to_config
     def __init__(

src/diffusers/schedulers/scheduling_dpmsolver_multistep_flax.py

@@ -149,6 +149,7 @@ class FlaxDPMSolverMultistepScheduler(FlaxSchedulerMixin, ConfigMixin):
     """
 
     _compatibles = _FLAX_COMPATIBLE_STABLE_DIFFUSION_SCHEDULERS.copy()
+    _deprecated_kwargs = ["predict_epsilon"]
 
     @property
     def has_state(self):

tests/test_modeling_common.py

@@ -265,3 +265,23 @@ def test_enable_disable_gradient_checkpointing(self):
         # check disable works
         model.disable_gradient_checkpointing()
         self.assertFalse(model.is_gradient_checkpointing)
+
+    def test_deprecated_kwargs(self):
+        has_kwarg_in_model_class = "kwargs" in inspect.signature(self.model_class.__init__).parameters
+        has_deprecated_kwarg = len(self.model_class._deprecated_kwargs) > 0
+
+        if has_kwarg_in_model_class and not has_deprecated_kwarg:
+            raise ValueError(
+                f"{self.model_class} has `**kwargs` in its __init__ method but has not defined any deprecated kwargs"
+                " under the `_deprecated_kwargs` class attribute. Make sure to either remove `**kwargs` if there are"
+                " no deprecated arguments or add the deprecated argument with `_deprecated_kwargs ="
+                " [<deprecated_argument>]`"
+            )
+
+        if not has_kwarg_in_model_class and has_deprecated_kwarg:
+            raise ValueError(
+                f"{self.model_class} doesn't have `**kwargs` in its __init__ method but has defined deprecated kwargs"
+                " under the `_deprecated_kwargs` class attribute. Make sure to either add the `**kwargs` argument to"
+                f" {self.model_class}.__init__ if there are deprecated arguments or remove the deprecated argument"
+                " from `_deprecated_kwargs = [<deprecated_argument>]`"
+            )