setback

Author: zRzRzRzRzRzRzR

src/diffusers/loaders/ip_adapter.py

@@ -292,7 +292,8 @@ def set_ip_adapter_scale(self, scale):
             ):
                 if len(scale_configs) != len(attn_processor.scale):
                     raise ValueError(
-                        f"Cannot assign {len(scale_configs)} scale_configs to {len(attn_processor.scale)} IP-Adapter."
+                        f"Cannot assign {len(scale_configs)} scale_configs to "
+                        f"{len(attn_processor.scale)} IP-Adapter."
                     )
                 elif len(scale_configs) == 1:
                     scale_configs = scale_configs * len(attn_processor.scale)
@@ -591,7 +592,8 @@ def LinearStrengthModel(start, finish, size):
             if isinstance(attn_processor, (FluxIPAdapterJointAttnProcessor2_0)):
                 if len(scale_configs) != len(attn_processor.scale):
                     raise ValueError(
-                        f"Cannot assign {len(scale_configs)} scale_configs to {len(attn_processor.scale)} IP-Adapter."
+                        f"Cannot assign {len(scale_configs)} scale_configs to "
+                        f"{len(attn_processor.scale)} IP-Adapter."
                     )
                 elif len(scale_configs) == 1:
                     scale_configs = scale_configs * len(attn_processor.scale)

src/diffusers/loaders/lora_conversion_utils.py

@@ -177,9 +177,9 @@ def _convert_non_diffusers_lora_to_diffusers(state_dict, unet_name="unet", text_
             # Store DoRA scale if present.
             if dora_present_in_unet:
                 dora_scale_key_to_replace = "_lora.down." if "_lora.down." in diffusers_name else ".lora.down."
-                unet_state_dict[diffusers_name.replace(dora_scale_key_to_replace, ".lora_magnitude_vector.")] = (
-                    state_dict.pop(key.replace("lora_down.weight", "dora_scale"))
-                )
+                unet_state_dict[
+                    diffusers_name.replace(dora_scale_key_to_replace, ".lora_magnitude_vector.")
+                ] = state_dict.pop(key.replace("lora_down.weight", "dora_scale"))
 
         # Handle text encoder LoRAs.
         elif lora_name.startswith(("lora_te_", "lora_te1_", "lora_te2_")):
@@ -199,13 +199,13 @@ def _convert_non_diffusers_lora_to_diffusers(state_dict, unet_name="unet", text_
                     "_lora.down." if "_lora.down." in diffusers_name else ".lora_linear_layer."
                 )
                 if lora_name.startswith(("lora_te_", "lora_te1_")):
-                    te_state_dict[diffusers_name.replace(dora_scale_key_to_replace_te, ".lora_magnitude_vector.")] = (
-                        state_dict.pop(key.replace("lora_down.weight", "dora_scale"))
-                    )
+                    te_state_dict[
+                        diffusers_name.replace(dora_scale_key_to_replace_te, ".lora_magnitude_vector.")
+                    ] = state_dict.pop(key.replace("lora_down.weight", "dora_scale"))
                 elif lora_name.startswith("lora_te2_"):
-                    te2_state_dict[diffusers_name.replace(dora_scale_key_to_replace_te, ".lora_magnitude_vector.")] = (
-                        state_dict.pop(key.replace("lora_down.weight", "dora_scale"))
-                    )
+                    te2_state_dict[
+                        diffusers_name.replace(dora_scale_key_to_replace_te, ".lora_magnitude_vector.")
+                    ] = state_dict.pop(key.replace("lora_down.weight", "dora_scale"))
 
         # Store alpha if present.
         if lora_name_alpha in state_dict:
@@ -684,21 +684,21 @@ def swap_scale_shift(weight):
 
     for lora_key in ["lora_A", "lora_B"]:
         ## time_text_embed.timestep_embedder <-  time_in
-        converted_state_dict[f"time_text_embed.timestep_embedder.linear_1.{lora_key}.weight"] = (
-            original_state_dict.pop(f"time_in.in_layer.{lora_key}.weight")
-        )
+        converted_state_dict[
+            f"time_text_embed.timestep_embedder.linear_1.{lora_key}.weight"
+        ] = original_state_dict.pop(f"time_in.in_layer.{lora_key}.weight")
         if f"time_in.in_layer.{lora_key}.bias" in original_state_dict_keys:
-            converted_state_dict[f"time_text_embed.timestep_embedder.linear_1.{lora_key}.bias"] = (
-                original_state_dict.pop(f"time_in.in_layer.{lora_key}.bias")
-            )
+            converted_state_dict[
+                f"time_text_embed.timestep_embedder.linear_1.{lora_key}.bias"
+            ] = original_state_dict.pop(f"time_in.in_layer.{lora_key}.bias")
 
-        converted_state_dict[f"time_text_embed.timestep_embedder.linear_2.{lora_key}.weight"] = (
-            original_state_dict.pop(f"time_in.out_layer.{lora_key}.weight")
-        )
+        converted_state_dict[
+            f"time_text_embed.timestep_embedder.linear_2.{lora_key}.weight"
+        ] = original_state_dict.pop(f"time_in.out_layer.{lora_key}.weight")
         if f"time_in.out_layer.{lora_key}.bias" in original_state_dict_keys:
-            converted_state_dict[f"time_text_embed.timestep_embedder.linear_2.{lora_key}.bias"] = (
-                original_state_dict.pop(f"time_in.out_layer.{lora_key}.bias")
-            )
+            converted_state_dict[
+                f"time_text_embed.timestep_embedder.linear_2.{lora_key}.bias"
+            ] = original_state_dict.pop(f"time_in.out_layer.{lora_key}.bias")
 
         ## time_text_embed.text_embedder <- vector_in
         converted_state_dict[f"time_text_embed.text_embedder.linear_1.{lora_key}.weight"] = original_state_dict.pop(
@@ -720,21 +720,21 @@ def swap_scale_shift(weight):
         # guidance
         has_guidance = any("guidance" in k for k in original_state_dict)
         if has_guidance:
-            converted_state_dict[f"time_text_embed.guidance_embedder.linear_1.{lora_key}.weight"] = (
-                original_state_dict.pop(f"guidance_in.in_layer.{lora_key}.weight")
-            )
+            converted_state_dict[
+                f"time_text_embed.guidance_embedder.linear_1.{lora_key}.weight"
+            ] = original_state_dict.pop(f"guidance_in.in_layer.{lora_key}.weight")
             if f"guidance_in.in_layer.{lora_key}.bias" in original_state_dict_keys:
-                converted_state_dict[f"time_text_embed.guidance_embedder.linear_1.{lora_key}.bias"] = (
-                    original_state_dict.pop(f"guidance_in.in_layer.{lora_key}.bias")
-                )
+                converted_state_dict[
+                    f"time_text_embed.guidance_embedder.linear_1.{lora_key}.bias"
+                ] = original_state_dict.pop(f"guidance_in.in_layer.{lora_key}.bias")
 
-            converted_state_dict[f"time_text_embed.guidance_embedder.linear_2.{lora_key}.weight"] = (
-                original_state_dict.pop(f"guidance_in.out_layer.{lora_key}.weight")
-            )
+            converted_state_dict[
+                f"time_text_embed.guidance_embedder.linear_2.{lora_key}.weight"
+            ] = original_state_dict.pop(f"guidance_in.out_layer.{lora_key}.weight")
             if f"guidance_in.out_layer.{lora_key}.bias" in original_state_dict_keys:
-                converted_state_dict[f"time_text_embed.guidance_embedder.linear_2.{lora_key}.bias"] = (
-                    original_state_dict.pop(f"guidance_in.out_layer.{lora_key}.bias")
-                )
+                converted_state_dict[
+                    f"time_text_embed.guidance_embedder.linear_2.{lora_key}.bias"
+                ] = original_state_dict.pop(f"guidance_in.out_layer.{lora_key}.bias")
 
         # context_embedder
         converted_state_dict[f"context_embedder.{lora_key}.weight"] = original_state_dict.pop(

src/diffusers/models/model_loading_utils.py

@@ -181,7 +181,7 @@ def load_state_dict(
                     ) from e
         except (UnicodeDecodeError, ValueError):
             raise OSError(
-                f"Unable to load weights from checkpoint file for '{checkpoint_file}' at '{checkpoint_file}'. "
+                f"Unable to load weights from checkpoint file for '{checkpoint_file}' " f"at '{checkpoint_file}'. "
             )
 
 

src/diffusers/models/transformers/transformer_2d.py

@@ -211,9 +211,9 @@ def _init_continuous_input(self, norm_type):
 
     def _init_vectorized_inputs(self, norm_type):
         assert self.config.sample_size is not None, "Transformer2DModel over discrete input must provide sample_size"
-        assert self.config.num_vector_embeds is not None, (
-            "Transformer2DModel over discrete input must provide num_embed"
-        )
+        assert (
+            self.config.num_vector_embeds is not None
+        ), "Transformer2DModel over discrete input must provide num_embed"
 
         self.height = self.config.sample_size
         self.width = self.config.sample_size

src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py

@@ -650,15 +650,15 @@ def check_inputs(
         if padding_mask_crop is not None:
             if not isinstance(image, PIL.Image.Image):
                 raise ValueError(
-                    f"The image should be a PIL image when inpainting mask crop, but is of type {type(image)}."
+                    f"The image should be a PIL image when inpainting mask crop, but is of type" f" {type(image)}."
                 )
             if not isinstance(mask_image, PIL.Image.Image):
                 raise ValueError(
                     f"The mask image should be a PIL image when inpainting mask crop, but is of type"
                     f" {type(mask_image)}."
                 )
             if output_type != "pil":
-                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is {output_type}.")
+                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is" f" {output_type}.")
 
         # `prompt` needs more sophisticated handling when there are multiple
         # conditionings.

src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py

@@ -743,15 +743,15 @@ def check_inputs(
         if padding_mask_crop is not None:
             if not isinstance(image, PIL.Image.Image):
                 raise ValueError(
-                    f"The image should be a PIL image when inpainting mask crop, but is of type {type(image)}."
+                    f"The image should be a PIL image when inpainting mask crop, but is of type" f" {type(image)}."
                 )
             if not isinstance(mask_image, PIL.Image.Image):
                 raise ValueError(
                     f"The mask image should be a PIL image when inpainting mask crop, but is of type"
                     f" {type(mask_image)}."
                 )
             if output_type != "pil":
-                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is {output_type}.")
+                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is" f" {output_type}.")
 
         if prompt_embeds is not None and pooled_prompt_embeds is None:
             raise ValueError(
@@ -1644,7 +1644,7 @@ def denoising_value_valid(dnv):
                     f"Incorrect configuration settings! The config of `pipeline.unet`: {self.unet.config} expects"
                     f" {self.unet.config.in_channels} but received `num_channels_latents`: {num_channels_latents} +"
                     f" `num_channels_mask`: {num_channels_mask} + `num_channels_masked_image`: {num_channels_masked_image}"
-                    f" = {num_channels_latents + num_channels_masked_image + num_channels_mask}. Please verify the config of"
+                    f" = {num_channels_latents+num_channels_masked_image+num_channels_mask}. Please verify the config of"
                     " `pipeline.unet` or your `mask_image` or `image` input."
                 )
         elif num_channels_unet != 4:

src/diffusers/pipelines/controlnet/pipeline_controlnet_union_inpaint_sd_xl.py

@@ -726,15 +726,15 @@ def check_inputs(
         if padding_mask_crop is not None:
             if not isinstance(image, PIL.Image.Image):
                 raise ValueError(
-                    f"The image should be a PIL image when inpainting mask crop, but is of type {type(image)}."
+                    f"The image should be a PIL image when inpainting mask crop, but is of type" f" {type(image)}."
                 )
             if not isinstance(mask_image, PIL.Image.Image):
                 raise ValueError(
                     f"The mask image should be a PIL image when inpainting mask crop, but is of type"
                     f" {type(mask_image)}."
                 )
             if output_type != "pil":
-                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is {output_type}.")
+                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is" f" {output_type}.")
 
         if prompt_embeds is not None and pooled_prompt_embeds is None:
             raise ValueError(

src/diffusers/pipelines/flux/pipeline_flux_controlnet_inpainting.py

@@ -507,15 +507,15 @@ def check_inputs(
         if padding_mask_crop is not None:
             if not isinstance(image, PIL.Image.Image):
                 raise ValueError(
-                    f"The image should be a PIL image when inpainting mask crop, but is of type {type(image)}."
+                    f"The image should be a PIL image when inpainting mask crop, but is of type" f" {type(image)}."
                 )
             if not isinstance(mask_image, PIL.Image.Image):
                 raise ValueError(
                     f"The mask image should be a PIL image when inpainting mask crop, but is of type"
                     f" {type(mask_image)}."
                 )
             if output_type != "pil":
-                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is {output_type}.")
+                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is" f" {output_type}.")
 
         if max_sequence_length is not None and max_sequence_length > 512:
             raise ValueError(f"`max_sequence_length` cannot be greater than 512 but is {max_sequence_length}")

src/diffusers/pipelines/flux/pipeline_flux_inpaint.py

@@ -485,15 +485,15 @@ def check_inputs(
         if padding_mask_crop is not None:
             if not isinstance(image, PIL.Image.Image):
                 raise ValueError(
-                    f"The image should be a PIL image when inpainting mask crop, but is of type {type(image)}."
+                    f"The image should be a PIL image when inpainting mask crop, but is of type" f" {type(image)}."
                 )
             if not isinstance(mask_image, PIL.Image.Image):
                 raise ValueError(
                     f"The mask image should be a PIL image when inpainting mask crop, but is of type"
                     f" {type(mask_image)}."
                 )
             if output_type != "pil":
-                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is {output_type}.")
+                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is" f" {output_type}.")
 
         if max_sequence_length is not None and max_sequence_length > 512:
             raise ValueError(f"`max_sequence_length` cannot be greater than 512 but is {max_sequence_length}")

src/diffusers/pipelines/kandinsky/pipeline_kandinsky_combined.py

@@ -360,7 +360,7 @@ class KandinskyImg2ImgCombinedPipeline(DiffusionPipeline):
     """
 
     _load_connected_pipes = True
-    model_cpu_offload_seq = "prior_text_encoder->prior_image_encoder->prior_prior->text_encoder->unet->movq"
+    model_cpu_offload_seq = "prior_text_encoder->prior_image_encoder->prior_prior->" "text_encoder->unet->movq"
     _exclude_from_cpu_offload = ["prior_prior"]
 
     def __init__(