make_style

SHYuanBest · SHYuanBest · commit 33d429170c7a · 2024-12-10T15:35:40.000+08:00
diff --git a/examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py b/examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py
@@ -746,9 +746,9 @@ def initialize_new_tokens(self, inserting_toks: List[str]):
                 .to(dtype=self.dtype)
                 * std_token_embedding
             )
-            self.embeddings_settings[f"original_embeddings_{idx}"] = (
-                text_encoder.text_model.embeddings.token_embedding.weight.data.clone()
-            )
+            self.embeddings_settings[
+                f"original_embeddings_{idx}"
+            ] = text_encoder.text_model.embeddings.token_embedding.weight.data.clone()
             self.embeddings_settings[f"std_token_embedding_{idx}"] = std_token_embedding
 
             inu = torch.ones((len(tokenizer),), dtype=torch.bool)
diff --git a/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py b/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py
@@ -913,9 +913,9 @@ def initialize_new_tokens(self, inserting_toks: List[str]):
                 .to(dtype=self.dtype)
                 * std_token_embedding
             )
-            self.embeddings_settings[f"original_embeddings_{idx}"] = (
-                text_encoder.text_model.embeddings.token_embedding.weight.data.clone()
-            )
+            self.embeddings_settings[
+                f"original_embeddings_{idx}"
+            ] = text_encoder.text_model.embeddings.token_embedding.weight.data.clone()
             self.embeddings_settings[f"std_token_embedding_{idx}"] = std_token_embedding
 
             inu = torch.ones((len(tokenizer),), dtype=torch.bool)
diff --git a/examples/research_projects/multi_token_textual_inversion/textual_inversion.py b/examples/research_projects/multi_token_textual_inversion/textual_inversion.py
@@ -830,9 +830,9 @@ def main():
                 # Let's make sure we don't update any embedding weights besides the newly added token
                 index_no_updates = get_mask(tokenizer, accelerator)
                 with torch.no_grad():
-                    accelerator.unwrap_model(text_encoder).get_input_embeddings().weight[index_no_updates] = (
-                        orig_embeds_params[index_no_updates]
-                    )
+                    accelerator.unwrap_model(text_encoder).get_input_embeddings().weight[
+                        index_no_updates
+                    ] = orig_embeds_params[index_no_updates]
 
             # Checks if the accelerator has performed an optimization step behind the scenes
             if accelerator.sync_gradients:
diff --git a/examples/research_projects/onnxruntime/textual_inversion/textual_inversion.py b/examples/research_projects/onnxruntime/textual_inversion/textual_inversion.py
@@ -886,9 +886,9 @@ def main():
                 index_no_updates[min(placeholder_token_ids) : max(placeholder_token_ids) + 1] = False
 
                 with torch.no_grad():
-                    accelerator.unwrap_model(text_encoder).get_input_embeddings().weight[index_no_updates] = (
-                        orig_embeds_params[index_no_updates]
-                    )
+                    accelerator.unwrap_model(text_encoder).get_input_embeddings().weight[
+                        index_no_updates
+                    ] = orig_embeds_params[index_no_updates]
 
             # Checks if the accelerator has performed an optimization step behind the scenes
             if accelerator.sync_gradients:
diff --git a/examples/textual_inversion/textual_inversion.py b/examples/textual_inversion/textual_inversion.py
@@ -910,9 +910,9 @@ def main():
                 index_no_updates[min(placeholder_token_ids) : max(placeholder_token_ids) + 1] = False
 
                 with torch.no_grad():
-                    accelerator.unwrap_model(text_encoder).get_input_embeddings().weight[index_no_updates] = (
-                        orig_embeds_params[index_no_updates]
-                    )
+                    accelerator.unwrap_model(text_encoder).get_input_embeddings().weight[
+                        index_no_updates
+                    ] = orig_embeds_params[index_no_updates]
 
             # Checks if the accelerator has performed an optimization step behind the scenes
             if accelerator.sync_gradients:
diff --git a/examples/textual_inversion/textual_inversion_sdxl.py b/examples/textual_inversion/textual_inversion_sdxl.py
@@ -965,12 +965,12 @@ def main():
                 index_no_updates_2[min(placeholder_token_ids_2) : max(placeholder_token_ids_2) + 1] = False
 
                 with torch.no_grad():
-                    accelerator.unwrap_model(text_encoder_1).get_input_embeddings().weight[index_no_updates] = (
-                        orig_embeds_params[index_no_updates]
-                    )
-                    accelerator.unwrap_model(text_encoder_2).get_input_embeddings().weight[index_no_updates_2] = (
-                        orig_embeds_params_2[index_no_updates_2]
-                    )
+                    accelerator.unwrap_model(text_encoder_1).get_input_embeddings().weight[
+                        index_no_updates
+                    ] = orig_embeds_params[index_no_updates]
+                    accelerator.unwrap_model(text_encoder_2).get_input_embeddings().weight[
+                        index_no_updates_2
+                    ] = orig_embeds_params_2[index_no_updates_2]
 
             # Checks if the accelerator has performed an optimization step behind the scenes
             if accelerator.sync_gradients:
diff --git a/scripts/convert_hunyuandit_controlnet_to_diffusers.py b/scripts/convert_hunyuandit_controlnet_to_diffusers.py
@@ -21,9 +21,9 @@ def main(args):
     model_config = HunyuanDiT2DControlNetModel.load_config(
         "Tencent-Hunyuan/HunyuanDiT-v1.2-Diffusers", subfolder="transformer"
     )
-    model_config["use_style_cond_and_image_meta_size"] = (
-        args.use_style_cond_and_image_meta_size
-    )  ### version <= v1.1: True; version >= v1.2: False
+    model_config[
+        "use_style_cond_and_image_meta_size"
+    ] = args.use_style_cond_and_image_meta_size  ### version <= v1.1: True; version >= v1.2: False
     print(model_config)
 
     for key in state_dict:
diff --git a/scripts/convert_hunyuandit_to_diffusers.py b/scripts/convert_hunyuandit_to_diffusers.py
@@ -19,9 +19,9 @@ def main(args):
 
     device = "cuda"
     model_config = HunyuanDiT2DModel.load_config("Tencent-Hunyuan/HunyuanDiT-Diffusers", subfolder="transformer")
-    model_config["use_style_cond_and_image_meta_size"] = (
-        args.use_style_cond_and_image_meta_size
-    )  ### version <= v1.1: True; version >= v1.2: False
+    model_config[
+        "use_style_cond_and_image_meta_size"
+    ] = args.use_style_cond_and_image_meta_size  ### version <= v1.1: True; version >= v1.2: False
 
     # input_size -> sample_size, text_dim -> cross_attention_dim
     for key in state_dict:
diff --git a/scripts/convert_mochi_to_diffusers.py b/scripts/convert_mochi_to_diffusers.py
@@ -303,9 +303,9 @@ def convert_mochi_vae_state_dict_to_diffusers(encoder_ckpt_path, decoder_ckpt_pa
 
         for i in range(down_block_layers[block]):
             # Convert resnets
-            new_state_dict[f"{prefix}down_blocks.{block}.resnets.{i}.norm1.norm_layer.weight"] = (
-                encoder_state_dict.pop(f"layers.{block+4}.layers.{i+1}.stack.0.weight")
-            )
+            new_state_dict[
+                f"{prefix}down_blocks.{block}.resnets.{i}.norm1.norm_layer.weight"
+            ] = encoder_state_dict.pop(f"layers.{block+4}.layers.{i+1}.stack.0.weight")
             new_state_dict[f"{prefix}down_blocks.{block}.resnets.{i}.norm1.norm_layer.bias"] = encoder_state_dict.pop(
                 f"layers.{block+4}.layers.{i+1}.stack.0.bias"
             )
@@ -315,9 +315,9 @@ def convert_mochi_vae_state_dict_to_diffusers(encoder_ckpt_path, decoder_ckpt_pa
             new_state_dict[f"{prefix}down_blocks.{block}.resnets.{i}.conv1.conv.bias"] = encoder_state_dict.pop(
                 f"layers.{block+4}.layers.{i+1}.stack.2.bias"
             )
-            new_state_dict[f"{prefix}down_blocks.{block}.resnets.{i}.norm2.norm_layer.weight"] = (
-                encoder_state_dict.pop(f"layers.{block+4}.layers.{i+1}.stack.3.weight")
-            )
+            new_state_dict[
+                f"{prefix}down_blocks.{block}.resnets.{i}.norm2.norm_layer.weight"
+            ] = encoder_state_dict.pop(f"layers.{block+4}.layers.{i+1}.stack.3.weight")
             new_state_dict[f"{prefix}down_blocks.{block}.resnets.{i}.norm2.norm_layer.bias"] = encoder_state_dict.pop(
                 f"layers.{block+4}.layers.{i+1}.stack.3.bias"
             )
diff --git a/scripts/convert_svd_to_diffusers.py b/scripts/convert_svd_to_diffusers.py
@@ -381,9 +381,9 @@ def convert_ldm_unet_checkpoint(
 
         # TODO resnet time_mixer.mix_factor
         if f"input_blocks.{i}.0.time_mixer.mix_factor" in unet_state_dict:
-            new_checkpoint[f"down_blocks.{block_id}.resnets.{layer_in_block_id}.time_mixer.mix_factor"] = (
-                unet_state_dict[f"input_blocks.{i}.0.time_mixer.mix_factor"]
-            )
+            new_checkpoint[
+                f"down_blocks.{block_id}.resnets.{layer_in_block_id}.time_mixer.mix_factor"
+            ] = unet_state_dict[f"input_blocks.{i}.0.time_mixer.mix_factor"]
 
         if len(attentions):
             paths = renew_attention_paths(attentions)
@@ -478,9 +478,9 @@ def convert_ldm_unet_checkpoint(
             )
 
             if f"output_blocks.{i}.0.time_mixer.mix_factor" in unet_state_dict:
-                new_checkpoint[f"up_blocks.{block_id}.resnets.{layer_in_block_id}.time_mixer.mix_factor"] = (
-                    unet_state_dict[f"output_blocks.{i}.0.time_mixer.mix_factor"]
-                )
+                new_checkpoint[
+                    f"up_blocks.{block_id}.resnets.{layer_in_block_id}.time_mixer.mix_factor"
+                ] = unet_state_dict[f"output_blocks.{i}.0.time_mixer.mix_factor"]
 
             output_block_list = {k: sorted(v) for k, v in output_block_list.items()}
             if ["conv.bias", "conv.weight"] in output_block_list.values():
diff --git a/src/diffusers/loaders/lora_conversion_utils.py b/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:
diff --git a/src/diffusers/pipelines/consisid/pipeline_consisid.py b/src/diffusers/pipelines/consisid/pipeline_consisid.py
@@ -90,6 +90,19 @@
 
 
 def draw_kps(image_pil, kps, color_list=[(255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 0), (255, 0, 255)]):
+    """
+    This function draws keypoints and the limbs connecting them on an image.
+
+    Parameters:
+    - image_pil (PIL.Image): Input image as a PIL object.
+    - kps (list of tuples): A list of keypoints where each keypoint is a tuple of (x, y) coordinates.
+    - color_list (list of tuples, optional): List of colors (in RGB format) for each keypoint. Default is a set of five
+      colors.
+
+    Returns:
+    - PIL.Image: Image with the keypoints and limbs drawn.
+    """
+
     stickwidth = 4
     limbSeq = np.array([[0, 2], [1, 2], [3, 2], [4, 2]])
     kps = np.array(kps)
@@ -120,17 +133,23 @@ def draw_kps(image_pil, kps, color_list=[(255, 0, 0), (0, 255, 0), (0, 0, 255),
     return out_img_pil
 
 
-def process_image(image, vae):
-    image_noise_sigma = torch.normal(mean=-3.0, std=0.5, size=(1,), device=image.device)
-    image_noise_sigma = torch.exp(image_noise_sigma).to(dtype=image.dtype)
-    noisy_image = torch.randn_like(image) * image_noise_sigma[:, None, None, None, None]
-    input_image = image + noisy_image
-    image_latent_dist = vae.encode(input_image).latent_dist
-    return image_latent_dist
-
-
 # Similar to diffusers.pipelines.hunyuandit.pipeline_hunyuandit.get_resize_crop_region_for_grid
 def get_resize_crop_region_for_grid(src, tgt_width, tgt_height):
+    """
+    This function calculates the resize and crop region for an image to fit a target width and height while preserving
+    the aspect ratio.
+
+    Parameters:
+    - src (tuple): A tuple containing the source image's height (h) and width (w).
+    - tgt_width (int): The target width to resize the image.
+    - tgt_height (int): The target height to resize the image.
+
+    Returns:
+    - tuple: Two tuples representing the crop region:
+        1. The top-left coordinates of the crop region.
+        2. The bottom-right coordinates of the crop region.
+    """
+
     tw = tgt_width
     th = tgt_height
     h, w = src
diff --git a/src/diffusers/pipelines/free_noise_utils.py b/src/diffusers/pipelines/free_noise_utils.py
@@ -341,9 +341,9 @@ def _encode_prompt_free_noise(
                 start_tensor = negative_prompt_embeds[i].unsqueeze(0)
                 end_tensor = negative_prompt_embeds[i + 1].unsqueeze(0)
 
-                negative_prompt_interpolation_embeds[start_frame : end_frame + 1] = (
-                    self._free_noise_prompt_interpolation_callback(start_frame, end_frame, start_tensor, end_tensor)
-                )
+                negative_prompt_interpolation_embeds[
+                    start_frame : end_frame + 1
+                ] = self._free_noise_prompt_interpolation_callback(start_frame, end_frame, start_tensor, end_tensor)
 
         prompt_embeds = prompt_interpolation_embeds
         negative_prompt_embeds = negative_prompt_interpolation_embeds
diff --git a/src/diffusers/quantizers/base.py b/src/diffusers/quantizers/base.py
@@ -215,15 +215,19 @@ def _dequantize(self, model):
         )
 
     @abstractmethod
-    def _process_model_before_weight_loading(self, model, **kwargs): ...
+    def _process_model_before_weight_loading(self, model, **kwargs):
+        ...
 
     @abstractmethod
-    def _process_model_after_weight_loading(self, model, **kwargs): ...
+    def _process_model_after_weight_loading(self, model, **kwargs):
+        ...
 
     @property
     @abstractmethod
-    def is_serializable(self): ...
+    def is_serializable(self):
+        ...
 
     @property
     @abstractmethod
-    def is_trainable(self): ...
+    def is_trainable(self):
+        ...
diff --git a/tests/pipelines/amused/test_amused.py b/tests/pipelines/amused/test_amused.py
@@ -124,7 +124,8 @@ def test_inference_batch_consistent(self, batch_sizes=[2]):
         self._test_inference_batch_consistent(batch_sizes=batch_sizes, batch_generator=False)
 
     @unittest.skip("aMUSEd does not support lists of generators")
-    def test_inference_batch_single_identical(self): ...
+    def test_inference_batch_single_identical(self):
+        ...
 
 
 @slow
diff --git a/tests/pipelines/amused/test_amused_img2img.py b/tests/pipelines/amused/test_amused_img2img.py
@@ -126,7 +126,8 @@ def test_inference_batch_consistent(self, batch_sizes=[2]):
         self._test_inference_batch_consistent(batch_sizes=batch_sizes, batch_generator=False)
 
     @unittest.skip("aMUSEd does not support lists of generators")
-    def test_inference_batch_single_identical(self): ...
+    def test_inference_batch_single_identical(self):
+        ...
 
 
 @slow
diff --git a/tests/pipelines/amused/test_amused_inpaint.py b/tests/pipelines/amused/test_amused_inpaint.py
@@ -130,7 +130,8 @@ def test_inference_batch_consistent(self, batch_sizes=[2]):
         self._test_inference_batch_consistent(batch_sizes=batch_sizes, batch_generator=False)
 
     @unittest.skip("aMUSEd does not support lists of generators")
-    def test_inference_batch_single_identical(self): ...
+    def test_inference_batch_single_identical(self):
+        ...
 
 
 @slow
