Release: v0.33.1

* fix consisid imports

* fix opencv import

* fix

docs/source/en/_toctree.yml

@@ -265,6 +265,8 @@
     sections:
     - local: api/models/overview
       title: Overview
+    - local: api/models/auto_model
+      title: AutoModel
     - sections:
       - local: api/models/controlnet
         title: ControlNetModel

docs/source/en/api/models/auto_model.md

@@ -0,0 +1,29 @@
+<!--Copyright 2024 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# AutoModel
+
+The `AutoModel` is designed to make it easy to load a checkpoint without needing to know the specific model class. `AutoModel` automatically retrieves the correct model class from the checkpoint `config.json` file.
+
+```python
+from diffusers import AutoModel, AutoPipelineForText2Image
+
+unet = AutoModel.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="unet")
+pipe = AutoPipelineForText2Image.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", unet=unet)
+```
+
+
+## AutoModel
+
+[[autodoc]] AutoModel
+	- all
+	- from_pretrained

examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py

@@ -74,7 +74,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -839,9 +839,9 @@ class TokenEmbeddingsHandler:
         idx = 0
         for tokenizer, text_encoder in zip(self.tokenizers, self.text_encoders):
             assert isinstance(inserting_toks, list), "inserting_toks should be a list of strings."
-            assert all(
-                isinstance(tok, str) for tok in inserting_toks
-            ), "All elements in inserting_toks should be strings."
+            assert all(isinstance(tok, str) for tok in inserting_toks), (
+                "All elements in inserting_toks should be strings."
+            )
 
             self.inserting_toks = inserting_toks
             special_tokens_dict = {"additional_special_tokens": self.inserting_toks}
@@ -1605,7 +1605,7 @@ def main(args):
         lora_state_dict = FluxPipeline.lora_state_dict(input_dir)
 
         transformer_state_dict = {
-            f'{k.replace("transformer.", "")}': v for k, v in lora_state_dict.items() if k.startswith("transformer.")
+            f"{k.replace('transformer.', '')}": v for k, v in lora_state_dict.items() if k.startswith("transformer.")
         }
         transformer_state_dict = convert_unet_state_dict_to_peft(transformer_state_dict)
         incompatible_keys = set_peft_model_state_dict(transformer_, transformer_state_dict, adapter_name="default")

examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py

@@ -73,7 +73,7 @@ from diffusers.utils.import_utils import is_xformers_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -200,7 +200,8 @@ Special VAE used for training: {vae_path}.
         "diffusers",
         "diffusers-training",
         lora,
-        "template:sd-lora" "stable-diffusion",
+        "template:sd-lora",
+        "stable-diffusion",
         "stable-diffusion-diffusers",
     ]
     model_card = populate_model_card(model_card, tags=tags)
@@ -724,9 +725,9 @@ class TokenEmbeddingsHandler:
         idx = 0
         for tokenizer, text_encoder in zip(self.tokenizers, self.text_encoders):
             assert isinstance(inserting_toks, list), "inserting_toks should be a list of strings."
-            assert all(
-                isinstance(tok, str) for tok in inserting_toks
-            ), "All elements in inserting_toks should be strings."
+            assert all(isinstance(tok, str) for tok in inserting_toks), (
+                "All elements in inserting_toks should be strings."
+            )
 
             self.inserting_toks = inserting_toks
             special_tokens_dict = {"additional_special_tokens": self.inserting_toks}
@@ -746,9 +747,9 @@ class TokenEmbeddingsHandler:
                 .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)
@@ -1322,7 +1323,7 @@ def main(args):
 
         lora_state_dict, network_alphas = StableDiffusionPipeline.lora_state_dict(input_dir)
 
-        unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
+        unet_state_dict = {f"{k.replace('unet.', '')}": v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)
         incompatible_keys = set_peft_model_state_dict(unet_, unet_state_dict, adapter_name="default")
         if incompatible_keys is not None:

examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py

@@ -80,7 +80,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -890,9 +890,9 @@ class TokenEmbeddingsHandler:
         idx = 0
         for tokenizer, text_encoder in zip(self.tokenizers, self.text_encoders):
             assert isinstance(inserting_toks, list), "inserting_toks should be a list of strings."
-            assert all(
-                isinstance(tok, str) for tok in inserting_toks
-            ), "All elements in inserting_toks should be strings."
+            assert all(isinstance(tok, str) for tok in inserting_toks), (
+                "All elements in inserting_toks should be strings."
+            )
 
             self.inserting_toks = inserting_toks
             special_tokens_dict = {"additional_special_tokens": self.inserting_toks}
@@ -912,9 +912,9 @@ class TokenEmbeddingsHandler:
                 .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)
@@ -1647,7 +1647,7 @@ def main(args):
 
         lora_state_dict, network_alphas = StableDiffusionLoraLoaderMixin.lora_state_dict(input_dir)
 
-        unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
+        unet_state_dict = {f"{k.replace('unet.', '')}": v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)
         incompatible_keys = set_peft_model_state_dict(unet_, unet_state_dict, adapter_name="default")
         if incompatible_keys is not None:

examples/amused/train_amused.py

@@ -720,7 +720,7 @@ def main(args):
     # Train!
     logger.info("***** Running training *****")
     logger.info(f"  Num training steps = {args.max_train_steps}")
-    logger.info(f"  Instantaneous batch size per device = { args.train_batch_size}")
+    logger.info(f"  Instantaneous batch size per device = {args.train_batch_size}")
     logger.info(f"  Total train batch size (w. parallel, distributed & accumulation) = {total_batch_size}")
     logger.info(f"  Gradient Accumulation steps = {args.gradient_accumulation_steps}")
 

examples/cogvideo/train_cogvideox_image_to_video_lora.py

@@ -61,7 +61,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -1138,7 +1138,7 @@ def main(args):
         lora_state_dict = CogVideoXImageToVideoPipeline.lora_state_dict(input_dir)
 
         transformer_state_dict = {
-            f'{k.replace("transformer.", "")}': v for k, v in lora_state_dict.items() if k.startswith("transformer.")
+            f"{k.replace('transformer.', '')}": v for k, v in lora_state_dict.items() if k.startswith("transformer.")
         }
         transformer_state_dict = convert_unet_state_dict_to_peft(transformer_state_dict)
         incompatible_keys = set_peft_model_state_dict(transformer_, transformer_state_dict, adapter_name="default")

examples/cogvideo/train_cogvideox_lora.py

@@ -52,7 +52,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -1159,7 +1159,7 @@ def main(args):
         lora_state_dict = CogVideoXPipeline.lora_state_dict(input_dir)
 
         transformer_state_dict = {
-            f'{k.replace("transformer.", "")}': v for k, v in lora_state_dict.items() if k.startswith("transformer.")
+            f"{k.replace('transformer.', '')}": v for k, v in lora_state_dict.items() if k.startswith("transformer.")
         }
         transformer_state_dict = convert_unet_state_dict_to_peft(transformer_state_dict)
         incompatible_keys = set_peft_model_state_dict(transformer_, transformer_state_dict, adapter_name="default")

examples/cogview4-control/train_control_cogview4.py

@@ -59,7 +59,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 

examples/community/adaptive_mask_inpainting.py

@@ -1103,7 +1103,7 @@ class AdaptiveMaskInpaintPipeline(
                     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 `default_mask_image` or `image` input."
                 )
         elif num_channels_unet != 4:

examples/community/hd_painter.py

@@ -686,7 +686,7 @@ class StableDiffusionHDPainterPipeline(StableDiffusionInpaintPipeline):
                     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:

examples/community/img2img_inpainting.py

@@ -362,7 +362,7 @@ class ImageToImageInpaintingPipeline(DiffusionPipeline):
                 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."
             )
 

examples/community/llm_grounded_diffusion.py

@@ -1120,7 +1120,7 @@ class LLMGroundedDiffusionPipeline(
 
             if verbose:
                 logger.info(
-                    f"time index {index}, loss: {loss.item()/loss_scale:.3f} (de-scaled with scale {loss_scale:.1f}), loss threshold: {loss_threshold:.3f}"
+                    f"time index {index}, loss: {loss.item() / loss_scale:.3f} (de-scaled with scale {loss_scale:.1f}), loss threshold: {loss_threshold:.3f}"
                 )
 
             try:
@@ -1184,7 +1184,7 @@ class LLMGroundedDiffusionPipeline(
 
                     if verbose:
                         logger.info(
-                            f"time index {index}, loss: {loss.item()/loss_scale:.3f}, loss threshold: {loss_threshold:.3f}, iteration: {iteration}"
+                            f"time index {index}, loss: {loss.item() / loss_scale:.3f}, loss threshold: {loss_threshold:.3f}, iteration: {iteration}"
                         )
 
             finally:

examples/community/marigold_depth_estimation.py

@@ -43,8 +43,7 @@ from diffusers.utils import BaseOutput, check_min_version
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
-
+check_min_version("0.33.0")
 
 class MarigoldDepthOutput(BaseOutput):
     """

examples/community/mod_controlnet_tile_sr_sdxl.py

@@ -701,7 +701,7 @@ class StableDiffusionXLControlNetTileSRPipeline(
             raise ValueError("`max_tile_size` cannot be None.")
         elif not isinstance(max_tile_size, int) or max_tile_size not in (1024, 1280):
             raise ValueError(
-                f"`max_tile_size` has to be in 1024 or 1280 but is {max_tile_size} of type" f" {type(max_tile_size)}."
+                f"`max_tile_size` has to be in 1024 or 1280 but is {max_tile_size} of type {type(max_tile_size)}."
             )
         if tile_gaussian_sigma is None:
             raise ValueError("`tile_gaussian_sigma` cannot be None.")

examples/community/pipeline_flux_differential_img2img.py

@@ -488,7 +488,7 @@ class FluxDifferentialImg2ImgPipeline(DiffusionPipeline, FluxLoraLoaderMixin):
         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" f" {type(image)}."
+                    f"The image should be a PIL image when inpainting mask crop, but is of type {type(image)}."
                 )
             if not isinstance(mask_image, PIL.Image.Image):
                 raise ValueError(
@@ -496,7 +496,7 @@ class FluxDifferentialImg2ImgPipeline(DiffusionPipeline, FluxLoraLoaderMixin):
                     f" {type(mask_image)}."
                 )
             if output_type != "pil":
-                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is" f" {output_type}.")
+                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is {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}")

examples/community/pipeline_prompt2prompt.py

@@ -907,12 +907,12 @@ def create_controller(
 
     # reweight
     if edit_type == "reweight":
-        assert (
-            equalizer_words is not None and equalizer_strengths is not None
-        ), "To use reweight edit, please specify equalizer_words and equalizer_strengths."
-        assert len(equalizer_words) == len(
-            equalizer_strengths
-        ), "equalizer_words and equalizer_strengths must be of same length."
+        assert equalizer_words is not None and equalizer_strengths is not None, (
+            "To use reweight edit, please specify equalizer_words and equalizer_strengths."
+        )
+        assert len(equalizer_words) == len(equalizer_strengths), (
+            "equalizer_words and equalizer_strengths must be of same length."
+        )
         equalizer = get_equalizer(prompts[1], equalizer_words, equalizer_strengths, tokenizer=tokenizer)
         return AttentionReweight(
             prompts,

examples/community/pipeline_sdxl_style_aligned.py

@@ -1738,7 +1738,7 @@ class StyleAlignedSDXLPipeline(
                         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:

examples/community/pipeline_stable_diffusion_upscale_ldm3d.py

@@ -689,7 +689,7 @@ class StableDiffusionUpscaleLDM3DPipeline(
                 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_image`: {num_channels_image} "
-                f" = {num_channels_latents+num_channels_image}. Please verify the config of"
+                f" = {num_channels_latents + num_channels_image}. Please verify the config of"
                 " `pipeline.unet` or your `image` input."
             )
 

examples/community/pipeline_stable_diffusion_xl_attentive_eraser.py

@@ -1028,7 +1028,7 @@ class StableDiffusionXL_AE_Pipeline(
         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" f" {type(image)}."
+                    f"The image should be a PIL image when inpainting mask crop, but is of type {type(image)}."
                 )
             if not isinstance(mask_image, PIL.Image.Image):
                 raise ValueError(
@@ -1036,7 +1036,7 @@ class StableDiffusionXL_AE_Pipeline(
                     f" {type(mask_image)}."
                 )
             if output_type != "pil":
-                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is" f" {output_type}.")
+                raise ValueError(f"The output type should be PIL when inpainting mask crop, but is {output_type}.")
 
         if ip_adapter_image is not None and ip_adapter_image_embeds is not None:
             raise ValueError(
@@ -2050,7 +2050,7 @@ class StableDiffusionXL_AE_Pipeline(
                     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:

examples/community/pipeline_stable_diffusion_xl_controlnet_adapter_inpaint.py

@@ -1578,7 +1578,7 @@ class StableDiffusionXLControlNetAdapterInpaintPipeline(
                     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:

examples/community/scheduling_ufogen.py

@@ -288,8 +288,7 @@ class UFOGenScheduler(SchedulerMixin, ConfigMixin):
 
             if timesteps[0] >= self.config.num_train_timesteps:
                 raise ValueError(
-                    f"`timesteps` must start before `self.config.train_timesteps`:"
-                    f" {self.config.num_train_timesteps}."
+                    f"`timesteps` must start before `self.config.train_timesteps`: {self.config.num_train_timesteps}."
                 )
 
             timesteps = np.array(timesteps, dtype=np.int64)

examples/consistency_distillation/train_lcm_distill_lora_sd_wds.py

@@ -73,7 +73,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -89,7 +89,7 @@ def get_module_kohya_state_dict(module, prefix: str, dtype: torch.dtype, adapter
 
         # Set alpha parameter
         if "lora_down" in kohya_key:
-            alpha_key = f'{kohya_key.split(".")[0]}.alpha'
+            alpha_key = f"{kohya_key.split('.')[0]}.alpha"
             kohya_ss_state_dict[alpha_key] = torch.tensor(module.peft_config[adapter_name].lora_alpha).to(dtype)
 
     return kohya_ss_state_dict

examples/consistency_distillation/train_lcm_distill_lora_sdxl.py

@@ -66,7 +66,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -901,7 +901,7 @@ def main(args):
             unet_ = accelerator.unwrap_model(unet)
             lora_state_dict, _ = StableDiffusionXLPipeline.lora_state_dict(input_dir)
             unet_state_dict = {
-                f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")
+                f"{k.replace('unet.', '')}": v for k, v in lora_state_dict.items() if k.startswith("unet.")
             }
             unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)
             incompatible_keys = set_peft_model_state_dict(unet_, unet_state_dict, adapter_name="default")

examples/consistency_distillation/train_lcm_distill_lora_sdxl_wds.py

@@ -79,7 +79,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -95,7 +95,7 @@ def get_module_kohya_state_dict(module, prefix: str, dtype: torch.dtype, adapter
 
         # Set alpha parameter
         if "lora_down" in kohya_key:
-            alpha_key = f'{kohya_key.split(".")[0]}.alpha'
+            alpha_key = f"{kohya_key.split('.')[0]}.alpha"
             kohya_ss_state_dict[alpha_key] = torch.tensor(module.peft_config[adapter_name].lora_alpha).to(dtype)
 
     return kohya_ss_state_dict

examples/consistency_distillation/train_lcm_distill_sd_wds.py

@@ -72,7 +72,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 

examples/consistency_distillation/train_lcm_distill_sdxl_wds.py

@@ -78,7 +78,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 

examples/controlnet/train_controlnet.py

@@ -60,7 +60,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 

examples/controlnet/train_controlnet_flax.py

@@ -60,7 +60,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = logging.getLogger(__name__)
 

examples/controlnet/train_controlnet_flux.py

@@ -65,7 +65,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 if is_torch_npu_available():

examples/controlnet/train_controlnet_sd3.py

@@ -61,7 +61,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 

examples/controlnet/train_controlnet_sdxl.py

@@ -61,7 +61,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 if is_torch_npu_available():

examples/custom_diffusion/retrieve.py

@@ -50,9 +50,11 @@ def retrieve(class_prompt, class_data_dir, num_class_images):
     total = 0
     pbar = tqdm(desc="downloading real regularization images", total=num_class_images)
 
-    with open(f"{class_data_dir}/caption.txt", "w") as f1, open(f"{class_data_dir}/urls.txt", "w") as f2, open(
-        f"{class_data_dir}/images.txt", "w"
-    ) as f3:
+    with (
+        open(f"{class_data_dir}/caption.txt", "w") as f1,
+        open(f"{class_data_dir}/urls.txt", "w") as f2,
+        open(f"{class_data_dir}/images.txt", "w") as f3,
+    ):
         while total < num_class_images:
             images = class_images[count]
             count += 1

examples/custom_diffusion/train_custom_diffusion.py

@@ -63,7 +63,7 @@ from diffusers.utils.import_utils import is_xformers_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -731,18 +731,18 @@ def main(args):
             if not class_images_dir.exists():
                 class_images_dir.mkdir(parents=True, exist_ok=True)
             if args.real_prior:
-                assert (
-                    class_images_dir / "images"
-                ).exists(), f"Please run: python retrieve.py --class_prompt \"{concept['class_prompt']}\" --class_data_dir {class_images_dir} --num_class_images {args.num_class_images}"
-                assert (
-                    len(list((class_images_dir / "images").iterdir())) == args.num_class_images
-                ), f"Please run: python retrieve.py --class_prompt \"{concept['class_prompt']}\" --class_data_dir {class_images_dir} --num_class_images {args.num_class_images}"
-                assert (
-                    class_images_dir / "caption.txt"
-                ).exists(), f"Please run: python retrieve.py --class_prompt \"{concept['class_prompt']}\" --class_data_dir {class_images_dir} --num_class_images {args.num_class_images}"
-                assert (
-                    class_images_dir / "images.txt"
-                ).exists(), f"Please run: python retrieve.py --class_prompt \"{concept['class_prompt']}\" --class_data_dir {class_images_dir} --num_class_images {args.num_class_images}"
+                assert (class_images_dir / "images").exists(), (
+                    f'Please run: python retrieve.py --class_prompt "{concept["class_prompt"]}" --class_data_dir {class_images_dir} --num_class_images {args.num_class_images}'
+                )
+                assert len(list((class_images_dir / "images").iterdir())) == args.num_class_images, (
+                    f'Please run: python retrieve.py --class_prompt "{concept["class_prompt"]}" --class_data_dir {class_images_dir} --num_class_images {args.num_class_images}'
+                )
+                assert (class_images_dir / "caption.txt").exists(), (
+                    f'Please run: python retrieve.py --class_prompt "{concept["class_prompt"]}" --class_data_dir {class_images_dir} --num_class_images {args.num_class_images}'
+                )
+                assert (class_images_dir / "images.txt").exists(), (
+                    f'Please run: python retrieve.py --class_prompt "{concept["class_prompt"]}" --class_data_dir {class_images_dir} --num_class_images {args.num_class_images}'
+                )
                 concept["class_prompt"] = os.path.join(class_images_dir, "caption.txt")
                 concept["class_data_dir"] = os.path.join(class_images_dir, "images.txt")
                 args.concepts_list[i] = concept

examples/dreambooth/train_dreambooth.py

@@ -63,7 +63,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -1014,7 +1014,7 @@ def main(args):
 
     if args.train_text_encoder and unwrap_model(text_encoder).dtype != torch.float32:
         raise ValueError(
-            f"Text encoder loaded as datatype {unwrap_model(text_encoder).dtype}." f" {low_precision_error_string}"
+            f"Text encoder loaded as datatype {unwrap_model(text_encoder).dtype}. {low_precision_error_string}"
         )
 
     # Enable TF32 for faster training on Ampere GPUs,

examples/dreambooth/train_dreambooth_flax.py

@@ -35,7 +35,7 @@ from diffusers.utils import check_min_version
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 # Cache compiled models across invocations of this script.
 cc.initialize_cache(os.path.expanduser("~/.cache/jax/compilation_cache"))

examples/dreambooth/train_dreambooth_flux.py

@@ -65,7 +65,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 

examples/dreambooth/train_dreambooth_lora.py

@@ -74,7 +74,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -982,7 +982,7 @@ def main(args):
 
         lora_state_dict, network_alphas = StableDiffusionLoraLoaderMixin.lora_state_dict(input_dir)
 
-        unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
+        unet_state_dict = {f"{k.replace('unet.', '')}": v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)
         incompatible_keys = set_peft_model_state_dict(unet_, unet_state_dict, adapter_name="default")
 

examples/dreambooth/train_dreambooth_lora_flux.py

@@ -72,7 +72,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -1294,7 +1294,7 @@ def main(args):
         lora_state_dict = FluxPipeline.lora_state_dict(input_dir)
 
         transformer_state_dict = {
-            f'{k.replace("transformer.", "")}': v for k, v in lora_state_dict.items() if k.startswith("transformer.")
+            f"{k.replace('transformer.', '')}": v for k, v in lora_state_dict.items() if k.startswith("transformer.")
         }
         transformer_state_dict = convert_unet_state_dict_to_peft(transformer_state_dict)
         incompatible_keys = set_peft_model_state_dict(transformer_, transformer_state_dict, adapter_name="default")

examples/dreambooth/train_dreambooth_lora_lumina2.py

@@ -72,7 +72,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -1053,7 +1053,7 @@ def main(args):
         lora_state_dict = Lumina2Text2ImgPipeline.lora_state_dict(input_dir)
 
         transformer_state_dict = {
-            f'{k.replace("transformer.", "")}': v for k, v in lora_state_dict.items() if k.startswith("transformer.")
+            f"{k.replace('transformer.', '')}": v for k, v in lora_state_dict.items() if k.startswith("transformer.")
         }
         transformer_state_dict = convert_unet_state_dict_to_peft(transformer_state_dict)
         incompatible_keys = set_peft_model_state_dict(transformer_, transformer_state_dict, adapter_name="default")

examples/dreambooth/train_dreambooth_lora_sana.py

@@ -71,7 +71,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -1064,7 +1064,7 @@ def main(args):
         lora_state_dict = SanaPipeline.lora_state_dict(input_dir)
 
         transformer_state_dict = {
-            f'{k.replace("transformer.", "")}': v for k, v in lora_state_dict.items() if k.startswith("transformer.")
+            f"{k.replace('transformer.', '')}": v for k, v in lora_state_dict.items() if k.startswith("transformer.")
         }
         transformer_state_dict = convert_unet_state_dict_to_peft(transformer_state_dict)
         incompatible_keys = set_peft_model_state_dict(transformer_, transformer_state_dict, adapter_name="default")

examples/dreambooth/train_dreambooth_lora_sd3.py

@@ -72,7 +72,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -1355,7 +1355,7 @@ def main(args):
         lora_state_dict = StableDiffusion3Pipeline.lora_state_dict(input_dir)
 
         transformer_state_dict = {
-            f'{k.replace("transformer.", "")}': v for k, v in lora_state_dict.items() if k.startswith("transformer.")
+            f"{k.replace('transformer.', '')}": v for k, v in lora_state_dict.items() if k.startswith("transformer.")
         }
         transformer_state_dict = convert_unet_state_dict_to_peft(transformer_state_dict)
         incompatible_keys = set_peft_model_state_dict(transformer_, transformer_state_dict, adapter_name="default")

examples/dreambooth/train_dreambooth_lora_sdxl.py

@@ -79,7 +79,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -118,7 +118,7 @@ def save_model_card(
             )
 
     model_description = f"""
-# {'SDXL' if 'playground' not in base_model else 'Playground'} LoRA DreamBooth - {repo_id}
+# {"SDXL" if "playground" not in base_model else "Playground"} LoRA DreamBooth - {repo_id}
 
 <Gallery />
 
@@ -1286,7 +1286,7 @@ def main(args):
 
         lora_state_dict, network_alphas = StableDiffusionLoraLoaderMixin.lora_state_dict(input_dir)
 
-        unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
+        unet_state_dict = {f"{k.replace('unet.', '')}": v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)
         incompatible_keys = set_peft_model_state_dict(unet_, unet_state_dict, adapter_name="default")
         if incompatible_keys is not None:

examples/dreambooth/train_dreambooth_sd3.py

@@ -63,7 +63,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 

examples/flux-control/train_control_flux.py

@@ -54,7 +54,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 

examples/flux-control/train_control_lora_flux.py

@@ -57,7 +57,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -91,9 +91,9 @@ def log_validation(flux_transformer, args, accelerator, weight_dtype, step, is_f
             torch_dtype=weight_dtype,
         )
         pipeline.load_lora_weights(args.output_dir)
-        assert (
-            pipeline.transformer.config.in_channels == initial_channels * 2
-        ), f"{pipeline.transformer.config.in_channels=}"
+        assert pipeline.transformer.config.in_channels == initial_channels * 2, (
+            f"{pipeline.transformer.config.in_channels=}"
+        )
 
     pipeline.to(accelerator.device)
     pipeline.set_progress_bar_config(disable=True)
@@ -954,7 +954,7 @@ def main(args):
 
             lora_state_dict = FluxControlPipeline.lora_state_dict(input_dir)
             transformer_lora_state_dict = {
-                f'{k.replace("transformer.", "")}': v
+                f"{k.replace('transformer.', '')}": v
                 for k, v in lora_state_dict.items()
                 if k.startswith("transformer.") and "lora" in k
             }

examples/instruct_pix2pix/train_instruct_pix2pix.py

@@ -58,7 +58,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/instruct_pix2pix/train_instruct_pix2pix_sdxl.py

@@ -60,7 +60,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/kandinsky2_2/text_to_image/train_text_to_image_decoder.py

@@ -52,7 +52,7 @@ if is_wandb_available():
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/kandinsky2_2/text_to_image/train_text_to_image_lora_decoder.py

@@ -46,7 +46,7 @@ from diffusers.utils import check_min_version, is_wandb_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/kandinsky2_2/text_to_image/train_text_to_image_lora_prior.py

@@ -46,7 +46,7 @@ from diffusers.utils import check_min_version, is_wandb_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/kandinsky2_2/text_to_image/train_text_to_image_prior.py

@@ -51,7 +51,7 @@ if is_wandb_available():
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/model_search/pipeline_easy.py

@@ -1081,9 +1081,9 @@ class AutoConfig:
                     f"textual_inversion_path: {search_word} -> {textual_inversion_path.model_status.site_url}"
                 )
 
-                pretrained_model_name_or_paths[
-                    pretrained_model_name_or_paths.index(search_word)
-                ] = textual_inversion_path.model_path
+                pretrained_model_name_or_paths[pretrained_model_name_or_paths.index(search_word)] = (
+                    textual_inversion_path.model_path
+                )
 
         self.load_textual_inversion(
             pretrained_model_name_or_paths, token=tokens, tokenizer=tokenizer, text_encoder=text_encoder, **kwargs

examples/research_projects/anytext/anytext.py

@@ -187,9 +187,9 @@ def get_clip_token_for_string(tokenizer, string):
         return_tensors="pt",
     )
     tokens = batch_encoding["input_ids"]
-    assert (
-        torch.count_nonzero(tokens - 49407) == 2
-    ), f"String '{string}' maps to more than a single token. Please use another string"
+    assert torch.count_nonzero(tokens - 49407) == 2, (
+        f"String '{string}' maps to more than a single token. Please use another string"
+    )
     return tokens[0, 1]
 
 

examples/research_projects/anytext/ocr_recog/RecSVTR.py

@@ -312,9 +312,9 @@ class PatchEmbed(nn.Module):
 
     def forward(self, x):
         B, C, H, W = x.shape
-        assert (
-            H == self.img_size[0] and W == self.img_size[1]
-        ), f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})."
+        assert H == self.img_size[0] and W == self.img_size[1], (
+            f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})."
+        )
         x = self.proj(x).flatten(2).permute(0, 2, 1)
         return x
 

examples/research_projects/colossalai/train_dreambooth_colossalai.py

@@ -619,7 +619,7 @@ def main(args):
 
             optimizer.step()
             lr_scheduler.step()
-            logger.info(f"max GPU_mem cost is {torch.cuda.max_memory_allocated()/2**20} MB", ranks=[0])
+            logger.info(f"max GPU_mem cost is {torch.cuda.max_memory_allocated() / 2**20} MB", ranks=[0])
             # Checks if the accelerator has performed an optimization step behind the scenes
             progress_bar.update(1)
             global_step += 1

examples/research_projects/controlnet/train_controlnet_webdataset.py

@@ -803,21 +803,20 @@ def parse_args(input_args=None):
         "--control_type",
         type=str,
         default="canny",
-        help=("The type of controlnet conditioning image to use. One of `canny`, `depth`" " Defaults to `canny`."),
+        help=("The type of controlnet conditioning image to use. One of `canny`, `depth` Defaults to `canny`."),
     )
     parser.add_argument(
         "--transformer_layers_per_block",
         type=str,
         default=None,
-        help=("The number of layers per block in the transformer. If None, defaults to" " `args.transformer_layers`."),
+        help=("The number of layers per block in the transformer. If None, defaults to `args.transformer_layers`."),
     )
     parser.add_argument(
         "--old_style_controlnet",
         action="store_true",
         default=False,
         help=(
-            "Use the old style controlnet, which is a single transformer layer with"
-            " a single head. Defaults to False."
+            "Use the old style controlnet, which is a single transformer layer with a single head. Defaults to False."
         ),
     )
 

examples/research_projects/diffusion_dpo/train_diffusion_dpo.py

@@ -86,7 +86,7 @@ def import_model_class_from_model_name_or_path(pretrained_model_name_or_path: st
 
 
 def log_validation(args, unet, accelerator, weight_dtype, epoch, is_final_validation=False):
-    logger.info(f"Running validation... \n Generating images with prompts:\n" f" {VALIDATION_PROMPTS}.")
+    logger.info(f"Running validation... \n Generating images with prompts:\n {VALIDATION_PROMPTS}.")
 
     # create pipeline
     pipeline = DiffusionPipeline.from_pretrained(

examples/research_projects/diffusion_dpo/train_diffusion_dpo_sdxl.py

@@ -91,7 +91,7 @@ def import_model_class_from_model_name_or_path(
 
 
 def log_validation(args, unet, vae, accelerator, weight_dtype, epoch, is_final_validation=False):
-    logger.info(f"Running validation... \n Generating images with prompts:\n" f" {VALIDATION_PROMPTS}.")
+    logger.info(f"Running validation... \n Generating images with prompts:\n {VALIDATION_PROMPTS}.")
 
     if is_final_validation:
         if args.mixed_precision == "fp16":

examples/research_projects/diffusion_orpo/train_diffusion_orpo_sdxl_lora.py

@@ -91,7 +91,7 @@ def import_model_class_from_model_name_or_path(
 
 
 def log_validation(args, unet, vae, accelerator, weight_dtype, epoch, is_final_validation=False):
-    logger.info(f"Running validation... \n Generating images with prompts:\n" f" {VALIDATION_PROMPTS}.")
+    logger.info(f"Running validation... \n Generating images with prompts:\n {VALIDATION_PROMPTS}.")
 
     if is_final_validation:
         if args.mixed_precision == "fp16":
@@ -683,7 +683,7 @@ def main(args):
 
         lora_state_dict, network_alphas = StableDiffusionXLLoraLoaderMixin.lora_state_dict(input_dir)
 
-        unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
+        unet_state_dict = {f"{k.replace('unet.', '')}": v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)
         incompatible_keys = set_peft_model_state_dict(unet_, unet_state_dict, adapter_name="default")
         if incompatible_keys is not None:

examples/research_projects/diffusion_orpo/train_diffusion_orpo_sdxl_lora_wds.py

@@ -89,7 +89,7 @@ def import_model_class_from_model_name_or_path(
 
 
 def log_validation(args, unet, vae, accelerator, weight_dtype, epoch, is_final_validation=False):
-    logger.info(f"Running validation... \n Generating images with prompts:\n" f" {VALIDATION_PROMPTS}.")
+    logger.info(f"Running validation... \n Generating images with prompts:\n {VALIDATION_PROMPTS}.")
 
     if is_final_validation:
         if args.mixed_precision == "fp16":
@@ -790,7 +790,7 @@ def main(args):
 
         lora_state_dict, network_alphas = StableDiffusionXLLoraLoaderMixin.lora_state_dict(input_dir)
 
-        unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
+        unet_state_dict = {f"{k.replace('unet.', '')}": v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)
         incompatible_keys = set_peft_model_state_dict(unet_, unet_state_dict, adapter_name="default")
         if incompatible_keys is not None:

examples/research_projects/flux_lora_quantization/train_dreambooth_lora_flux_miniature.py

@@ -783,7 +783,7 @@ def main(args):
         lora_state_dict = FluxPipeline.lora_state_dict(input_dir)
 
         transformer_state_dict = {
-            f'{k.replace("transformer.", "")}': v for k, v in lora_state_dict.items() if k.startswith("transformer.")
+            f"{k.replace('transformer.', '')}": v for k, v in lora_state_dict.items() if k.startswith("transformer.")
         }
         transformer_state_dict = convert_unet_state_dict_to_peft(transformer_state_dict)
         incompatible_keys = set_peft_model_state_dict(transformer_, transformer_state_dict, adapter_name="default")

examples/research_projects/gligen/demo.ipynb

@@ -26,8 +26,7 @@
     "%load_ext autoreload\n",
     "%autoreload 2\n",
     "\n",
-    "import torch\n",
-    "from diffusers import StableDiffusionGLIGENTextImagePipeline, StableDiffusionGLIGENPipeline"
+    "from diffusers import StableDiffusionGLIGENPipeline"
    ]
   },
   {
@@ -36,28 +35,25 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
+    "from transformers import CLIPTextModel, CLIPTokenizer\n",
+    "\n",
     "import diffusers\n",
     "from diffusers import (\n",
     "    AutoencoderKL,\n",
     "    DDPMScheduler,\n",
-    "    UNet2DConditionModel,\n",
-    "    UniPCMultistepScheduler,\n",
     "    EulerDiscreteScheduler,\n",
+    "    UNet2DConditionModel,\n",
     ")\n",
-    "from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer\n",
+    "\n",
+    "\n",
     "# pretrained_model_name_or_path = 'masterful/gligen-1-4-generation-text-box'\n",
     "\n",
-    "pretrained_model_name_or_path = '/root/data/zhizhonghuang/checkpoints/models--masterful--gligen-1-4-generation-text-box/snapshots/d2820dc1e9ba6ca082051ce79cfd3eb468ae2c83'\n",
+    "pretrained_model_name_or_path = \"/root/data/zhizhonghuang/checkpoints/models--masterful--gligen-1-4-generation-text-box/snapshots/d2820dc1e9ba6ca082051ce79cfd3eb468ae2c83\"\n",
     "\n",
     "tokenizer = CLIPTokenizer.from_pretrained(pretrained_model_name_or_path, subfolder=\"tokenizer\")\n",
     "noise_scheduler = DDPMScheduler.from_pretrained(pretrained_model_name_or_path, subfolder=\"scheduler\")\n",
-    "text_encoder = CLIPTextModel.from_pretrained(\n",
-    "    pretrained_model_name_or_path, subfolder=\"text_encoder\"\n",
-    ")\n",
-    "vae = AutoencoderKL.from_pretrained(\n",
-    "    pretrained_model_name_or_path, subfolder=\"vae\"\n",
-    ")\n",
+    "text_encoder = CLIPTextModel.from_pretrained(pretrained_model_name_or_path, subfolder=\"text_encoder\")\n",
+    "vae = AutoencoderKL.from_pretrained(pretrained_model_name_or_path, subfolder=\"vae\")\n",
     "# unet = UNet2DConditionModel.from_pretrained(\n",
     "#     pretrained_model_name_or_path, subfolder=\"unet\"\n",
     "# )\n",
@@ -71,9 +67,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "unet = UNet2DConditionModel.from_pretrained(\n",
-    "    '/root/data/zhizhonghuang/ckpt/GLIGEN_Text_Retrain_COCO'\n",
-    ")"
+    "unet = UNet2DConditionModel.from_pretrained(\"/root/data/zhizhonghuang/ckpt/GLIGEN_Text_Retrain_COCO\")"
    ]
   },
   {
@@ -108,6 +102,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import numpy as np\n",
+    "\n",
+    "\n",
     "# prompt = 'A realistic image of landscape scene depicting a green car parking on the left of a blue truck, with a red air balloon and a bird in the sky'\n",
     "# gen_boxes = [('a green car', [21, 281, 211, 159]), ('a blue truck', [269, 283, 209, 160]), ('a red air balloon', [66, 8, 145, 135]), ('a bird', [296, 42, 143, 100])]\n",
     "\n",
@@ -117,10 +114,8 @@
     "# prompt = 'A realistic scene of three skiers standing in a line on the snow near a palm tree'\n",
     "# gen_boxes = [('a skier', [5, 152, 139, 168]), ('a skier', [278, 192, 121, 158]), ('a skier', [148, 173, 124, 155]), ('a palm tree', [404, 105, 103, 251])]\n",
     "\n",
-    "prompt = 'An oil painting of a pink dolphin jumping on the left of a steam boat on the sea'\n",
-    "gen_boxes = [('a steam boat', [232, 225, 257, 149]), ('a jumping pink dolphin', [21, 249, 189, 123])]\n",
-    "\n",
-    "import numpy as np\n",
+    "prompt = \"An oil painting of a pink dolphin jumping on the left of a steam boat on the sea\"\n",
+    "gen_boxes = [(\"a steam boat\", [232, 225, 257, 149]), (\"a jumping pink dolphin\", [21, 249, 189, 123])]\n",
     "\n",
     "boxes = np.array([x[1] for x in gen_boxes])\n",
     "boxes = boxes / 512\n",
@@ -166,7 +161,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "diffusers.utils.make_image_grid(images, 4, len(images)//4)"
+    "diffusers.utils.make_image_grid(images, 4, len(images) // 4)"
    ]
   },
   {
@@ -179,7 +174,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "densecaption",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -197,5 +192,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

examples/research_projects/instructpix2pix_lora/train_instruct_pix2pix_lora.py

@@ -15,8 +15,8 @@
 # limitations under the License.
 
 """
-    Script to fine-tune Stable Diffusion for LORA InstructPix2Pix.
-    Base code referred from: https://github.com/huggingface/diffusers/blob/main/examples/instruct_pix2pix/train_instruct_pix2pix.py
+Script to fine-tune Stable Diffusion for LORA InstructPix2Pix.
+Base code referred from: https://github.com/huggingface/diffusers/blob/main/examples/instruct_pix2pix/train_instruct_pix2pix.py
 """
 
 import argparse

examples/research_projects/multi_subject_dreambooth/train_multi_subject_dreambooth.py

@@ -763,9 +763,9 @@ def main(args):
         # Parse instance and class inputs, and double check that lengths match
         instance_data_dir = args.instance_data_dir.split(",")
         instance_prompt = args.instance_prompt.split(",")
-        assert all(
-            x == len(instance_data_dir) for x in [len(instance_data_dir), len(instance_prompt)]
-        ), "Instance data dir and prompt inputs are not of the same length."
+        assert all(x == len(instance_data_dir) for x in [len(instance_data_dir), len(instance_prompt)]), (
+            "Instance data dir and prompt inputs are not of the same length."
+        )
 
         if args.with_prior_preservation:
             class_data_dir = args.class_data_dir.split(",")
@@ -788,9 +788,9 @@ def main(args):
                     negative_validation_prompts.append(None)
             args.validation_negative_prompt = negative_validation_prompts
 
-            assert num_of_validation_prompts == len(
-                negative_validation_prompts
-            ), "The length of negative prompts for validation is greater than the number of validation prompts."
+            assert num_of_validation_prompts == len(negative_validation_prompts), (
+                "The length of negative prompts for validation is greater than the number of validation prompts."
+            )
             args.validation_inference_steps = [args.validation_inference_steps] * num_of_validation_prompts
             args.validation_guidance_scale = [args.validation_guidance_scale] * num_of_validation_prompts
 

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:

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:

examples/research_projects/promptdiffusion/pipeline_prompt_diffusion.py

@@ -663,8 +663,7 @@ class PromptDiffusionPipeline(
                     self.check_image(image, prompt, prompt_embeds)
         else:
             raise ValueError(
-                f"You have passed a list of images of length {len(image_pair)}."
-                f"Make sure the list size equals to two."
+                f"You have passed a list of images of length {len(image_pair)}.Make sure the list size equals to two."
             )
 
         # Check `controlnet_conditioning_scale`

examples/research_projects/pytorch_xla/training/text_to_image/train_text_to_image_xla.py

@@ -173,7 +173,7 @@ class TrainSD:
         if not dataloader_exception:
             xm.wait_device_ops()
             total_time = time.time() - last_time
-            print(f"Average step time: {total_time/(self.args.max_train_steps-measure_start_step)}")
+            print(f"Average step time: {total_time / (self.args.max_train_steps - measure_start_step)}")
         else:
             print("dataloader exception happen, skip result")
             return
@@ -622,7 +622,7 @@ def main(args):
     num_devices_per_host = num_devices // num_hosts
     if xm.is_master_ordinal():
         print("***** Running training *****")
-        print(f"Instantaneous batch size per device = {args.train_batch_size // num_devices_per_host }")
+        print(f"Instantaneous batch size per device = {args.train_batch_size // num_devices_per_host}")
         print(
             f"Total train batch size (w. parallel, distributed & accumulation) = {args.train_batch_size * num_hosts}"
         )

examples/research_projects/scheduled_huber_loss_training/dreambooth/train_dreambooth.py

@@ -1057,7 +1057,7 @@ def main(args):
 
     if args.train_text_encoder and unwrap_model(text_encoder).dtype != torch.float32:
         raise ValueError(
-            f"Text encoder loaded as datatype {unwrap_model(text_encoder).dtype}." f" {low_precision_error_string}"
+            f"Text encoder loaded as datatype {unwrap_model(text_encoder).dtype}. {low_precision_error_string}"
         )
 
     # Enable TF32 for faster training on Ampere GPUs,

examples/research_projects/scheduled_huber_loss_training/dreambooth/train_dreambooth_lora.py

@@ -1021,7 +1021,7 @@ def main(args):
 
         lora_state_dict, network_alphas = StableDiffusionLoraLoaderMixin.lora_state_dict(input_dir)
 
-        unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
+        unet_state_dict = {f"{k.replace('unet.', '')}": v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)
         incompatible_keys = set_peft_model_state_dict(unet_, unet_state_dict, adapter_name="default")
 

examples/research_projects/scheduled_huber_loss_training/dreambooth/train_dreambooth_lora_sdxl.py

@@ -118,7 +118,7 @@ def save_model_card(
             )
 
     model_description = f"""
-# {'SDXL' if 'playground' not in base_model else 'Playground'} LoRA DreamBooth - {repo_id}
+# {"SDXL" if "playground" not in base_model else "Playground"} LoRA DreamBooth - {repo_id}
 
 <Gallery />
 
@@ -1336,7 +1336,7 @@ def main(args):
 
         lora_state_dict, network_alphas = StableDiffusionLoraLoaderMixin.lora_state_dict(input_dir)
 
-        unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
+        unet_state_dict = {f"{k.replace('unet.', '')}": v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)
         incompatible_keys = set_peft_model_state_dict(unet_, unet_state_dict, adapter_name="default")
         if incompatible_keys is not None:

examples/research_projects/scheduled_huber_loss_training/text_to_image/train_text_to_image_lora_sdxl.py

@@ -750,7 +750,7 @@ def main(args):
                 raise ValueError(f"unexpected save model: {model.__class__}")
 
         lora_state_dict, _ = StableDiffusionLoraLoaderMixin.lora_state_dict(input_dir)
-        unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
+        unet_state_dict = {f"{k.replace('unet.', '')}": v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)
         incompatible_keys = set_peft_model_state_dict(unet_, unet_state_dict, adapter_name="default")
         if incompatible_keys is not None:

examples/research_projects/sd3_lora_colab/train_dreambooth_lora_sd3_miniature.py

@@ -765,7 +765,7 @@ def main(args):
         lora_state_dict = StableDiffusion3Pipeline.lora_state_dict(input_dir)
 
         transformer_state_dict = {
-            f'{k.replace("transformer.", "")}': v for k, v in lora_state_dict.items() if k.startswith("transformer.")
+            f"{k.replace('transformer.', '')}": v for k, v in lora_state_dict.items() if k.startswith("transformer.")
         }
         transformer_state_dict = convert_unet_state_dict_to_peft(transformer_state_dict)
         incompatible_keys = set_peft_model_state_dict(transformer_, transformer_state_dict, adapter_name="default")

examples/t2i_adapter/train_t2i_adapter_sdxl.py

@@ -60,7 +60,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 

examples/text_to_image/train_text_to_image.py

@@ -57,7 +57,7 @@ if is_wandb_available():
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/text_to_image/train_text_to_image_flax.py

@@ -49,7 +49,7 @@ from diffusers.utils import check_min_version
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = logging.getLogger(__name__)
 

examples/text_to_image/train_text_to_image_lora.py

@@ -56,7 +56,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/text_to_image/train_text_to_image_lora_sdxl.py

@@ -68,7 +68,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 if is_torch_npu_available():
@@ -767,7 +767,7 @@ def main(args):
                 raise ValueError(f"unexpected save model: {model.__class__}")
 
         lora_state_dict, _ = StableDiffusionLoraLoaderMixin.lora_state_dict(input_dir)
-        unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
+        unet_state_dict = {f"{k.replace('unet.', '')}": v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)
         incompatible_keys = set_peft_model_state_dict(unet_, unet_state_dict, adapter_name="default")
         if incompatible_keys is not None:

examples/text_to_image/train_text_to_image_sdxl.py

@@ -55,7 +55,7 @@ from diffusers.utils.torch_utils import is_compiled_module
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 if is_torch_npu_available():

examples/textual_inversion/textual_inversion.py

@@ -81,7 +81,7 @@ else:
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -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:

examples/textual_inversion/textual_inversion_flax.py

@@ -56,7 +56,7 @@ else:
 # ------------------------------------------------------------------------------
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = logging.getLogger(__name__)
 

examples/textual_inversion/textual_inversion_sdxl.py

@@ -76,7 +76,7 @@ else:
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__)
 
@@ -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:

examples/unconditional_image_generation/train_unconditional.py

@@ -29,7 +29,7 @@ from diffusers.utils.import_utils import is_xformers_available
 
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__, log_level="INFO")
 

examples/vqgan/test_vqgan.py

@@ -177,7 +177,7 @@ class TextToImage(ExamplesTestsAccelerate):
                 --model_config_name_or_path {vqmodel_config_path}
                 --discriminator_config_name_or_path {discriminator_config_path}
                 --checkpointing_steps=1
-                --resume_from_checkpoint={os.path.join(tmpdir, 'checkpoint-4')}
+                --resume_from_checkpoint={os.path.join(tmpdir, "checkpoint-4")}
                 --output_dir {tmpdir}
                 --seed=0
                 """.split()
@@ -262,7 +262,7 @@ class TextToImage(ExamplesTestsAccelerate):
                 --model_config_name_or_path {vqmodel_config_path}
                 --discriminator_config_name_or_path {discriminator_config_path}
                 --checkpointing_steps=1
-                --resume_from_checkpoint={os.path.join(tmpdir, 'checkpoint-4')}
+                --resume_from_checkpoint={os.path.join(tmpdir, "checkpoint-4")}
                 --output_dir {tmpdir}
                 --use_ema
                 --seed=0
@@ -377,7 +377,7 @@ class TextToImage(ExamplesTestsAccelerate):
                 --discriminator_config_name_or_path {discriminator_config_path}
                 --output_dir {tmpdir}
                 --checkpointing_steps=2
-                --resume_from_checkpoint={os.path.join(tmpdir, 'checkpoint-4')}
+                --resume_from_checkpoint={os.path.join(tmpdir, "checkpoint-4")}
                 --checkpoints_total_limit=2
                 --seed=0
                 """.split()

examples/vqgan/train_vqgan.py

@@ -50,7 +50,7 @@ if is_wandb_available():
     import wandb
 
 # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
-check_min_version("0.33.0.dev0")
+check_min_version("0.33.0")
 
 logger = get_logger(__name__, log_level="INFO")
 
@@ -653,15 +653,15 @@ def main():
     try:
         # Gets the resolution of the timm transformation after centercrop
         timm_centercrop_transform = timm_transform.transforms[1]
-        assert isinstance(
-            timm_centercrop_transform, transforms.CenterCrop
-        ), f"Timm model {timm_model} is currently incompatible with this script. Try vgg19."
+        assert isinstance(timm_centercrop_transform, transforms.CenterCrop), (
+            f"Timm model {timm_model} is currently incompatible with this script. Try vgg19."
+        )
         timm_model_resolution = timm_centercrop_transform.size[0]
         # Gets final normalization
         timm_model_normalization = timm_transform.transforms[-1]
-        assert isinstance(
-            timm_model_normalization, transforms.Normalize
-        ), f"Timm model {timm_model} is currently incompatible with this script. Try vgg19."
+        assert isinstance(timm_model_normalization, transforms.Normalize), (
+            f"Timm model {timm_model} is currently incompatible with this script. Try vgg19."
+        )
     except AssertionError as e:
         raise NotImplementedError(e)
     # Enable flash attention if asked

pyproject.toml

@@ -3,7 +3,7 @@ line-length = 119
 
 [tool.ruff.lint]
 # Never enforce `E501` (line length violations).
-ignore = ["C901", "E501", "E741", "F402", "F823"]
+ignore = ["C901", "E501", "E721", "E741", "F402", "F823"]
 select = ["C", "E", "F", "I", "W"]
 
 # Ignore import violations in all `__init__.py` files.

scripts/convert_amused.py

@@ -468,7 +468,7 @@ def make_vqvae(old_vae):
 
     # assert (old_output == new_output).all()
     print("skipping full vae equivalence check")
-    print(f"vae full diff { (old_output - new_output).float().abs().sum()}")
+    print(f"vae full diff {(old_output - new_output).float().abs().sum()}")
 
     return new_vae
 

scripts/convert_consistency_to_diffusers.py

@@ -239,7 +239,7 @@ def con_pt_to_diffuser(checkpoint_path: str, unet_config):
 
             if i != len(up_block_types) - 1:
                 new_prefix = f"up_blocks.{i}.upsamplers.0"
-                old_prefix = f"output_blocks.{current_layer-1}.1"
+                old_prefix = f"output_blocks.{current_layer - 1}.1"
                 new_checkpoint = convert_resnet(checkpoint, new_checkpoint, old_prefix, new_prefix)
         elif layer_type == "AttnUpBlock2D":
             for j in range(layers_per_block + 1):
@@ -255,7 +255,7 @@ def con_pt_to_diffuser(checkpoint_path: str, unet_config):
 
             if i != len(up_block_types) - 1:
                 new_prefix = f"up_blocks.{i}.upsamplers.0"
-                old_prefix = f"output_blocks.{current_layer-1}.2"
+                old_prefix = f"output_blocks.{current_layer - 1}.2"
                 new_checkpoint = convert_resnet(checkpoint, new_checkpoint, old_prefix, new_prefix)
 
     new_checkpoint["conv_norm_out.weight"] = checkpoint["out.0.weight"]

scripts/convert_dance_diffusion_to_diffusers.py

@@ -261,9 +261,9 @@ def main(args):
 
     model_name = args.model_path.split("/")[-1].split(".")[0]
     if not os.path.isfile(args.model_path):
-        assert (
-            model_name == args.model_path
-        ), f"Make sure to provide one of the official model names {MODELS_MAP.keys()}"
+        assert model_name == args.model_path, (
+            f"Make sure to provide one of the official model names {MODELS_MAP.keys()}"
+        )
         args.model_path = download(model_name)
 
     sample_rate = MODELS_MAP[model_name]["sample_rate"]
@@ -290,9 +290,9 @@ def main(args):
     assert all(k.endswith("kernel") for k in list(diffusers_minus_renamed)), f"Problem with {diffusers_minus_renamed}"
 
     for key, value in renamed_state_dict.items():
-        assert (
-            diffusers_state_dict[key].squeeze().shape == value.squeeze().shape
-        ), f"Shape for {key} doesn't match. Diffusers: {diffusers_state_dict[key].shape} vs. {value.shape}"
+        assert diffusers_state_dict[key].squeeze().shape == value.squeeze().shape, (
+            f"Shape for {key} doesn't match. Diffusers: {diffusers_state_dict[key].shape} vs. {value.shape}"
+        )
         if key == "time_proj.weight":
             value = value.squeeze()
 

scripts/convert_diffusers_to_original_sdxl.py

@@ -52,18 +52,18 @@ for i in range(3):
     for j in range(2):
         # loop over resnets/attentions for downblocks
         hf_down_res_prefix = f"down_blocks.{i}.resnets.{j}."
-        sd_down_res_prefix = f"input_blocks.{3*i + j + 1}.0."
+        sd_down_res_prefix = f"input_blocks.{3 * i + j + 1}.0."
         unet_conversion_map_layer.append((sd_down_res_prefix, hf_down_res_prefix))
 
         if i > 0:
             hf_down_atn_prefix = f"down_blocks.{i}.attentions.{j}."
-            sd_down_atn_prefix = f"input_blocks.{3*i + j + 1}.1."
+            sd_down_atn_prefix = f"input_blocks.{3 * i + j + 1}.1."
             unet_conversion_map_layer.append((sd_down_atn_prefix, hf_down_atn_prefix))
 
     for j in range(4):
         # loop over resnets/attentions for upblocks
         hf_up_res_prefix = f"up_blocks.{i}.resnets.{j}."
-        sd_up_res_prefix = f"output_blocks.{3*i + j}.0."
+        sd_up_res_prefix = f"output_blocks.{3 * i + j}.0."
         unet_conversion_map_layer.append((sd_up_res_prefix, hf_up_res_prefix))
 
         if i < 2:
@@ -75,12 +75,12 @@ for i in range(3):
     if i < 3:
         # no downsample in down_blocks.3
         hf_downsample_prefix = f"down_blocks.{i}.downsamplers.0.conv."
-        sd_downsample_prefix = f"input_blocks.{3*(i+1)}.0.op."
+        sd_downsample_prefix = f"input_blocks.{3 * (i + 1)}.0.op."
         unet_conversion_map_layer.append((sd_downsample_prefix, hf_downsample_prefix))
 
         # no upsample in up_blocks.3
         hf_upsample_prefix = f"up_blocks.{i}.upsamplers.0."
-        sd_upsample_prefix = f"output_blocks.{3*i + 2}.{1 if i == 0 else 2}."
+        sd_upsample_prefix = f"output_blocks.{3 * i + 2}.{1 if i == 0 else 2}."
         unet_conversion_map_layer.append((sd_upsample_prefix, hf_upsample_prefix))
 unet_conversion_map_layer.append(("output_blocks.2.2.conv.", "output_blocks.2.1.conv."))
 
@@ -89,7 +89,7 @@ sd_mid_atn_prefix = "middle_block.1."
 unet_conversion_map_layer.append((sd_mid_atn_prefix, hf_mid_atn_prefix))
 for j in range(2):
     hf_mid_res_prefix = f"mid_block.resnets.{j}."
-    sd_mid_res_prefix = f"middle_block.{2*j}."
+    sd_mid_res_prefix = f"middle_block.{2 * j}."
     unet_conversion_map_layer.append((sd_mid_res_prefix, hf_mid_res_prefix))
 
 
@@ -137,20 +137,20 @@ for i in range(4):
         vae_conversion_map.append((sd_downsample_prefix, hf_downsample_prefix))
 
         hf_upsample_prefix = f"up_blocks.{i}.upsamplers.0."
-        sd_upsample_prefix = f"up.{3-i}.upsample."
+        sd_upsample_prefix = f"up.{3 - i}.upsample."
         vae_conversion_map.append((sd_upsample_prefix, hf_upsample_prefix))
 
     # up_blocks have three resnets
     # also, up blocks in hf are numbered in reverse from sd
     for j in range(3):
         hf_up_prefix = f"decoder.up_blocks.{i}.resnets.{j}."
-        sd_up_prefix = f"decoder.up.{3-i}.block.{j}."
+        sd_up_prefix = f"decoder.up.{3 - i}.block.{j}."
         vae_conversion_map.append((sd_up_prefix, hf_up_prefix))
 
 # this part accounts for mid blocks in both the encoder and the decoder
 for i in range(2):
     hf_mid_res_prefix = f"mid_block.resnets.{i}."
-    sd_mid_res_prefix = f"mid.block_{i+1}."
+    sd_mid_res_prefix = f"mid.block_{i + 1}."
     vae_conversion_map.append((sd_mid_res_prefix, hf_mid_res_prefix))
 
 

scripts/convert_diffusers_to_original_stable_diffusion.py

@@ -47,36 +47,36 @@ for i in range(4):
     for j in range(2):
         # loop over resnets/attentions for downblocks
         hf_down_res_prefix = f"down_blocks.{i}.resnets.{j}."
-        sd_down_res_prefix = f"input_blocks.{3*i + j + 1}.0."
+        sd_down_res_prefix = f"input_blocks.{3 * i + j + 1}.0."
         unet_conversion_map_layer.append((sd_down_res_prefix, hf_down_res_prefix))
 
         if i < 3:
             # no attention layers in down_blocks.3
             hf_down_atn_prefix = f"down_blocks.{i}.attentions.{j}."
-            sd_down_atn_prefix = f"input_blocks.{3*i + j + 1}.1."
+            sd_down_atn_prefix = f"input_blocks.{3 * i + j + 1}.1."
             unet_conversion_map_layer.append((sd_down_atn_prefix, hf_down_atn_prefix))
 
     for j in range(3):
         # loop over resnets/attentions for upblocks
         hf_up_res_prefix = f"up_blocks.{i}.resnets.{j}."
-        sd_up_res_prefix = f"output_blocks.{3*i + j}.0."
+        sd_up_res_prefix = f"output_blocks.{3 * i + j}.0."
         unet_conversion_map_layer.append((sd_up_res_prefix, hf_up_res_prefix))
 
         if i > 0:
             # no attention layers in up_blocks.0
             hf_up_atn_prefix = f"up_blocks.{i}.attentions.{j}."
-            sd_up_atn_prefix = f"output_blocks.{3*i + j}.1."
+            sd_up_atn_prefix = f"output_blocks.{3 * i + j}.1."
             unet_conversion_map_layer.append((sd_up_atn_prefix, hf_up_atn_prefix))
 
     if i < 3:
         # no downsample in down_blocks.3
         hf_downsample_prefix = f"down_blocks.{i}.downsamplers.0.conv."
-        sd_downsample_prefix = f"input_blocks.{3*(i+1)}.0.op."
+        sd_downsample_prefix = f"input_blocks.{3 * (i + 1)}.0.op."
         unet_conversion_map_layer.append((sd_downsample_prefix, hf_downsample_prefix))
 
         # no upsample in up_blocks.3
         hf_upsample_prefix = f"up_blocks.{i}.upsamplers.0."
-        sd_upsample_prefix = f"output_blocks.{3*i + 2}.{1 if i == 0 else 2}."
+        sd_upsample_prefix = f"output_blocks.{3 * i + 2}.{1 if i == 0 else 2}."
         unet_conversion_map_layer.append((sd_upsample_prefix, hf_upsample_prefix))
 
 hf_mid_atn_prefix = "mid_block.attentions.0."
@@ -85,7 +85,7 @@ unet_conversion_map_layer.append((sd_mid_atn_prefix, hf_mid_atn_prefix))
 
 for j in range(2):
     hf_mid_res_prefix = f"mid_block.resnets.{j}."
-    sd_mid_res_prefix = f"middle_block.{2*j}."
+    sd_mid_res_prefix = f"middle_block.{2 * j}."
     unet_conversion_map_layer.append((sd_mid_res_prefix, hf_mid_res_prefix))
 
 
@@ -133,20 +133,20 @@ for i in range(4):
         vae_conversion_map.append((sd_downsample_prefix, hf_downsample_prefix))
 
         hf_upsample_prefix = f"up_blocks.{i}.upsamplers.0."
-        sd_upsample_prefix = f"up.{3-i}.upsample."
+        sd_upsample_prefix = f"up.{3 - i}.upsample."
         vae_conversion_map.append((sd_upsample_prefix, hf_upsample_prefix))
 
     # up_blocks have three resnets
     # also, up blocks in hf are numbered in reverse from sd
     for j in range(3):
         hf_up_prefix = f"decoder.up_blocks.{i}.resnets.{j}."
-        sd_up_prefix = f"decoder.up.{3-i}.block.{j}."
+        sd_up_prefix = f"decoder.up.{3 - i}.block.{j}."
         vae_conversion_map.append((sd_up_prefix, hf_up_prefix))
 
 # this part accounts for mid blocks in both the encoder and the decoder
 for i in range(2):
     hf_mid_res_prefix = f"mid_block.resnets.{i}."
-    sd_mid_res_prefix = f"mid.block_{i+1}."
+    sd_mid_res_prefix = f"mid.block_{i + 1}."
     vae_conversion_map.append((sd_mid_res_prefix, hf_mid_res_prefix))
 
 

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:

scripts/convert_hunyuandit_to_diffusers.py

@@ -13,15 +13,14 @@ def main(args):
             state_dict = state_dict[args.load_key]
         except KeyError:
             raise KeyError(
-                f"{args.load_key} not found in the checkpoint."
-                f"Please load from the following keys:{state_dict.keys()}"
+                f"{args.load_key} not found in the checkpoint.Please load from the following keys:{state_dict.keys()}"
             )
 
     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:

scripts/convert_k_upscaler_to_diffusers.py

@@ -142,14 +142,14 @@ def block_to_diffusers_checkpoint(block, checkpoint, block_idx, block_type):
             diffusers_attention_prefix = f"{block_type}_blocks.{block_idx}.attentions.{attention_idx}"
             idx = n * attention_idx + 1 if block_type == "up" else n * attention_idx + 2
             self_attention_prefix = f"{block_prefix}.{idx}"
-            cross_attention_prefix = f"{block_prefix}.{idx }"
+            cross_attention_prefix = f"{block_prefix}.{idx}"
             cross_attention_index = 1 if not attention.add_self_attention else 2
             idx = (
                 n * attention_idx + cross_attention_index
                 if block_type == "up"
                 else n * attention_idx + cross_attention_index + 1
             )
-            cross_attention_prefix = f"{block_prefix}.{idx }"
+            cross_attention_prefix = f"{block_prefix}.{idx}"
 
             diffusers_checkpoint.update(
                 cross_attn_to_diffusers_checkpoint(
@@ -220,9 +220,9 @@ def unet_model_from_original_config(original_config):
 
     block_out_channels = original_config["channels"]
 
-    assert (
-        len(set(original_config["depths"])) == 1
-    ), "UNet2DConditionModel currently do not support blocks with different number of layers"
+    assert len(set(original_config["depths"])) == 1, (
+        "UNet2DConditionModel currently do not support blocks with different number of layers"
+    )
     layers_per_block = original_config["depths"][0]
 
     class_labels_dim = original_config["mapping_cond_dim"]

scripts/convert_mochi_to_diffusers.py

@@ -168,28 +168,28 @@ def convert_mochi_vae_state_dict_to_diffusers(encoder_ckpt_path, decoder_ckpt_pa
     # Convert block_in (MochiMidBlock3D)
     for i in range(3):  # layers_per_block[-1] = 3
         new_state_dict[f"{prefix}block_in.resnets.{i}.norm1.norm_layer.weight"] = decoder_state_dict.pop(
-            f"blocks.0.{i+1}.stack.0.weight"
+            f"blocks.0.{i + 1}.stack.0.weight"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.norm1.norm_layer.bias"] = decoder_state_dict.pop(
-            f"blocks.0.{i+1}.stack.0.bias"
+            f"blocks.0.{i + 1}.stack.0.bias"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.conv1.conv.weight"] = decoder_state_dict.pop(
-            f"blocks.0.{i+1}.stack.2.weight"
+            f"blocks.0.{i + 1}.stack.2.weight"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.conv1.conv.bias"] = decoder_state_dict.pop(
-            f"blocks.0.{i+1}.stack.2.bias"
+            f"blocks.0.{i + 1}.stack.2.bias"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.norm2.norm_layer.weight"] = decoder_state_dict.pop(
-            f"blocks.0.{i+1}.stack.3.weight"
+            f"blocks.0.{i + 1}.stack.3.weight"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.norm2.norm_layer.bias"] = decoder_state_dict.pop(
-            f"blocks.0.{i+1}.stack.3.bias"
+            f"blocks.0.{i + 1}.stack.3.bias"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.conv2.conv.weight"] = decoder_state_dict.pop(
-            f"blocks.0.{i+1}.stack.5.weight"
+            f"blocks.0.{i + 1}.stack.5.weight"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.conv2.conv.bias"] = decoder_state_dict.pop(
-            f"blocks.0.{i+1}.stack.5.bias"
+            f"blocks.0.{i + 1}.stack.5.bias"
         )
 
     # Convert up_blocks (MochiUpBlock3D)
@@ -197,33 +197,35 @@ def convert_mochi_vae_state_dict_to_diffusers(encoder_ckpt_path, decoder_ckpt_pa
     for block in range(3):
         for i in range(down_block_layers[block]):
             new_state_dict[f"{prefix}up_blocks.{block}.resnets.{i}.norm1.norm_layer.weight"] = decoder_state_dict.pop(
-                f"blocks.{block+1}.blocks.{i}.stack.0.weight"
+                f"blocks.{block + 1}.blocks.{i}.stack.0.weight"
             )
             new_state_dict[f"{prefix}up_blocks.{block}.resnets.{i}.norm1.norm_layer.bias"] = decoder_state_dict.pop(
-                f"blocks.{block+1}.blocks.{i}.stack.0.bias"
+                f"blocks.{block + 1}.blocks.{i}.stack.0.bias"
             )
             new_state_dict[f"{prefix}up_blocks.{block}.resnets.{i}.conv1.conv.weight"] = decoder_state_dict.pop(
-                f"blocks.{block+1}.blocks.{i}.stack.2.weight"
+                f"blocks.{block + 1}.blocks.{i}.stack.2.weight"
             )
             new_state_dict[f"{prefix}up_blocks.{block}.resnets.{i}.conv1.conv.bias"] = decoder_state_dict.pop(
-                f"blocks.{block+1}.blocks.{i}.stack.2.bias"
+                f"blocks.{block + 1}.blocks.{i}.stack.2.bias"
             )
             new_state_dict[f"{prefix}up_blocks.{block}.resnets.{i}.norm2.norm_layer.weight"] = decoder_state_dict.pop(
-                f"blocks.{block+1}.blocks.{i}.stack.3.weight"
+                f"blocks.{block + 1}.blocks.{i}.stack.3.weight"
             )
             new_state_dict[f"{prefix}up_blocks.{block}.resnets.{i}.norm2.norm_layer.bias"] = decoder_state_dict.pop(
-                f"blocks.{block+1}.blocks.{i}.stack.3.bias"
+                f"blocks.{block + 1}.blocks.{i}.stack.3.bias"
             )
             new_state_dict[f"{prefix}up_blocks.{block}.resnets.{i}.conv2.conv.weight"] = decoder_state_dict.pop(
-                f"blocks.{block+1}.blocks.{i}.stack.5.weight"
+                f"blocks.{block + 1}.blocks.{i}.stack.5.weight"
             )
             new_state_dict[f"{prefix}up_blocks.{block}.resnets.{i}.conv2.conv.bias"] = decoder_state_dict.pop(
-                f"blocks.{block+1}.blocks.{i}.stack.5.bias"
+                f"blocks.{block + 1}.blocks.{i}.stack.5.bias"
             )
         new_state_dict[f"{prefix}up_blocks.{block}.proj.weight"] = decoder_state_dict.pop(
-            f"blocks.{block+1}.proj.weight"
+            f"blocks.{block + 1}.proj.weight"
+        )
+        new_state_dict[f"{prefix}up_blocks.{block}.proj.bias"] = decoder_state_dict.pop(
+            f"blocks.{block + 1}.proj.bias"
         )
-        new_state_dict[f"{prefix}up_blocks.{block}.proj.bias"] = decoder_state_dict.pop(f"blocks.{block+1}.proj.bias")
 
     # Convert block_out (MochiMidBlock3D)
     for i in range(3):  # layers_per_block[0] = 3
@@ -267,133 +269,133 @@ def convert_mochi_vae_state_dict_to_diffusers(encoder_ckpt_path, decoder_ckpt_pa
     # Convert block_in (MochiMidBlock3D)
     for i in range(3):  # layers_per_block[0] = 3
         new_state_dict[f"{prefix}block_in.resnets.{i}.norm1.norm_layer.weight"] = encoder_state_dict.pop(
-            f"layers.{i+1}.stack.0.weight"
+            f"layers.{i + 1}.stack.0.weight"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.norm1.norm_layer.bias"] = encoder_state_dict.pop(
-            f"layers.{i+1}.stack.0.bias"
+            f"layers.{i + 1}.stack.0.bias"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.conv1.conv.weight"] = encoder_state_dict.pop(
-            f"layers.{i+1}.stack.2.weight"
+            f"layers.{i + 1}.stack.2.weight"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.conv1.conv.bias"] = encoder_state_dict.pop(
-            f"layers.{i+1}.stack.2.bias"
+            f"layers.{i + 1}.stack.2.bias"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.norm2.norm_layer.weight"] = encoder_state_dict.pop(
-            f"layers.{i+1}.stack.3.weight"
+            f"layers.{i + 1}.stack.3.weight"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.norm2.norm_layer.bias"] = encoder_state_dict.pop(
-            f"layers.{i+1}.stack.3.bias"
+            f"layers.{i + 1}.stack.3.bias"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.conv2.conv.weight"] = encoder_state_dict.pop(
-            f"layers.{i+1}.stack.5.weight"
+            f"layers.{i + 1}.stack.5.weight"
         )
         new_state_dict[f"{prefix}block_in.resnets.{i}.conv2.conv.bias"] = encoder_state_dict.pop(
-            f"layers.{i+1}.stack.5.bias"
+            f"layers.{i + 1}.stack.5.bias"
         )
 
     # Convert down_blocks (MochiDownBlock3D)
     down_block_layers = [3, 4, 6]  # layers_per_block[1], layers_per_block[2], layers_per_block[3]
     for block in range(3):
         new_state_dict[f"{prefix}down_blocks.{block}.conv_in.conv.weight"] = encoder_state_dict.pop(
-            f"layers.{block+4}.layers.0.weight"
+            f"layers.{block + 4}.layers.0.weight"
         )
         new_state_dict[f"{prefix}down_blocks.{block}.conv_in.conv.bias"] = encoder_state_dict.pop(
-            f"layers.{block+4}.layers.0.bias"
+            f"layers.{block + 4}.layers.0.bias"
         )
 
         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"
+                f"layers.{block + 4}.layers.{i + 1}.stack.0.bias"
             )
             new_state_dict[f"{prefix}down_blocks.{block}.resnets.{i}.conv1.conv.weight"] = encoder_state_dict.pop(
-                f"layers.{block+4}.layers.{i+1}.stack.2.weight"
+                f"layers.{block + 4}.layers.{i + 1}.stack.2.weight"
             )
             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"
+                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"
+                f"layers.{block + 4}.layers.{i + 1}.stack.3.bias"
             )
             new_state_dict[f"{prefix}down_blocks.{block}.resnets.{i}.conv2.conv.weight"] = encoder_state_dict.pop(
-                f"layers.{block+4}.layers.{i+1}.stack.5.weight"
+                f"layers.{block + 4}.layers.{i + 1}.stack.5.weight"
             )
             new_state_dict[f"{prefix}down_blocks.{block}.resnets.{i}.conv2.conv.bias"] = encoder_state_dict.pop(
-                f"layers.{block+4}.layers.{i+1}.stack.5.bias"
+                f"layers.{block + 4}.layers.{i + 1}.stack.5.bias"
             )
 
             # Convert attentions
-            qkv_weight = encoder_state_dict.pop(f"layers.{block+4}.layers.{i+1}.attn_block.attn.qkv.weight")
+            qkv_weight = encoder_state_dict.pop(f"layers.{block + 4}.layers.{i + 1}.attn_block.attn.qkv.weight")
             q, k, v = qkv_weight.chunk(3, dim=0)
 
             new_state_dict[f"{prefix}down_blocks.{block}.attentions.{i}.to_q.weight"] = q
             new_state_dict[f"{prefix}down_blocks.{block}.attentions.{i}.to_k.weight"] = k
             new_state_dict[f"{prefix}down_blocks.{block}.attentions.{i}.to_v.weight"] = v
             new_state_dict[f"{prefix}down_blocks.{block}.attentions.{i}.to_out.0.weight"] = encoder_state_dict.pop(
-                f"layers.{block+4}.layers.{i+1}.attn_block.attn.out.weight"
+                f"layers.{block + 4}.layers.{i + 1}.attn_block.attn.out.weight"
             )
             new_state_dict[f"{prefix}down_blocks.{block}.attentions.{i}.to_out.0.bias"] = encoder_state_dict.pop(
-                f"layers.{block+4}.layers.{i+1}.attn_block.attn.out.bias"
+                f"layers.{block + 4}.layers.{i + 1}.attn_block.attn.out.bias"
             )
             new_state_dict[f"{prefix}down_blocks.{block}.norms.{i}.norm_layer.weight"] = encoder_state_dict.pop(
-                f"layers.{block+4}.layers.{i+1}.attn_block.norm.weight"
+                f"layers.{block + 4}.layers.{i + 1}.attn_block.norm.weight"
             )
             new_state_dict[f"{prefix}down_blocks.{block}.norms.{i}.norm_layer.bias"] = encoder_state_dict.pop(
-                f"layers.{block+4}.layers.{i+1}.attn_block.norm.bias"
+                f"layers.{block + 4}.layers.{i + 1}.attn_block.norm.bias"
             )
 
     # Convert block_out (MochiMidBlock3D)
     for i in range(3):  # layers_per_block[-1] = 3
         # Convert resnets
         new_state_dict[f"{prefix}block_out.resnets.{i}.norm1.norm_layer.weight"] = encoder_state_dict.pop(
-            f"layers.{i+7}.stack.0.weight"
+            f"layers.{i + 7}.stack.0.weight"
         )
         new_state_dict[f"{prefix}block_out.resnets.{i}.norm1.norm_layer.bias"] = encoder_state_dict.pop(
-            f"layers.{i+7}.stack.0.bias"
+            f"layers.{i + 7}.stack.0.bias"
         )
         new_state_dict[f"{prefix}block_out.resnets.{i}.conv1.conv.weight"] = encoder_state_dict.pop(
-            f"layers.{i+7}.stack.2.weight"
+            f"layers.{i + 7}.stack.2.weight"
         )
         new_state_dict[f"{prefix}block_out.resnets.{i}.conv1.conv.bias"] = encoder_state_dict.pop(
-            f"layers.{i+7}.stack.2.bias"
+            f"layers.{i + 7}.stack.2.bias"
         )
         new_state_dict[f"{prefix}block_out.resnets.{i}.norm2.norm_layer.weight"] = encoder_state_dict.pop(
-            f"layers.{i+7}.stack.3.weight"
+            f"layers.{i + 7}.stack.3.weight"
         )
         new_state_dict[f"{prefix}block_out.resnets.{i}.norm2.norm_layer.bias"] = encoder_state_dict.pop(
-            f"layers.{i+7}.stack.3.bias"
+            f"layers.{i + 7}.stack.3.bias"
         )
         new_state_dict[f"{prefix}block_out.resnets.{i}.conv2.conv.weight"] = encoder_state_dict.pop(
-            f"layers.{i+7}.stack.5.weight"
+            f"layers.{i + 7}.stack.5.weight"
         )
         new_state_dict[f"{prefix}block_out.resnets.{i}.conv2.conv.bias"] = encoder_state_dict.pop(
-            f"layers.{i+7}.stack.5.bias"
+            f"layers.{i + 7}.stack.5.bias"
         )
 
         # Convert attentions
-        qkv_weight = encoder_state_dict.pop(f"layers.{i+7}.attn_block.attn.qkv.weight")
+        qkv_weight = encoder_state_dict.pop(f"layers.{i + 7}.attn_block.attn.qkv.weight")
         q, k, v = qkv_weight.chunk(3, dim=0)
 
         new_state_dict[f"{prefix}block_out.attentions.{i}.to_q.weight"] = q
         new_state_dict[f"{prefix}block_out.attentions.{i}.to_k.weight"] = k
         new_state_dict[f"{prefix}block_out.attentions.{i}.to_v.weight"] = v
         new_state_dict[f"{prefix}block_out.attentions.{i}.to_out.0.weight"] = encoder_state_dict.pop(
-            f"layers.{i+7}.attn_block.attn.out.weight"
+            f"layers.{i + 7}.attn_block.attn.out.weight"
         )
         new_state_dict[f"{prefix}block_out.attentions.{i}.to_out.0.bias"] = encoder_state_dict.pop(
-            f"layers.{i+7}.attn_block.attn.out.bias"
+            f"layers.{i + 7}.attn_block.attn.out.bias"
         )
         new_state_dict[f"{prefix}block_out.norms.{i}.norm_layer.weight"] = encoder_state_dict.pop(
-            f"layers.{i+7}.attn_block.norm.weight"
+            f"layers.{i + 7}.attn_block.norm.weight"
         )
         new_state_dict[f"{prefix}block_out.norms.{i}.norm_layer.bias"] = encoder_state_dict.pop(
-            f"layers.{i+7}.attn_block.norm.bias"
+            f"layers.{i + 7}.attn_block.norm.bias"
         )
 
     # Convert output layers

scripts/convert_original_audioldm2_to_diffusers.py

@@ -662,7 +662,7 @@ def convert_open_clap_checkpoint(checkpoint):
             # replace sequential layers with list
             sequential_layer = re.match(sequential_layers_pattern, key).group(1)
 
-            key = key.replace(f"sequential.{sequential_layer}.", f"layers.{int(sequential_layer)//3}.linear.")
+            key = key.replace(f"sequential.{sequential_layer}.", f"layers.{int(sequential_layer) // 3}.linear.")
         elif re.match(text_projection_pattern, key):
             projecton_layer = int(re.match(text_projection_pattern, key).group(1))
 

scripts/convert_original_audioldm_to_diffusers.py

@@ -636,7 +636,7 @@ def convert_open_clap_checkpoint(checkpoint):
             # replace sequential layers with list
             sequential_layer = re.match(sequential_layers_pattern, key).group(1)
 
-            key = key.replace(f"sequential.{sequential_layer}.", f"layers.{int(sequential_layer)//3}.linear.")
+            key = key.replace(f"sequential.{sequential_layer}.", f"layers.{int(sequential_layer) // 3}.linear.")
         elif re.match(text_projection_pattern, key):
             projecton_layer = int(re.match(text_projection_pattern, key).group(1))
 

scripts/convert_original_musicldm_to_diffusers.py

@@ -642,7 +642,7 @@ def convert_open_clap_checkpoint(checkpoint):
             # replace sequential layers with list
             sequential_layer = re.match(sequential_layers_pattern, key).group(1)
 
-            key = key.replace(f"sequential.{sequential_layer}.", f"layers.{int(sequential_layer)//3}.linear.")
+            key = key.replace(f"sequential.{sequential_layer}.", f"layers.{int(sequential_layer) // 3}.linear.")
         elif re.match(text_projection_pattern, key):
             projecton_layer = int(re.match(text_projection_pattern, key).group(1))