update

docs/source/en/api/attnprocessor.md

@@ -46,7 +46,7 @@ An attention processor is a class for applying different types of attention mech
 
 ## CrossFrameAttnProcessor
 
-[[autodoc]] pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor
+[[autodoc]] pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor
 
 ## Custom Diffusion
 
@@ -163,4 +163,4 @@ An attention processor is a class for applying different types of attention mech
 
 ## XLAFluxFlashAttnProcessor2_0
 
-[[autodoc]] models.attention_processor.XLAFluxFlashAttnProcessor2_0
+[[autodoc]] models.attention_processor.XLAFluxFlashAttnProcessor2_0

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

@@ -42,4 +42,4 @@ pipe = FluxControlNetPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", co
 
 ## FluxControlNetOutput
 
-[[autodoc]] models.controlnet_flux.FluxControlNetOutput
+[[autodoc]] models.controlnets.FluxControlNetOutput

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

@@ -43,4 +43,4 @@ controlnet = SparseControlNetModel.from_pretrained("guoyww/animatediff-sparsectr
 
 ## SparseControlNetOutput
 
-[[autodoc]] models.controlnet_sparsectrl.SparseControlNetOutput
+[[autodoc]] models.controlnets.SparseControlNetOutput

docs/source/en/api/pipelines/i2vgenxl.md

@@ -55,4 +55,4 @@ Sample output with I2VGenXL:
 	- __call__
 
 ## I2VGenXLPipelineOutput
-[[autodoc]] pipelines.i2vgen_xl.pipeline_i2vgen_xl.I2VGenXLPipelineOutput
+[[autodoc]] pipelines.deprecated.i2vgen_xl.pipeline_i2vgen_xl.I2VGenXLPipelineOutput

docs/source/en/api/pipelines/pia.md

@@ -168,4 +168,4 @@ FreeInit is not really free - the improved quality comes at the cost of extra co
 
 ## PIAPipelineOutput
 
-[[autodoc]] pipelines.pia.PIAPipelineOutput
+[[autodoc]] pipelines.deprecated.pia.PIAPipelineOutput

docs/source/en/api/pipelines/semantic_stable_diffusion.md

@@ -31,5 +31,5 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers)
 	- __call__
 
 ## SemanticStableDiffusionPipelineOutput
-[[autodoc]] pipelines.semantic_stable_diffusion.pipeline_output.SemanticStableDiffusionPipelineOutput
+[[autodoc]] pipelines.deprecated.semantic_stable_diffusion.pipeline_output.SemanticStableDiffusionPipelineOutput
 	- all

docs/source/en/api/pipelines/shap_e.md

@@ -34,4 +34,4 @@ See the [reuse components across pipelines](../../using-diffusers/loading#reuse-
 	- __call__
 
 ## ShapEPipelineOutput
-[[autodoc]] pipelines.shap_e.pipeline_shap_e.ShapEPipelineOutput
+[[autodoc]] pipelines.deprecated.shap_e.pipeline_shap_e.ShapEPipelineOutput

docs/source/en/api/pipelines/stable_diffusion/ldm3d_diffusion.md

@@ -35,14 +35,14 @@ Make sure to check out the Stable Diffusion [Tips](overview#tips) section to lea
 
 ## StableDiffusionLDM3DPipeline
 
-[[autodoc]] pipelines.stable_diffusion_ldm3d.pipeline_stable_diffusion_ldm3d.StableDiffusionLDM3DPipeline
+[[autodoc]] pipelines.deprecated.stable_diffusion_ldm3d.pipeline_stable_diffusion_ldm3d.StableDiffusionLDM3DPipeline
 	- all
 	- __call__
 
 
 ## LDM3DPipelineOutput
 
-[[autodoc]] pipelines.stable_diffusion_ldm3d.pipeline_stable_diffusion_ldm3d.LDM3DPipelineOutput
+[[autodoc]] pipelines.deprecated.stable_diffusion_ldm3d.pipeline_stable_diffusion_ldm3d.LDM3DPipelineOutput
 	- all
 	- __call__
 

docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_safe.md

@@ -56,6 +56,6 @@ Make sure to check out the Stable Diffusion [Tips](overview#tips) section to lea
 
 ## StableDiffusionSafePipelineOutput
 
-[[autodoc]] pipelines.stable_diffusion_safe.StableDiffusionSafePipelineOutput
+[[autodoc]] pipelines.deprecated.stable_diffusion_safe.StableDiffusionSafePipelineOutput
 	- all
 	- __call__

docs/source/en/api/pipelines/text_to_video.md

@@ -194,4 +194,4 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers)
 	- __call__
 
 ## TextToVideoSDPipelineOutput
-[[autodoc]] pipelines.text_to_video_synthesis.TextToVideoSDPipelineOutput
+[[autodoc]] pipelines.deprecated.text_to_video_synthesis.TextToVideoSDPipelineOutput

docs/source/en/api/pipelines/text_to_video_zero.md

@@ -303,4 +303,4 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers)
 	- __call__
 
 ## TextToVideoPipelineOutput
-[[autodoc]] pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.TextToVideoPipelineOutput
+[[autodoc]] pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.TextToVideoPipelineOutput

docs/source/en/api/pipelines/wuerstchen.md

@@ -145,7 +145,7 @@ The original codebase, as well as experimental ideas, can be found at [dome272/W
 
 ## WuerstchenPriorPipelineOutput
 
-[[autodoc]] pipelines.wuerstchen.pipeline_wuerstchen_prior.WuerstchenPriorPipelineOutput
+[[autodoc]] pipelines.deprecated.wuerstchen.pipeline_wuerstchen_prior.WuerstchenPriorPipelineOutput
 
 ## WuerstchenDecoderPipeline
 

examples/community/pipeline_animatediff_controlnet.py

@@ -436,7 +436,7 @@ class AnimateDiffControlNetPipeline(
             image_embeds = ip_adapter_image_embeds
         return image_embeds
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
     def decode_latents(self, latents):
         latents = 1 / self.vae.config.scaling_factor * latents
 
@@ -663,7 +663,7 @@ class AnimateDiffControlNetPipeline(
                 f"If image batch size is not 1, image batch size must be same as prompt batch size. image batch size: {image_batch_size}, prompt batch size: {prompt_batch_size}"
             )
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
     def prepare_latents(
         self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents=None
     ):

examples/community/pipeline_animatediff_img2video.py

@@ -553,7 +553,7 @@ class AnimateDiffImgToVideoPipeline(
             image_embeds = ip_adapter_image_embeds
         return image_embeds
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
     def decode_latents(self, latents):
         latents = 1 / self.vae.config.scaling_factor * latents
 

examples/community/pipeline_animatediff_ipex.py

@@ -425,7 +425,7 @@ class AnimateDiffPipelineIpex(
 
         return image_embeds
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
     def decode_latents(self, latents):
         latents = 1 / self.vae.config.scaling_factor * latents
 
@@ -520,7 +520,7 @@ class AnimateDiffPipelineIpex(
                     f"`ip_adapter_image_embeds` has to be a list of 3D or 4D tensors but is {ip_adapter_image_embeds[0].ndim}D"
                 )
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
     def prepare_latents(
         self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents=None
     ):

examples/community/pipeline_stg_cogvideox.py

@@ -427,7 +427,7 @@ class CogVideoXSTGPipeline(DiffusionPipeline, CogVideoXLoraLoaderMixin):
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
-    # Copied from diffusers.pipelines.latte.pipeline_latte.LattePipeline.check_inputs
+    # Copied from diffusers.pipelines.deprecated.latte.pipeline_latte.LattePipeline.check_inputs
     def check_inputs(
         self,
         prompt,

examples/community/unclip_image_interpolation.py

@@ -18,7 +18,7 @@ from diffusers import (
     UNet2DConditionModel,
     UNet2DModel,
 )
-from diffusers.pipelines.unclip import UnCLIPTextProjModel
+from diffusers.pipelines.deprecated.unclip import UnCLIPTextProjModel
 from diffusers.utils import logging
 from diffusers.utils.torch_utils import randn_tensor
 
@@ -84,7 +84,7 @@ class UnCLIPImageInterpolationPipeline(DiffusionPipeline):
     decoder_scheduler: UnCLIPScheduler
     super_res_scheduler: UnCLIPScheduler
 
-    # Copied from diffusers.pipelines.unclip.pipeline_unclip_image_variation.UnCLIPImageVariationPipeline.__init__
+    # Copied from diffusers.pipelines.deprecated.unclip.pipeline_unclip_image_variation.UnCLIPImageVariationPipeline.__init__
     def __init__(
         self,
         decoder: UNet2DConditionModel,
@@ -113,7 +113,7 @@ class UnCLIPImageInterpolationPipeline(DiffusionPipeline):
             super_res_scheduler=super_res_scheduler,
         )
 
-    # Copied from diffusers.pipelines.unclip.pipeline_unclip.UnCLIPPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.unclip.pipeline_unclip.UnCLIPPipeline.prepare_latents
     def prepare_latents(self, shape, dtype, device, generator, latents, scheduler):
         if latents is None:
             latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
@@ -125,7 +125,7 @@ class UnCLIPImageInterpolationPipeline(DiffusionPipeline):
         latents = latents * scheduler.init_noise_sigma
         return latents
 
-    # Copied from diffusers.pipelines.unclip.pipeline_unclip_image_variation.UnCLIPImageVariationPipeline._encode_prompt
+    # Copied from diffusers.pipelines.deprecated.unclip.pipeline_unclip_image_variation.UnCLIPImageVariationPipeline._encode_prompt
     def _encode_prompt(self, prompt, device, num_images_per_prompt, do_classifier_free_guidance):
         batch_size = len(prompt) if isinstance(prompt, list) else 1
 
@@ -189,7 +189,7 @@ class UnCLIPImageInterpolationPipeline(DiffusionPipeline):
 
         return prompt_embeds, text_encoder_hidden_states, text_mask
 
-    # Copied from diffusers.pipelines.unclip.pipeline_unclip_image_variation.UnCLIPImageVariationPipeline._encode_image
+    # Copied from diffusers.pipelines.deprecated.unclip.pipeline_unclip_image_variation.UnCLIPImageVariationPipeline._encode_image
     def _encode_image(self, image, device, num_images_per_prompt, image_embeddings: Optional[torch.Tensor] = None):
         dtype = next(self.image_encoder.parameters()).dtype
 

examples/community/unclip_text_interpolation.py

@@ -14,7 +14,7 @@ from diffusers import (
     UNet2DConditionModel,
     UNet2DModel,
 )
-from diffusers.pipelines.unclip import UnCLIPTextProjModel
+from diffusers.pipelines.deprecated.unclip import UnCLIPTextProjModel
 from diffusers.utils import logging
 from diffusers.utils.torch_utils import randn_tensor
 
@@ -78,7 +78,7 @@ class UnCLIPTextInterpolationPipeline(DiffusionPipeline):
     decoder_scheduler: UnCLIPScheduler
     super_res_scheduler: UnCLIPScheduler
 
-    # Copied from diffusers.pipelines.unclip.pipeline_unclip.UnCLIPPipeline.__init__
+    # Copied from diffusers.pipelines.deprecated.unclip.pipeline_unclip.UnCLIPPipeline.__init__
     def __init__(
         self,
         prior: PriorTransformer,
@@ -107,7 +107,7 @@ class UnCLIPTextInterpolationPipeline(DiffusionPipeline):
             super_res_scheduler=super_res_scheduler,
         )
 
-    # Copied from diffusers.pipelines.unclip.pipeline_unclip.UnCLIPPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.unclip.pipeline_unclip.UnCLIPPipeline.prepare_latents
     def prepare_latents(self, shape, dtype, device, generator, latents, scheduler):
         if latents is None:
             latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
@@ -119,7 +119,7 @@ class UnCLIPTextInterpolationPipeline(DiffusionPipeline):
         latents = latents * scheduler.init_noise_sigma
         return latents
 
-    # Copied from diffusers.pipelines.unclip.pipeline_unclip.UnCLIPPipeline._encode_prompt
+    # Copied from diffusers.pipelines.deprecated.unclip.pipeline_unclip.UnCLIPPipeline._encode_prompt
     def _encode_prompt(
         self,
         prompt,

examples/research_projects/wuerstchen/text_to_image/train_text_to_image_lora_prior.py

@@ -40,7 +40,7 @@ from transformers.utils import ContextManagers
 
 from diffusers import AutoPipelineForText2Image, DDPMWuerstchenScheduler, WuerstchenPriorPipeline
 from diffusers.optimization import get_scheduler
-from diffusers.pipelines.wuerstchen import DEFAULT_STAGE_C_TIMESTEPS, WuerstchenPrior
+from diffusers.pipelines.deprecated.wuerstchen import DEFAULT_STAGE_C_TIMESTEPS, WuerstchenPrior
 from diffusers.utils import check_min_version, is_wandb_available, make_image_grid
 from diffusers.utils.logging import set_verbosity_error, set_verbosity_info
 

examples/research_projects/wuerstchen/text_to_image/train_text_to_image_prior.py

@@ -40,7 +40,7 @@ from transformers.utils import ContextManagers
 
 from diffusers import AutoPipelineForText2Image, DDPMWuerstchenScheduler
 from diffusers.optimization import get_scheduler
-from diffusers.pipelines.wuerstchen import DEFAULT_STAGE_C_TIMESTEPS, WuerstchenPrior
+from diffusers.pipelines.deprecated.wuerstchen import DEFAULT_STAGE_C_TIMESTEPS, WuerstchenPrior
 from diffusers.training_utils import EMAModel
 from diffusers.utils import check_min_version, is_wandb_available, make_image_grid
 from diffusers.utils.logging import set_verbosity_error, set_verbosity_info

scripts/convert_kakao_brain_unclip_to_diffusers.py

@@ -7,7 +7,7 @@ from transformers import CLIPTextModelWithProjection, CLIPTokenizer
 
 from diffusers import UnCLIPPipeline, UNet2DConditionModel, UNet2DModel
 from diffusers.models.transformers.prior_transformer import PriorTransformer
-from diffusers.pipelines.unclip.text_proj import UnCLIPTextProjModel
+from diffusers.pipelines.deprecated.unclip.text_proj import UnCLIPTextProjModel
 from diffusers.schedulers.scheduling_unclip import UnCLIPScheduler
 
 

scripts/convert_shap_e_to_diffusers.py

@@ -5,7 +5,7 @@ import torch
 from accelerate import load_checkpoint_and_dispatch
 
 from diffusers.models.transformers.prior_transformer import PriorTransformer
-from diffusers.pipelines.shap_e import ShapERenderer
+from diffusers.pipelines.deprecated.shap_e import ShapERenderer
 
 
 """

scripts/convert_stable_cascade.py

@@ -21,7 +21,7 @@ from diffusers import (
 from diffusers.loaders.single_file_utils import convert_stable_cascade_unet_single_file_to_diffusers
 from diffusers.models import StableCascadeUNet
 from diffusers.models.modeling_utils import load_model_dict_into_meta
-from diffusers.pipelines.wuerstchen import PaellaVQModel
+from diffusers.pipelines.deprecated.wuerstchen import PaellaVQModel
 from diffusers.utils import is_accelerate_available
 
 

scripts/convert_stable_cascade_lite.py

@@ -21,7 +21,7 @@ from diffusers import (
 from diffusers.loaders.single_file_utils import convert_stable_cascade_unet_single_file_to_diffusers
 from diffusers.models import StableCascadeUNet
 from diffusers.models.modeling_utils import load_model_dict_into_meta
-from diffusers.pipelines.wuerstchen import PaellaVQModel
+from diffusers.pipelines.deprecated.wuerstchen import PaellaVQModel
 from diffusers.utils import is_accelerate_available
 
 

scripts/convert_wuerstchen.py

@@ -11,7 +11,7 @@ from diffusers import (
     WuerstchenDecoderPipeline,
     WuerstchenPriorPipeline,
 )
-from diffusers.pipelines.wuerstchen import PaellaVQModel, WuerstchenDiffNeXt, WuerstchenPrior
+from diffusers.pipelines.deprecated.wuerstchen import PaellaVQModel, WuerstchenDiffNeXt, WuerstchenPrior
 
 
 model_path = "models/"

src/diffusers/models/unets/unet_stable_cascade.py

@@ -27,7 +27,7 @@ from ..attention_processor import Attention
 from ..modeling_utils import ModelMixin
 
 
-# Copied from diffusers.pipelines.wuerstchen.modeling_wuerstchen_common.WuerstchenLayerNorm with WuerstchenLayerNorm -> SDCascadeLayerNorm
+# Copied from diffusers.pipelines.deprecated.wuerstchen.modeling_wuerstchen_common.WuerstchenLayerNorm with WuerstchenLayerNorm -> SDCascadeLayerNorm
 class SDCascadeLayerNorm(nn.LayerNorm):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)

src/diffusers/pipelines/__init__.py

@@ -48,7 +48,6 @@ else:
         "AutoPipelineForText2Image",
     ]
     _import_structure["consistency_models"] = ["ConsistencyModelPipeline"]
-    _import_structure["dance_diffusion"] = ["DanceDiffusionPipeline"]
     _import_structure["ddim"] = ["DDIMPipeline"]
     _import_structure["ddpm"] = ["DDPMPipeline"]
     _import_structure["dit"] = ["DiTPipeline"]
@@ -62,6 +61,7 @@ else:
     _import_structure["deprecated"].extend(
         [
             "PNDMPipeline",
+            "DanceDiffusionPipeline",
             "LDMPipeline",
             "RePaintPipeline",
             "ScoreSdeVePipeline",
@@ -107,6 +107,7 @@ else:
             "AltDiffusionPipeline",
             "AltDiffusionImg2ImgPipeline",
             "CycleDiffusionPipeline",
+            "StableDiffusionLDM3DPipeline",
             "StableDiffusionInpaintPipelineLegacy",
             "StableDiffusionPix2PixZeroPipeline",
             "StableDiffusionParadigmsPipeline",
@@ -115,10 +116,45 @@ else:
             "VersatileDiffusionImageVariationPipeline",
             "VersatileDiffusionPipeline",
             "VersatileDiffusionTextToImagePipeline",
+            "AmusedImg2ImgPipeline",
+            "AmusedInpaintPipeline",
+            "AmusedPipeline",
+            "StableDiffusionControlNetXSPipeline",
+            "StableDiffusionXLControlNetXSPipeline",
+            "I2VGenXLPipeline",
+            "LattePipeline",
+            "MusicLDMPipeline",
+            "PaintByExamplePipeline",
+            "PIAPipeline",
+            "SemanticStableDiffusionPipeline",
+            "ShapEImg2ImgPipeline",
+            "ShapEPipeline",
+            "StableDiffusionAttendAndExcitePipeline",
+            "StableDiffusionPipelineSafe",
+            "StableDiffusionSAGPipeline",
+            "StableDiffusionGLIGENPipeline",
+            "StableDiffusionGLIGENTextImagePipeline",
+            "StableDiffusionDiffEditPipeline",
+            "StableDiffusionLDM3DPipeline",
+            "StableDiffusionPanoramaPipeline",
+            "TextToVideoSDPipeline",
+            "TextToVideoZeroPipeline",
+            "TextToVideoZeroSDXLPipeline",
+            "VideoToVideoSDPipeline",
+            "UnCLIPImageVariationPipeline",
+            "UnCLIPPipeline",
+            "ImageTextPipelineOutput",
+            "UniDiffuserModel",
+            "UniDiffuserPipeline",
+            "UniDiffuserTextDecoder",
+            "WuerstchenCombinedPipeline",
+            "WuerstchenDecoderPipeline",
+            "WuerstchenPriorPipeline",
+            "BlipDiffusionPipeline",
+            "BlipDiffusionControlNetPipeline",
         ]
     )
     _import_structure["allegro"] = ["AllegroPipeline"]
-    _import_structure["amused"] = ["AmusedImg2ImgPipeline", "AmusedInpaintPipeline", "AmusedPipeline"]
     _import_structure["animatediff"] = [
         "AnimateDiffPipeline",
         "AnimateDiffControlNetPipeline",
@@ -147,7 +183,6 @@ else:
         "AudioLDM2ProjectionModel",
         "AudioLDM2UNet2DConditionModel",
     ]
-    _import_structure["blip_diffusion"] = ["BlipDiffusionPipeline"]
     _import_structure["cogvideo"] = [
         "CogVideoXPipeline",
         "CogVideoXImageToVideoPipeline",
@@ -158,7 +193,6 @@ else:
     _import_structure["cogview4"] = ["CogView4Pipeline", "CogView4ControlPipeline"]
     _import_structure["controlnet"].extend(
         [
-            "BlipDiffusionControlNetPipeline",
             "StableDiffusionControlNetImg2ImgPipeline",
             "StableDiffusionControlNetInpaintPipeline",
             "StableDiffusionControlNetPipeline",
@@ -191,12 +225,6 @@ else:
             "SanaPAGPipeline",
         ]
     )
-    _import_structure["controlnet_xs"].extend(
-        [
-            "StableDiffusionControlNetXSPipeline",
-            "StableDiffusionXLControlNetXSPipeline",
-        ]
-    )
     _import_structure["controlnet_hunyuandit"].extend(
         [
             "HunyuanDiTControlNetPipeline",
@@ -264,7 +292,6 @@ else:
             "LEditsPPPipelineStableDiffusionXL",
         ]
     )
-    _import_structure["latte"] = ["LattePipeline"]
     _import_structure["ltx"] = ["LTXPipeline", "LTXImageToVideoPipeline", "LTXConditionPipeline"]
     _import_structure["lumina"] = ["LuminaPipeline", "LuminaText2ImgPipeline"]
     _import_structure["lumina2"] = ["Lumina2Pipeline", "Lumina2Text2ImgPipeline"]
@@ -276,14 +303,9 @@ else:
         ]
     )
     _import_structure["mochi"] = ["MochiPipeline"]
-    _import_structure["musicldm"] = ["MusicLDMPipeline"]
     _import_structure["omnigen"] = ["OmniGenPipeline"]
-    _import_structure["paint_by_example"] = ["PaintByExamplePipeline"]
-    _import_structure["pia"] = ["PIAPipeline"]
     _import_structure["pixart_alpha"] = ["PixArtAlphaPipeline", "PixArtSigmaPipeline"]
     _import_structure["sana"] = ["SanaPipeline", "SanaSprintPipeline", "SanaControlNetPipeline"]
-    _import_structure["semantic_stable_diffusion"] = ["SemanticStableDiffusionPipeline"]
-    _import_structure["shap_e"] = ["ShapEImg2ImgPipeline", "ShapEPipeline"]
     _import_structure["stable_audio"] = [
         "StableAudioProjectionModel",
         "StableAudioPipeline",
@@ -306,7 +328,6 @@ else:
             "StableDiffusionUpscalePipeline",
             "StableUnCLIPImg2ImgPipeline",
             "StableUnCLIPPipeline",
-            "StableDiffusionLDM3DPipeline",
         ]
     )
     _import_structure["aura_flow"] = ["AuraFlowPipeline"]
@@ -315,13 +336,6 @@ else:
         "StableDiffusion3Img2ImgPipeline",
         "StableDiffusion3InpaintPipeline",
     ]
-    _import_structure["stable_diffusion_attend_and_excite"] = ["StableDiffusionAttendAndExcitePipeline"]
-    _import_structure["stable_diffusion_safe"] = ["StableDiffusionPipelineSafe"]
-    _import_structure["stable_diffusion_sag"] = ["StableDiffusionSAGPipeline"]
-    _import_structure["stable_diffusion_gligen"] = [
-        "StableDiffusionGLIGENPipeline",
-        "StableDiffusionGLIGENTextImagePipeline",
-    ]
     _import_structure["stable_video_diffusion"] = ["StableVideoDiffusionPipeline"]
     _import_structure["stable_diffusion_xl"].extend(
         [
@@ -331,32 +345,10 @@ else:
             "StableDiffusionXLPipeline",
         ]
     )
-    _import_structure["stable_diffusion_diffedit"] = ["StableDiffusionDiffEditPipeline"]
-    _import_structure["stable_diffusion_ldm3d"] = ["StableDiffusionLDM3DPipeline"]
-    _import_structure["stable_diffusion_panorama"] = ["StableDiffusionPanoramaPipeline"]
     _import_structure["t2i_adapter"] = [
         "StableDiffusionAdapterPipeline",
         "StableDiffusionXLAdapterPipeline",
     ]
-    _import_structure["text_to_video_synthesis"] = [
-        "TextToVideoSDPipeline",
-        "TextToVideoZeroPipeline",
-        "TextToVideoZeroSDXLPipeline",
-        "VideoToVideoSDPipeline",
-    ]
-    _import_structure["i2vgen_xl"] = ["I2VGenXLPipeline"]
-    _import_structure["unclip"] = ["UnCLIPImageVariationPipeline", "UnCLIPPipeline"]
-    _import_structure["unidiffuser"] = [
-        "ImageTextPipelineOutput",
-        "UniDiffuserModel",
-        "UniDiffuserPipeline",
-        "UniDiffuserTextDecoder",
-    ]
-    _import_structure["wuerstchen"] = [
-        "WuerstchenCombinedPipeline",
-        "WuerstchenDecoderPipeline",
-        "WuerstchenPriorPipeline",
-    ]
     _import_structure["wan"] = ["WanPipeline", "WanImageToVideoPipeline", "WanVideoToVideoPipeline"]
 try:
     if not is_onnx_available():
@@ -395,10 +387,12 @@ except OptionalDependencyNotAvailable:
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_and_k_diffusion_objects))
 else:
-    _import_structure["stable_diffusion_k_diffusion"] = [
+    _import_structure["deprecated"].extend(
-        "StableDiffusionKDiffusionPipeline",
+        [
-        "StableDiffusionXLKDiffusionPipeline",
+            "StableDiffusionKDiffusionPipeline",
-    ]
+            "StableDiffusionXLKDiffusionPipeline",
+        ]
+    )
 
 try:
     if not (is_torch_available() and is_transformers_available() and is_sentencepiece_available()):
@@ -472,10 +466,16 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             AutoPipelineForText2Image,
         )
         from .consistency_models import ConsistencyModelPipeline
-        from .dance_diffusion import DanceDiffusionPipeline
         from .ddim import DDIMPipeline
         from .ddpm import DDPMPipeline
-        from .deprecated import KarrasVePipeline, LDMPipeline, PNDMPipeline, RePaintPipeline, ScoreSdeVePipeline
+        from .deprecated import (
+            DanceDiffusionPipeline,
+            KarrasVePipeline,
+            LDMPipeline,
+            PNDMPipeline,
+            RePaintPipeline,
+            ScoreSdeVePipeline,
+        )
         from .dit import DiTPipeline
         from .latent_diffusion import LDMSuperResolutionPipeline
         from .pipeline_utils import (
@@ -500,7 +500,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from ..utils.dummy_torch_and_transformers_objects import *
     else:
         from .allegro import AllegroPipeline
-        from .amused import AmusedImg2ImgPipeline, AmusedInpaintPipeline, AmusedPipeline
         from .animatediff import (
             AnimateDiffControlNetPipeline,
             AnimateDiffPipeline,
@@ -509,14 +508,12 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             AnimateDiffVideoToVideoControlNetPipeline,
             AnimateDiffVideoToVideoPipeline,
         )
-        from .audioldm import AudioLDMPipeline
         from .audioldm2 import (
             AudioLDM2Pipeline,
             AudioLDM2ProjectionModel,
             AudioLDM2UNet2DConditionModel,
         )
         from .aura_flow import AuraFlowPipeline
-        from .blip_diffusion import BlipDiffusionPipeline
         from .cogvideo import (
             CogVideoXFunControlPipeline,
             CogVideoXImageToVideoPipeline,
@@ -526,7 +523,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from .cogview3 import CogView3PlusPipeline
         from .cogview4 import CogView4ControlPipeline, CogView4Pipeline
         from .controlnet import (
-            BlipDiffusionControlNetPipeline,
             StableDiffusionControlNetImg2ImgPipeline,
             StableDiffusionControlNetInpaintPipeline,
             StableDiffusionControlNetPipeline,
@@ -541,10 +537,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             HunyuanDiTControlNetPipeline,
         )
         from .controlnet_sd3 import StableDiffusion3ControlNetInpaintingPipeline, StableDiffusion3ControlNetPipeline
-        from .controlnet_xs import (
-            StableDiffusionControlNetXSPipeline,
-            StableDiffusionXLControlNetXSPipeline,
-        )
         from .deepfloyd_if import (
             IFImg2ImgPipeline,
             IFImg2ImgSuperResolutionPipeline,
@@ -556,16 +548,53 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from .deprecated import (
             AltDiffusionImg2ImgPipeline,
             AltDiffusionPipeline,
+            AmusedImg2ImgPipeline,
+            AmusedInpaintPipeline,
+            AmusedPipeline,
+            AudioLDMPipeline,
+            BlipDiffusionControlNetPipeline,
+            BlipDiffusionPipeline,
             CycleDiffusionPipeline,
+            I2VGenXLPipeline,
+            ImageTextPipelineOutput,
+            LattePipeline,
+            MusicLDMPipeline,
+            PaintByExamplePipeline,
+            PIAPipeline,
+            SemanticStableDiffusionPipeline,
+            ShapEImg2ImgPipeline,
+            ShapEPipeline,
+            StableDiffusionAttendAndExcitePipeline,
+            StableDiffusionControlNetXSPipeline,
+            StableDiffusionDiffEditPipeline,
+            StableDiffusionGLIGENPipeline,
+            StableDiffusionGLIGENTextImagePipeline,
             StableDiffusionInpaintPipelineLegacy,
+            StableDiffusionLDM3DPipeline,
             StableDiffusionModelEditingPipeline,
+            StableDiffusionPanoramaPipeline,
             StableDiffusionParadigmsPipeline,
+            StableDiffusionPipelineSafe,
             StableDiffusionPix2PixZeroPipeline,
+            StableDiffusionSAGPipeline,
+            StableDiffusionXLControlNetXSPipeline,
+            TextToVideoSDPipeline,
+            TextToVideoZeroPipeline,
+            TextToVideoZeroSDXLPipeline,
+            UnCLIPImageVariationPipeline,
+            UnCLIPPipeline,
+            UniDiffuserModel,
+            UniDiffuserPipeline,
+            UniDiffuserTextDecoder,
             VersatileDiffusionDualGuidedPipeline,
             VersatileDiffusionImageVariationPipeline,
             VersatileDiffusionPipeline,
             VersatileDiffusionTextToImagePipeline,
+            VideoToVideoSDPipeline,
             VQDiffusionPipeline,
+            WuerstchenCombinedPipeline,
+            WuerstchenDecoderPipeline,
+            WuerstchenPriorPipeline,
         )
         from .easyanimate import (
             EasyAnimateControlPipeline,
@@ -593,7 +622,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             HunyuanVideoPipeline,
         )
         from .hunyuandit import HunyuanDiTPipeline
-        from .i2vgen_xl import I2VGenXLPipeline
         from .kandinsky import (
             KandinskyCombinedPipeline,
             KandinskyImg2ImgCombinedPipeline,
@@ -624,7 +652,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             LatentConsistencyModelPipeline,
         )
         from .latent_diffusion import LDMTextToImagePipeline
-        from .latte import LattePipeline
         from .ledits_pp import (
             LEditsPPDiffusionPipelineOutput,
             LEditsPPInversionPipelineOutput,
@@ -640,7 +667,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             MarigoldNormalsPipeline,
         )
         from .mochi import MochiPipeline
-        from .musicldm import MusicLDMPipeline
         from .omnigen import OmniGenPipeline
         from .pag import (
             AnimateDiffPAGPipeline,
@@ -661,12 +687,8 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusionXLPAGInpaintPipeline,
             StableDiffusionXLPAGPipeline,
         )
-        from .paint_by_example import PaintByExamplePipeline
-        from .pia import PIAPipeline
         from .pixart_alpha import PixArtAlphaPipeline, PixArtSigmaPipeline
         from .sana import SanaControlNetPipeline, SanaPipeline, SanaSprintPipeline
-        from .semantic_stable_diffusion import SemanticStableDiffusionPipeline
-        from .shap_e import ShapEImg2ImgPipeline, ShapEPipeline
         from .stable_audio import StableAudioPipeline, StableAudioProjectionModel
         from .stable_cascade import (
             StableCascadeCombinedPipeline,
@@ -691,13 +713,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusion3InpaintPipeline,
             StableDiffusion3Pipeline,
         )
-        from .stable_diffusion_attend_and_excite import StableDiffusionAttendAndExcitePipeline
-        from .stable_diffusion_diffedit import StableDiffusionDiffEditPipeline
-        from .stable_diffusion_gligen import StableDiffusionGLIGENPipeline, StableDiffusionGLIGENTextImagePipeline
-        from .stable_diffusion_ldm3d import StableDiffusionLDM3DPipeline
-        from .stable_diffusion_panorama import StableDiffusionPanoramaPipeline
-        from .stable_diffusion_safe import StableDiffusionPipelineSafe
-        from .stable_diffusion_sag import StableDiffusionSAGPipeline
         from .stable_diffusion_xl import (
             StableDiffusionXLImg2ImgPipeline,
             StableDiffusionXLInpaintPipeline,
@@ -709,25 +724,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusionAdapterPipeline,
             StableDiffusionXLAdapterPipeline,
         )
-        from .text_to_video_synthesis import (
-            TextToVideoSDPipeline,
-            TextToVideoZeroPipeline,
-            TextToVideoZeroSDXLPipeline,
-            VideoToVideoSDPipeline,
-        )
-        from .unclip import UnCLIPImageVariationPipeline, UnCLIPPipeline
-        from .unidiffuser import (
-            ImageTextPipelineOutput,
-            UniDiffuserModel,
-            UniDiffuserPipeline,
-            UniDiffuserTextDecoder,
-        )
         from .wan import WanImageToVideoPipeline, WanPipeline, WanVideoToVideoPipeline
-        from .wuerstchen import (
-            WuerstchenCombinedPipeline,
-            WuerstchenDecoderPipeline,
-            WuerstchenPriorPipeline,
-        )
 
         try:
             if not is_onnx_available():
@@ -758,7 +755,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         except OptionalDependencyNotAvailable:
             from ..utils.dummy_torch_and_transformers_and_k_diffusion_objects import *
         else:
-            from .stable_diffusion_k_diffusion import (
+            from .deprecated import (
                 StableDiffusionKDiffusionPipeline,
                 StableDiffusionXLKDiffusionPipeline,
             )

src/diffusers/pipelines/animatediff/pipeline_animatediff_sdxl.py

@@ -635,7 +635,7 @@ class AnimateDiffSDXLPipeline(
 
         return ip_adapter_image_embeds
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
     def decode_latents(self, latents):
         latents = 1 / self.vae.config.scaling_factor * latents
 
@@ -738,7 +738,7 @@ class AnimateDiffSDXLPipeline(
                 "If `negative_prompt_embeds` are provided, `negative_pooled_prompt_embeds` also have to be passed. Make sure to generate `negative_pooled_prompt_embeds` from the same text encoder that was used to generate `negative_prompt_embeds`."
             )
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
     def prepare_latents(
         self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents=None
     ):

src/diffusers/pipelines/animatediff/pipeline_animatediff_sparsectrl.py

@@ -458,7 +458,7 @@ class AnimateDiffSparseControlNetPipeline(
 
         return ip_adapter_image_embeds
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
     def decode_latents(self, latents):
         latents = 1 / self.vae.config.scaling_factor * latents
 
@@ -621,7 +621,7 @@ class AnimateDiffSparseControlNetPipeline(
                 f"If image batch size is not 1, image batch size must be same as prompt batch size. image batch size: {image_batch_size}, prompt batch size: {prompt_batch_size}"
             )
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
     def prepare_latents(
         self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents=None
     ):

src/diffusers/pipelines/auto_pipeline.py

@@ -39,6 +39,7 @@ from .controlnet_sd3 import (
     StableDiffusion3ControlNetPipeline,
 )
 from .deepfloyd_if import IFImg2ImgPipeline, IFInpaintingPipeline, IFPipeline
+from .deprecated.wuerstchen import WuerstchenCombinedPipeline, WuerstchenDecoderPipeline
 from .flux import (
     FluxControlImg2ImgPipeline,
     FluxControlInpaintPipeline,
@@ -106,7 +107,6 @@ from .stable_diffusion_xl import (
     StableDiffusionXLInpaintPipeline,
     StableDiffusionXLPipeline,
 )
-from .wuerstchen import WuerstchenCombinedPipeline, WuerstchenDecoderPipeline
 
 
 AUTO_TEXT2IMAGE_PIPELINES_MAPPING = OrderedDict(

src/diffusers/pipelines/cogvideo/pipeline_cogvideox.py

@@ -373,7 +373,7 @@ class CogVideoXPipeline(DiffusionPipeline, CogVideoXLoraLoaderMixin):
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
-    # Copied from diffusers.pipelines.latte.pipeline_latte.LattePipeline.check_inputs
+    # Copied from diffusers.pipelines.deprecated.latte.pipeline_latte.LattePipeline.check_inputs
     def check_inputs(
         self,
         prompt,

src/diffusers/pipelines/cogview3/pipeline_cogview3plus.py

@@ -333,7 +333,7 @@ class CogView3PlusPipeline(DiffusionPipeline):
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
-    # Copied from diffusers.pipelines.latte.pipeline_latte.LattePipeline.check_inputs
+    # Copied from diffusers.pipelines.deprecated.latte.pipeline_latte.LattePipeline.check_inputs
     def check_inputs(
         self,
         prompt,

src/diffusers/pipelines/controlnet/__init__.py

@@ -24,7 +24,6 @@ except OptionalDependencyNotAvailable:
 else:
     _import_structure["multicontrolnet"] = ["MultiControlNetModel"]
     _import_structure["pipeline_controlnet"] = ["StableDiffusionControlNetPipeline"]
-    _import_structure["pipeline_controlnet_blip_diffusion"] = ["BlipDiffusionControlNetPipeline"]
     _import_structure["pipeline_controlnet_img2img"] = ["StableDiffusionControlNetImg2ImgPipeline"]
     _import_structure["pipeline_controlnet_inpaint"] = ["StableDiffusionControlNetInpaintPipeline"]
     _import_structure["pipeline_controlnet_inpaint_sd_xl"] = ["StableDiffusionXLControlNetInpaintPipeline"]
@@ -54,7 +53,6 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
     else:
         from .multicontrolnet import MultiControlNetModel
         from .pipeline_controlnet import StableDiffusionControlNetPipeline
-        from .pipeline_controlnet_blip_diffusion import BlipDiffusionControlNetPipeline
         from .pipeline_controlnet_img2img import StableDiffusionControlNetImg2ImgPipeline
         from .pipeline_controlnet_inpaint import StableDiffusionControlNetInpaintPipeline
         from .pipeline_controlnet_inpaint_sd_xl import StableDiffusionXLControlNetInpaintPipeline

src/diffusers/pipelines/deprecated/__init__.py

@@ -1,3 +1,7 @@
+import functools
+import inspect
+import sys
+import warnings
 from typing import TYPE_CHECKING
 
 from ...utils import (
@@ -9,9 +13,32 @@ from ...utils import (
     is_note_seq_available,
     is_torch_available,
     is_transformers_available,
+    logging,
 )
 
 
+logger = logging.get_logger(__name__)
+
+
+# Custom Lazy Module for deprecated pipelines that shows a warning
+class _DeprecatedLazyModule(_LazyModule):
+    """
+    Module class that surfaces all objects but only performs associated imports when the objects are requested, and
+    shows deprecation warnings when any of its attributes are accessed.
+    """
+
+    def __getattr__(self, name):
+        # Regular attribute access - first check if it's supposed to be loaded
+        if name in self._modules or name in self._class_to_module:
+            # Only warn for actual pipeline components, not utility functions
+            logger.warning(
+                f"{name} is deprecated and will no longer be maintained or receive future updates.",
+            )
+
+        # Use the standard lazy module behavior to load the attribute
+        return super().__getattr__(name)
+
+
 _dummy_objects = {}
 _import_structure = {}
 
@@ -23,6 +50,7 @@ except OptionalDependencyNotAvailable:
 
     _dummy_objects.update(get_objects_from_module(dummy_pt_objects))
 else:
+    _import_structure["dance_diffusion"] = ["DanceDiffusionPipeline"]
     _import_structure["latent_diffusion_uncond"] = ["LDMPipeline"]
     _import_structure["pndm"] = ["PNDMPipeline"]
     _import_structure["repaint"] = ["RePaintPipeline"]
@@ -42,6 +70,62 @@ else:
         "AltDiffusionPipeline",
         "AltDiffusionPipelineOutput",
     ]
+    _import_structure["amused"] = ["AmusedPipeline", "AmusedImg2ImgPipeline", "AmusedInpaintPipeline"]
+    _import_structure["audioldm"] = ["AudioLDMPipeline"]
+    _import_structure["controlnet_xs"] = [
+        "StableDiffusionControlNetXSPipeline",
+        "StableDiffusionXLControlNetXSPipeline",
+    ]
+    _import_structure["blip_diffusion"] = ["BlipDiffusionPipeline"]
+    _import_structure["controlnet"] = ["BlipDiffusionControlNetPipeline"]
+    _import_structure["i2vgen_xl"] = ["I2VGenXLPipeline"]
+    _import_structure["latte"] = ["LattePipeline"]
+    _import_structure["musicldm"] = ["MusicLDMPipeline"]
+    _import_structure["paint_by_example"] = ["PaintByExamplePipeline"]
+    _import_structure["pia"] = ["PIAPipeline"]
+    _import_structure["semantic_stable_diffusion"] = ["SemanticStableDiffusionPipeline"]
+    _import_structure["shap_e"] = [
+        "ShapEPipeline",
+        "ShapEImg2ImgPipeline",
+    ]
+    _import_structure["stable_diffusion_attend_and_excite"] = ["StableDiffusionAttendAndExcitePipeline"]
+    _import_structure["stable_diffusion_diffedit"] = ["StableDiffusionDiffEditPipeline"]
+    _import_structure["stable_diffusion_gligen"] = [
+        "StableDiffusionGLIGENPipeline",
+        "StableDiffusionGLIGENTextImagePipeline",
+    ]
+    _import_structure["stable_diffusion_k_diffusion"] = [
+        "StableDiffusionKDiffusionPipeline",
+        "StableDiffusionXLKDiffusionPipeline",
+    ]
+    _import_structure["stable_diffusion_ldm3d"] = ["StableDiffusionLDM3DPipeline"]
+    _import_structure["stable_diffusion_panorama"] = ["StableDiffusionPanoramaPipeline"]
+    _import_structure["stable_diffusion_safe"] = ["StableDiffusionPipelineSafe"]
+    _import_structure["stable_diffusion_sag"] = ["StableDiffusionSAGPipeline"]
+    _import_structure["stable_diffusion_variants"] = [
+        "CycleDiffusionPipeline",
+        "StableDiffusionInpaintPipelineLegacy",
+        "StableDiffusionPix2PixZeroPipeline",
+        "StableDiffusionParadigmsPipeline",
+        "StableDiffusionModelEditingPipeline",
+    ]
+    _import_structure["text_to_video_synthesis"] = [
+        "TextToVideoSDPipeline",
+        "TextToVideoZeroPipeline",
+        "TextToVideoZeroSDXLPipeline",
+        "VideoToVideoSDPipeline",
+    ]
+    _import_structure["unclip"] = [
+        "UnCLIPPipeline",
+        "UnCLIPImageVariationPipeline",
+    ]
+    _import_structure["unidiffuser"] = [
+        "UniDiffuserTextDecoder",
+        "UniDiffuserModel",
+        "UTransformer2DModel",
+        "UniDiffuserPipeline",
+        "ImageTextPipelineOutput",
+    ]
     _import_structure["versatile_diffusion"] = [
         "VersatileDiffusionDualGuidedPipeline",
         "VersatileDiffusionImageVariationPipeline",
@@ -49,12 +133,10 @@ else:
         "VersatileDiffusionTextToImagePipeline",
     ]
     _import_structure["vq_diffusion"] = ["VQDiffusionPipeline"]
-    _import_structure["stable_diffusion_variants"] = [
+    _import_structure["wuerstchen"] = [
-        "CycleDiffusionPipeline",
+        "WuerstchenCombinedPipeline",
-        "StableDiffusionInpaintPipelineLegacy",
+        "WuerstchenDecoderPipeline",
-        "StableDiffusionPix2PixZeroPipeline",
+        "WuerstchenPriorPipeline",
-        "StableDiffusionParadigmsPipeline",
-        "StableDiffusionModelEditingPipeline",
     ]
 
 try:
@@ -88,6 +170,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from ...utils.dummy_pt_objects import *
 
     else:
+        from .dance_diffusion import DanceDiffusionPipeline
         from .latent_diffusion_uncond import LDMPipeline
         from .pndm import PNDMPipeline
         from .repaint import RePaintPipeline
@@ -102,8 +185,29 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
 
     else:
         from .alt_diffusion import AltDiffusionImg2ImgPipeline, AltDiffusionPipeline, AltDiffusionPipelineOutput
-        from .audio_diffusion import AudioDiffusionPipeline, Mel
+        from .amused import AmusedImg2ImgPipeline, AmusedInpaintPipeline, AmusedPipeline
-        from .spectrogram_diffusion import SpectrogramDiffusionPipeline
+        from .audioldm import AudioLDMPipeline
+        from .blip_diffusion import BlipDiffusionPipeline
+        from .controlnet import BlipDiffusionControlNetPipeline
+        from .controlnet_xs import StableDiffusionControlNetXSPipeline, StableDiffusionXLControlNetXSPipeline
+        from .i2vgen_xl import I2VGenXLPipeline
+        from .latte import LattePipeline
+        from .musicldm import MusicLDMPipeline
+        from .paint_by_example import PaintByExamplePipeline
+        from .pia import PIAPipeline
+        from .semantic_stable_diffusion import SemanticStableDiffusionPipeline
+        from .shap_e import ShapEImg2ImgPipeline, ShapEPipeline
+        from .stable_diffusion_attend_and_excite import StableDiffusionAttendAndExcitePipeline
+        from .stable_diffusion_diffedit import StableDiffusionDiffEditPipeline
+        from .stable_diffusion_gligen import StableDiffusionGLIGENPipeline, StableDiffusionGLIGENTextImagePipeline
+        from .stable_diffusion_k_diffusion import (
+            StableDiffusionKDiffusionPipeline,
+            StableDiffusionXLKDiffusionPipeline,
+        )
+        from .stable_diffusion_ldm3d import StableDiffusionLDM3DPipeline
+        from .stable_diffusion_panorama import StableDiffusionPanoramaPipeline
+        from .stable_diffusion_safe import StableDiffusionPipelineSafe
+        from .stable_diffusion_sag import StableDiffusionSAGPipeline
         from .stable_diffusion_variants import (
             CycleDiffusionPipeline,
             StableDiffusionInpaintPipelineLegacy,
@@ -111,7 +215,14 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusionParadigmsPipeline,
             StableDiffusionPix2PixZeroPipeline,
         )
-        from .stochastic_karras_ve import KarrasVePipeline
+        from .text_to_video_synthesis import (
+            TextToVideoSDPipeline,
+            TextToVideoZeroPipeline,
+            TextToVideoZeroSDXLPipeline,
+            VideoToVideoSDPipeline,
+        )
+        from .unclip import UnCLIPImageVariationPipeline, UnCLIPPipeline
+        from .unidiffuser import ImageTextPipelineOutput, UniDiffuserModel, UniDiffuserPipeline, UniDiffuserTextDecoder
         from .versatile_diffusion import (
             VersatileDiffusionDualGuidedPipeline,
             VersatileDiffusionImageVariationPipeline,
@@ -119,6 +230,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             VersatileDiffusionTextToImagePipeline,
         )
         from .vq_diffusion import VQDiffusionPipeline
+        from .wuerstchen import WuerstchenCombinedPipeline, WuerstchenDecoderPipeline, WuerstchenPriorPipeline
 
     try:
         if not (is_torch_available() and is_librosa_available()):
@@ -143,7 +255,8 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
 else:
     import sys
 
-    sys.modules[__name__] = _LazyModule(
+    # Use the custom deprecated lazy module instead of the standard one
+    sys.modules[__name__] = _DeprecatedLazyModule(
         __name__,
         globals()["__file__"],
         _import_structure,

src/diffusers/pipelines/deprecated/amused/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -16,7 +16,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils.dummy_torch_and_transformers_objects import (
+    from ....utils.dummy_torch_and_transformers_objects import (
         AmusedImg2ImgPipeline,
         AmusedInpaintPipeline,
         AmusedPipeline,
@@ -40,7 +40,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         if not (is_transformers_available() and is_torch_available()):
             raise OptionalDependencyNotAvailable()
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import (
+        from ....utils.dummy_torch_and_transformers_objects import (
             AmusedPipeline,
         )
     else:

src/diffusers/pipelines/deprecated/amused/pipeline_amused.py

@@ -17,11 +17,11 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 import torch
 from transformers import CLIPTextModelWithProjection, CLIPTokenizer
 
-from ...image_processor import VaeImageProcessor
+from ....image_processor import VaeImageProcessor
-from ...models import UVit2DModel, VQModel
+from ....models import UVit2DModel, VQModel
-from ...schedulers import AmusedScheduler
+from ....schedulers import AmusedScheduler
-from ...utils import is_torch_xla_available, replace_example_docstring
+from ....utils import is_torch_xla_available, replace_example_docstring
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from ...pipeline_utils import DiffusionPipeline, ImagePipelineOutput
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/amused/pipeline_amused_img2img.py

@@ -17,11 +17,11 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 import torch
 from transformers import CLIPTextModelWithProjection, CLIPTokenizer
 
-from ...image_processor import PipelineImageInput, VaeImageProcessor
+from ....image_processor import PipelineImageInput, VaeImageProcessor
-from ...models import UVit2DModel, VQModel
+from ....models import UVit2DModel, VQModel
-from ...schedulers import AmusedScheduler
+from ....schedulers import AmusedScheduler
-from ...utils import is_torch_xla_available, replace_example_docstring
+from ....utils import is_torch_xla_available, replace_example_docstring
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from ...pipeline_utils import DiffusionPipeline, ImagePipelineOutput
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/amused/pipeline_amused_inpaint.py

@@ -18,11 +18,11 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 import torch
 from transformers import CLIPTextModelWithProjection, CLIPTokenizer
 
-from ...image_processor import PipelineImageInput, VaeImageProcessor
+from ....image_processor import PipelineImageInput, VaeImageProcessor
-from ...models import UVit2DModel, VQModel
+from ....models import UVit2DModel, VQModel
-from ...schedulers import AmusedScheduler
+from ....schedulers import AmusedScheduler
-from ...utils import is_torch_xla_available, replace_example_docstring
+from ....utils import is_torch_xla_available, replace_example_docstring
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from ...pipeline_utils import DiffusionPipeline, ImagePipelineOutput
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/audioldm/__init__.py

@@ -0,0 +1,51 @@
+from typing import TYPE_CHECKING
+
+from ....utils import (
+    DIFFUSERS_SLOW_IMPORT,
+    OptionalDependencyNotAvailable,
+    _LazyModule,
+    is_torch_available,
+    is_transformers_available,
+    is_transformers_version,
+)
+
+
+_dummy_objects = {}
+_import_structure = {}
+
+try:
+    if not (is_transformers_available() and is_torch_available() and is_transformers_version(">=", "4.27.0")):
+        raise OptionalDependencyNotAvailable()
+except OptionalDependencyNotAvailable:
+    from ....utils.dummy_torch_and_transformers_objects import (
+        AudioLDMPipeline,
+    )
+
+    _dummy_objects.update({"AudioLDMPipeline": AudioLDMPipeline})
+else:
+    _import_structure["pipeline_audioldm"] = ["AudioLDMPipeline"]
+
+
+if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
+    try:
+        if not (is_transformers_available() and is_torch_available() and is_transformers_version(">=", "4.27.0")):
+            raise OptionalDependencyNotAvailable()
+    except OptionalDependencyNotAvailable:
+        from ....utils.dummy_torch_and_transformers_objects import (
+            AudioLDMPipeline,
+        )
+
+    else:
+        from .pipeline_audioldm import AudioLDMPipeline
+else:
+    import sys
+
+    sys.modules[__name__] = _LazyModule(
+        __name__,
+        globals()["__file__"],
+        _import_structure,
+        module_spec=__spec__,
+    )
+
+    for name, value in _dummy_objects.items():
+        setattr(sys.modules[__name__], name, value)

src/diffusers/pipelines/deprecated/audioldm/pipeline_audioldm.py

@@ -0,0 +1,561 @@
+# 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.
+
+import inspect
+from typing import Any, Callable, Dict, List, Optional, Union
+
+import numpy as np
+import torch
+import torch.nn.functional as F
+from transformers import ClapTextModelWithProjection, RobertaTokenizer, RobertaTokenizerFast, SpeechT5HifiGan
+
+from ....models import AutoencoderKL, UNet2DConditionModel
+from ....schedulers import KarrasDiffusionSchedulers
+from ....utils import is_torch_xla_available, logging, replace_example_docstring
+from ....utils.torch_utils import randn_tensor
+from ...pipeline_utils import AudioPipelineOutput, DiffusionPipeline, StableDiffusionMixin
+
+
+if is_torch_xla_available():
+    import torch_xla.core.xla_model as xm
+
+    XLA_AVAILABLE = True
+else:
+    XLA_AVAILABLE = False
+
+logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
+
+
+EXAMPLE_DOC_STRING = """
+    Examples:
+        ```py
+        >>> from diffusers import AudioLDMPipeline
+        >>> import torch
+        >>> import scipy
+
+        >>> repo_id = "cvssp/audioldm-s-full-v2"
+        >>> pipe = AudioLDMPipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
+        >>> pipe = pipe.to("cuda")
+
+        >>> prompt = "Techno music with a strong, upbeat tempo and high melodic riffs"
+        >>> audio = pipe(prompt, num_inference_steps=10, audio_length_in_s=5.0).audios[0]
+
+        >>> # save the audio sample as a .wav file
+        >>> scipy.io.wavfile.write("techno.wav", rate=16000, data=audio)
+        ```
+"""
+
+
+class AudioLDMPipeline(DiffusionPipeline, StableDiffusionMixin):
+    r"""
+    Pipeline for text-to-audio generation using AudioLDM.
+
+    This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods
+    implemented for all pipelines (downloading, saving, running on a particular device, etc.).
+
+    Args:
+        vae ([`AutoencoderKL`]):
+            Variational Auto-Encoder (VAE) model to encode and decode images to and from latent representations.
+        text_encoder ([`~transformers.ClapTextModelWithProjection`]):
+            Frozen text-encoder (`ClapTextModelWithProjection`, specifically the
+            [laion/clap-htsat-unfused](https://huggingface.co/laion/clap-htsat-unfused) variant.
+        tokenizer ([`PreTrainedTokenizer`]):
+            A [`~transformers.RobertaTokenizer`] to tokenize text.
+        unet ([`UNet2DConditionModel`]):
+            A `UNet2DConditionModel` to denoise the encoded audio latents.
+        scheduler ([`SchedulerMixin`]):
+            A scheduler to be used in combination with `unet` to denoise the encoded audio latents. Can be one of
+            [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
+        vocoder ([`~transformers.SpeechT5HifiGan`]):
+            Vocoder of class `SpeechT5HifiGan`.
+    """
+
+    model_cpu_offload_seq = "text_encoder->unet->vae"
+
+    def __init__(
+        self,
+        vae: AutoencoderKL,
+        text_encoder: ClapTextModelWithProjection,
+        tokenizer: Union[RobertaTokenizer, RobertaTokenizerFast],
+        unet: UNet2DConditionModel,
+        scheduler: KarrasDiffusionSchedulers,
+        vocoder: SpeechT5HifiGan,
+    ):
+        super().__init__()
+
+        logger.warning(f"{self.__class__.__name__} is deprecated and will no longer be actively maintained")
+
+        logger.warning(f"{self.__class__.__name__} is deprecated and will no longer be actively maintained")
+
+        self.register_modules(
+            vae=vae,
+            text_encoder=text_encoder,
+            tokenizer=tokenizer,
+            unet=unet,
+            scheduler=scheduler,
+            vocoder=vocoder,
+        )
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1) if getattr(self, "vae", None) else 8
+
+    def _encode_prompt(
+        self,
+        prompt,
+        device,
+        num_waveforms_per_prompt,
+        do_classifier_free_guidance,
+        negative_prompt=None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
+    ):
+        r"""
+        Encodes the prompt into text encoder hidden states.
+
+        Args:
+            prompt (`str` or `List[str]`, *optional*):
+                prompt to be encoded
+            device (`torch.device`):
+                torch device
+            num_waveforms_per_prompt (`int`):
+                number of waveforms that should be generated per prompt
+            do_classifier_free_guidance (`bool`):
+                whether to use classifier free guidance or not
+            negative_prompt (`str` or `List[str]`, *optional*):
+                The prompt or prompts not to guide the audio generation. If not defined, one has to pass
+                `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
+                less than `1`).
+            prompt_embeds (`torch.Tensor`, *optional*):
+                Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
+                provided, text embeddings will be generated from `prompt` input argument.
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
+                Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
+                weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
+                argument.
+        """
+        if prompt is not None and isinstance(prompt, str):
+            batch_size = 1
+        elif prompt is not None and isinstance(prompt, list):
+            batch_size = len(prompt)
+        else:
+            batch_size = prompt_embeds.shape[0]
+
+        if prompt_embeds is None:
+            text_inputs = self.tokenizer(
+                prompt,
+                padding="max_length",
+                max_length=self.tokenizer.model_max_length,
+                truncation=True,
+                return_tensors="pt",
+            )
+            text_input_ids = text_inputs.input_ids
+            attention_mask = text_inputs.attention_mask
+            untruncated_ids = self.tokenizer(prompt, padding="longest", return_tensors="pt").input_ids
+
+            if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal(
+                text_input_ids, untruncated_ids
+            ):
+                removed_text = self.tokenizer.batch_decode(
+                    untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1]
+                )
+                logger.warning(
+                    "The following part of your input was truncated because CLAP can only handle sequences up to"
+                    f" {self.tokenizer.model_max_length} tokens: {removed_text}"
+                )
+
+            prompt_embeds = self.text_encoder(
+                text_input_ids.to(device),
+                attention_mask=attention_mask.to(device),
+            )
+            prompt_embeds = prompt_embeds.text_embeds
+            # additional L_2 normalization over each hidden-state
+            prompt_embeds = F.normalize(prompt_embeds, dim=-1)
+
+        prompt_embeds = prompt_embeds.to(dtype=self.text_encoder.dtype, device=device)
+
+        (
+            bs_embed,
+            seq_len,
+        ) = prompt_embeds.shape
+        # duplicate text embeddings for each generation per prompt, using mps friendly method
+        prompt_embeds = prompt_embeds.repeat(1, num_waveforms_per_prompt)
+        prompt_embeds = prompt_embeds.view(bs_embed * num_waveforms_per_prompt, seq_len)
+
+        # get unconditional embeddings for classifier free guidance
+        if do_classifier_free_guidance and negative_prompt_embeds is None:
+            uncond_tokens: List[str]
+            if negative_prompt is None:
+                uncond_tokens = [""] * batch_size
+            elif type(prompt) is not type(negative_prompt):
+                raise TypeError(
+                    f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
+                    f" {type(prompt)}."
+                )
+            elif isinstance(negative_prompt, str):
+                uncond_tokens = [negative_prompt]
+            elif batch_size != len(negative_prompt):
+                raise ValueError(
+                    f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
+                    f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
+                    " the batch size of `prompt`."
+                )
+            else:
+                uncond_tokens = negative_prompt
+
+            max_length = prompt_embeds.shape[1]
+            uncond_input = self.tokenizer(
+                uncond_tokens,
+                padding="max_length",
+                max_length=max_length,
+                truncation=True,
+                return_tensors="pt",
+            )
+
+            uncond_input_ids = uncond_input.input_ids.to(device)
+            attention_mask = uncond_input.attention_mask.to(device)
+
+            negative_prompt_embeds = self.text_encoder(
+                uncond_input_ids,
+                attention_mask=attention_mask,
+            )
+            negative_prompt_embeds = negative_prompt_embeds.text_embeds
+            # additional L_2 normalization over each hidden-state
+            negative_prompt_embeds = F.normalize(negative_prompt_embeds, dim=-1)
+
+        if do_classifier_free_guidance:
+            # duplicate unconditional embeddings for each generation per prompt, using mps friendly method
+            seq_len = negative_prompt_embeds.shape[1]
+
+            negative_prompt_embeds = negative_prompt_embeds.to(dtype=self.text_encoder.dtype, device=device)
+
+            negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_waveforms_per_prompt)
+            negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_waveforms_per_prompt, seq_len)
+
+            # For classifier free guidance, we need to do two forward passes.
+            # Here we concatenate the unconditional and text embeddings into a single batch
+            # to avoid doing two forward passes
+            prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
+
+        return prompt_embeds
+
+    def decode_latents(self, latents):
+        latents = 1 / self.vae.config.scaling_factor * latents
+        mel_spectrogram = self.vae.decode(latents).sample
+        return mel_spectrogram
+
+    def mel_spectrogram_to_waveform(self, mel_spectrogram):
+        if mel_spectrogram.dim() == 4:
+            mel_spectrogram = mel_spectrogram.squeeze(1)
+
+        waveform = self.vocoder(mel_spectrogram)
+        # we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
+        waveform = waveform.cpu().float()
+        return waveform
+
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_extra_step_kwargs
+    def prepare_extra_step_kwargs(self, generator, eta):
+        # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
+        # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
+        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
+        # and should be between [0, 1]
+
+        accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
+        extra_step_kwargs = {}
+        if accepts_eta:
+            extra_step_kwargs["eta"] = eta
+
+        # check if the scheduler accepts generator
+        accepts_generator = "generator" in set(inspect.signature(self.scheduler.step).parameters.keys())
+        if accepts_generator:
+            extra_step_kwargs["generator"] = generator
+        return extra_step_kwargs
+
+    def check_inputs(
+        self,
+        prompt,
+        audio_length_in_s,
+        vocoder_upsample_factor,
+        callback_steps,
+        negative_prompt=None,
+        prompt_embeds=None,
+        negative_prompt_embeds=None,
+    ):
+        min_audio_length_in_s = vocoder_upsample_factor * self.vae_scale_factor
+        if audio_length_in_s < min_audio_length_in_s:
+            raise ValueError(
+                f"`audio_length_in_s` has to be a positive value greater than or equal to {min_audio_length_in_s}, but "
+                f"is {audio_length_in_s}."
+            )
+
+        if self.vocoder.config.model_in_dim % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"The number of frequency bins in the vocoder's log-mel spectrogram has to be divisible by the "
+                f"VAE scale factor, but got {self.vocoder.config.model_in_dim} bins and a scale factor of "
+                f"{self.vae_scale_factor}."
+            )
+
+        if (callback_steps is None) or (
+            callback_steps is not None and (not isinstance(callback_steps, int) or callback_steps <= 0)
+        ):
+            raise ValueError(
+                f"`callback_steps` has to be a positive integer but is {callback_steps} of type"
+                f" {type(callback_steps)}."
+            )
+
+        if prompt is not None and prompt_embeds is not None:
+            raise ValueError(
+                f"Cannot forward both `prompt`: {prompt} and `prompt_embeds`: {prompt_embeds}. Please make sure to"
+                " only forward one of the two."
+            )
+        elif prompt is None and prompt_embeds is None:
+            raise ValueError(
+                "Provide either `prompt` or `prompt_embeds`. Cannot leave both `prompt` and `prompt_embeds` undefined."
+            )
+        elif prompt is not None and (not isinstance(prompt, str) and not isinstance(prompt, list)):
+            raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
+
+        if negative_prompt is not None and negative_prompt_embeds is not None:
+            raise ValueError(
+                f"Cannot forward both `negative_prompt`: {negative_prompt} and `negative_prompt_embeds`:"
+                f" {negative_prompt_embeds}. Please make sure to only forward one of the two."
+            )
+
+        if prompt_embeds is not None and negative_prompt_embeds is not None:
+            if prompt_embeds.shape != negative_prompt_embeds.shape:
+                raise ValueError(
+                    "`prompt_embeds` and `negative_prompt_embeds` must have the same shape when passed directly, but"
+                    f" got: `prompt_embeds` {prompt_embeds.shape} != `negative_prompt_embeds`"
+                    f" {negative_prompt_embeds.shape}."
+                )
+
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents with width->self.vocoder.config.model_in_dim
+    def prepare_latents(self, batch_size, num_channels_latents, height, dtype, device, generator, latents=None):
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(self.vocoder.config.model_in_dim) // self.vae_scale_factor,
+        )
+        if isinstance(generator, list) and len(generator) != batch_size:
+            raise ValueError(
+                f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
+                f" size of {batch_size}. Make sure the batch size matches the length of the generators."
+            )
+
+        if latents is None:
+            latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
+        else:
+            latents = latents.to(device)
+
+        # scale the initial noise by the standard deviation required by the scheduler
+        latents = latents * self.scheduler.init_noise_sigma
+        return latents
+
+    @torch.no_grad()
+    @replace_example_docstring(EXAMPLE_DOC_STRING)
+    def __call__(
+        self,
+        prompt: Union[str, List[str]] = None,
+        audio_length_in_s: Optional[float] = None,
+        num_inference_steps: int = 10,
+        guidance_scale: float = 2.5,
+        negative_prompt: Optional[Union[str, List[str]]] = None,
+        num_waveforms_per_prompt: Optional[int] = 1,
+        eta: float = 0.0,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        latents: Optional[torch.Tensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
+        return_dict: bool = True,
+        callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
+        callback_steps: Optional[int] = 1,
+        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
+        output_type: Optional[str] = "np",
+    ):
+        r"""
+        The call function to the pipeline for generation.
+
+        Args:
+            prompt (`str` or `List[str]`, *optional*):
+                The prompt or prompts to guide audio generation. If not defined, you need to pass `prompt_embeds`.
+            audio_length_in_s (`int`, *optional*, defaults to 5.12):
+                The length of the generated audio sample in seconds.
+            num_inference_steps (`int`, *optional*, defaults to 10):
+                The number of denoising steps. More denoising steps usually lead to a higher quality audio at the
+                expense of slower inference.
+            guidance_scale (`float`, *optional*, defaults to 2.5):
+                A higher guidance scale value encourages the model to generate audio that is closely linked to the text
+                `prompt` at the expense of lower sound quality. Guidance scale is enabled when `guidance_scale > 1`.
+            negative_prompt (`str` or `List[str]`, *optional*):
+                The prompt or prompts to guide what to not include in audio generation. If not defined, you need to
+                pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`).
+            num_waveforms_per_prompt (`int`, *optional*, defaults to 1):
+                The number of waveforms to generate per prompt.
+            eta (`float`, *optional*, defaults to 0.0):
+                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
+                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
+            generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
+                A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
+                generation deterministic.
+            latents (`torch.Tensor`, *optional*):
+                Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
+                generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
+                tensor is generated by sampling using the supplied random `generator`.
+            prompt_embeds (`torch.Tensor`, *optional*):
+                Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
+                provided, text embeddings are generated from the `prompt` input argument.
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
+                Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
+                not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
+            return_dict (`bool`, *optional*, defaults to `True`):
+                Whether or not to return a [`~pipelines.AudioPipelineOutput`] instead of a plain tuple.
+            callback (`Callable`, *optional*):
+                A function that calls every `callback_steps` steps during inference. The function is called with the
+                following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
+            callback_steps (`int`, *optional*, defaults to 1):
+                The frequency at which the `callback` function is called. If not specified, the callback is called at
+                every step.
+            cross_attention_kwargs (`dict`, *optional*):
+                A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in
+                [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
+            output_type (`str`, *optional*, defaults to `"np"`):
+                The output format of the generated image. Choose between `"np"` to return a NumPy `np.ndarray` or
+                `"pt"` to return a PyTorch `torch.Tensor` object.
+
+        Examples:
+
+        Returns:
+            [`~pipelines.AudioPipelineOutput`] or `tuple`:
+                If `return_dict` is `True`, [`~pipelines.AudioPipelineOutput`] is returned, otherwise a `tuple` is
+                returned where the first element is a list with the generated audio.
+        """
+        # 0. Convert audio input length from seconds to spectrogram height
+        vocoder_upsample_factor = np.prod(self.vocoder.config.upsample_rates) / self.vocoder.config.sampling_rate
+
+        if audio_length_in_s is None:
+            audio_length_in_s = self.unet.config.sample_size * self.vae_scale_factor * vocoder_upsample_factor
+
+        height = int(audio_length_in_s / vocoder_upsample_factor)
+
+        original_waveform_length = int(audio_length_in_s * self.vocoder.config.sampling_rate)
+        if height % self.vae_scale_factor != 0:
+            height = int(np.ceil(height / self.vae_scale_factor)) * self.vae_scale_factor
+            logger.info(
+                f"Audio length in seconds {audio_length_in_s} is increased to {height * vocoder_upsample_factor} "
+                f"so that it can be handled by the model. It will be cut to {audio_length_in_s} after the "
+                f"denoising process."
+            )
+
+        # 1. Check inputs. Raise error if not correct
+        self.check_inputs(
+            prompt,
+            audio_length_in_s,
+            vocoder_upsample_factor,
+            callback_steps,
+            negative_prompt,
+            prompt_embeds,
+            negative_prompt_embeds,
+        )
+
+        # 2. Define call parameters
+        if prompt is not None and isinstance(prompt, str):
+            batch_size = 1
+        elif prompt is not None and isinstance(prompt, list):
+            batch_size = len(prompt)
+        else:
+            batch_size = prompt_embeds.shape[0]
+
+        device = self._execution_device
+        # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
+        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+        # corresponds to doing no classifier free guidance.
+        do_classifier_free_guidance = guidance_scale > 1.0
+
+        # 3. Encode input prompt
+        prompt_embeds = self._encode_prompt(
+            prompt,
+            device,
+            num_waveforms_per_prompt,
+            do_classifier_free_guidance,
+            negative_prompt,
+            prompt_embeds=prompt_embeds,
+            negative_prompt_embeds=negative_prompt_embeds,
+        )
+
+        # 4. Prepare timesteps
+        self.scheduler.set_timesteps(num_inference_steps, device=device)
+        timesteps = self.scheduler.timesteps
+
+        # 5. Prepare latent variables
+        num_channels_latents = self.unet.config.in_channels
+        latents = self.prepare_latents(
+            batch_size * num_waveforms_per_prompt,
+            num_channels_latents,
+            height,
+            prompt_embeds.dtype,
+            device,
+            generator,
+            latents,
+        )
+
+        # 6. Prepare extra step kwargs
+        extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
+
+        # 7. Denoising loop
+        num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
+        with self.progress_bar(total=num_inference_steps) as progress_bar:
+            for i, t in enumerate(timesteps):
+                # expand the latents if we are doing classifier free guidance
+                latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
+                latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
+
+                # predict the noise residual
+                noise_pred = self.unet(
+                    latent_model_input,
+                    t,
+                    encoder_hidden_states=None,
+                    class_labels=prompt_embeds,
+                    cross_attention_kwargs=cross_attention_kwargs,
+                ).sample
+
+                # perform guidance
+                if do_classifier_free_guidance:
+                    noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
+                    noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
+
+                # compute the previous noisy sample x_t -> x_t-1
+                latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs).prev_sample
+
+                # call the callback, if provided
+                if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0):
+                    progress_bar.update()
+                    if callback is not None and i % callback_steps == 0:
+                        step_idx = i // getattr(self.scheduler, "order", 1)
+                        callback(step_idx, t, latents)
+
+                if XLA_AVAILABLE:
+                    xm.mark_step()
+
+        # 8. Post-processing
+        mel_spectrogram = self.decode_latents(latents)
+
+        audio = self.mel_spectrogram_to_waveform(mel_spectrogram)
+
+        audio = audio[:, :original_waveform_length]
+
+        if output_type == "np":
+            audio = audio.numpy()
+
+        if not return_dict:
+            return (audio,)
+
+        return AudioPipelineOutput(audios=audio)

src/diffusers/pipelines/deprecated/blip_diffusion/__init__.py

@@ -5,7 +5,7 @@ import numpy as np
 import PIL
 from PIL import Image
 
-from ...utils import OptionalDependencyNotAvailable, is_torch_available, is_transformers_available
+from ....utils import OptionalDependencyNotAvailable, is_torch_available, is_transformers_available
 
 
 try:

src/diffusers/pipelines/deprecated/blip_diffusion/pipeline_blip_diffusion.py

@@ -17,15 +17,15 @@ import PIL.Image
 import torch
 from transformers import CLIPTokenizer
 
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...schedulers import PNDMScheduler
+from ....schedulers import PNDMScheduler
-from ...utils import (
+from ....utils import (
     is_torch_xla_available,
     logging,
     replace_example_docstring,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from ...pipeline_utils import DiffusionPipeline, ImagePipelineOutput
 from .blip_image_processing import BlipImageProcessor
 from .modeling_blip2 import Blip2QFormerModel
 from .modeling_ctx_clip import ContextCLIPTextModel

src/diffusers/pipelines/deprecated/controlnet/__init__.py

@@ -0,0 +1,46 @@
+from typing import TYPE_CHECKING
+
+from ....utils import (
+    DIFFUSERS_SLOW_IMPORT,
+    OptionalDependencyNotAvailable,
+    _LazyModule,
+    get_objects_from_module,
+    is_torch_available,
+    is_transformers_available,
+)
+
+
+_dummy_objects = {}
+_import_structure = {}
+
+try:
+    if not (is_transformers_available() and is_torch_available()):
+        raise OptionalDependencyNotAvailable()
+except OptionalDependencyNotAvailable:
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
+
+    _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
+else:
+    _import_structure["pipeline_controlnet_blip_diffusion"] = ["BlipDiffusionControlNetPipeline"]
+
+if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
+    try:
+        if not (is_transformers_available() and is_torch_available()):
+            raise OptionalDependencyNotAvailable()
+
+    except OptionalDependencyNotAvailable:
+        from ...utils.dummy_torch_and_transformers_objects import *
+    else:
+        from .pipeline_controlnet_blip_diffusion import BlipDiffusionControlNetPipeline
+
+else:
+    import sys
+
+    sys.modules[__name__] = _LazyModule(
+        __name__,
+        globals()["__file__"],
+        _import_structure,
+        module_spec=__spec__,
+    )
+    for name, value in _dummy_objects.items():
+        setattr(sys.modules[__name__], name, value)

src/diffusers/pipelines/deprecated/controlnet/pipeline_controlnet_blip_diffusion.py

@@ -18,18 +18,18 @@ import PIL.Image
 import torch
 from transformers import CLIPTokenizer
 
-from ...models import AutoencoderKL, ControlNetModel, UNet2DConditionModel
+from ....models import AutoencoderKL, ControlNetModel, UNet2DConditionModel
-from ...schedulers import PNDMScheduler
+from ....schedulers import PNDMScheduler
-from ...utils import (
+from ....utils import (
     is_torch_xla_available,
     logging,
     replace_example_docstring,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
+from ...pipeline_utils import DiffusionPipeline, ImagePipelineOutput
 from ..blip_diffusion.blip_image_processing import BlipImageProcessor
 from ..blip_diffusion.modeling_blip2 import Blip2QFormerModel
 from ..blip_diffusion.modeling_ctx_clip import ContextCLIPTextModel
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/controlnet_xs/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -18,7 +18,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -28,7 +28,7 @@ try:
     if not (is_transformers_available() and is_flax_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_flax_and_transformers_objects  # noqa F403
+    from ....utils import dummy_flax_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_flax_and_transformers_objects))
 else:
@@ -41,7 +41,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_controlnet_xs import StableDiffusionControlNetXSPipeline
         from .pipeline_controlnet_xs_sd_xl import StableDiffusionXLControlNetXSPipeline
@@ -50,7 +50,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         if not (is_transformers_available() and is_flax_available()):
             raise OptionalDependencyNotAvailable()
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_flax_and_transformers_objects import *  # noqa F403
+        from ....utils.dummy_flax_and_transformers_objects import *  # noqa F403
     else:
         pass  # from .pipeline_flax_controlnet import FlaxStableDiffusionControlNetPipeline
 

src/diffusers/pipelines/deprecated/controlnet_xs/pipeline_controlnet_xs.py

@@ -21,13 +21,13 @@ import torch
 import torch.nn.functional as F
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
-from ...callbacks import MultiPipelineCallbacks, PipelineCallback
+from ....callbacks import MultiPipelineCallbacks, PipelineCallback
-from ...image_processor import PipelineImageInput, VaeImageProcessor
+from ....image_processor import PipelineImageInput, VaeImageProcessor
-from ...loaders import FromSingleFileMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import FromSingleFileMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, ControlNetXSAdapter, UNet2DConditionModel, UNetControlNetXSModel
+from ....models import AutoencoderKL, ControlNetXSAdapter, UNet2DConditionModel, UNetControlNetXSModel
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     deprecate,
     is_torch_xla_available,
@@ -36,10 +36,10 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import is_compiled_module, is_torch_version, randn_tensor
+from ....utils.torch_utils import is_compiled_module, is_torch_version, randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion.pipeline_output import StableDiffusionPipelineOutput
+from ...stable_diffusion.pipeline_output import StableDiffusionPipelineOutput
-from ..stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from ...stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/controlnet_xs/pipeline_controlnet_xs_sd_xl.py

@@ -28,33 +28,33 @@ from transformers import (
 
 from diffusers.utils.import_utils import is_invisible_watermark_available
 
-from ...callbacks import MultiPipelineCallbacks, PipelineCallback
+from ....callbacks import MultiPipelineCallbacks, PipelineCallback
-from ...image_processor import PipelineImageInput, VaeImageProcessor
+from ....image_processor import PipelineImageInput, VaeImageProcessor
-from ...loaders import FromSingleFileMixin, StableDiffusionXLLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import FromSingleFileMixin, StableDiffusionXLLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, ControlNetXSAdapter, UNet2DConditionModel, UNetControlNetXSModel
+from ....models import AutoencoderKL, ControlNetXSAdapter, UNet2DConditionModel, UNetControlNetXSModel
-from ...models.attention_processor import (
+from ....models.attention_processor import (
     AttnProcessor2_0,
     XFormersAttnProcessor,
 )
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     logging,
     replace_example_docstring,
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import is_compiled_module, is_torch_version, randn_tensor
+from ....utils.torch_utils import is_compiled_module, is_torch_version, randn_tensor
-from ..pipeline_utils import DiffusionPipeline
+from ...pipeline_utils import DiffusionPipeline
-from ..stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
+from ...stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
 
 
 if is_invisible_watermark_available():
-    from ..stable_diffusion_xl.watermark import StableDiffusionXLWatermarker
+    from ...stable_diffusion_xl.watermark import StableDiffusionXLWatermarker
 
 
-from ...utils import is_torch_xla_available
+from ....utils import is_torch_xla_available
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/dance_diffusion/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import DIFFUSERS_SLOW_IMPORT, _LazyModule
+from ....utils import DIFFUSERS_SLOW_IMPORT, _LazyModule
 
 
 _import_structure = {"pipeline_dance_diffusion": ["DanceDiffusionPipeline"]}

src/diffusers/pipelines/deprecated/dance_diffusion/pipeline_dance_diffusion.py

@@ -17,11 +17,11 @@ from typing import List, Optional, Tuple, Union
 
 import torch
 
-from ...models import UNet1DModel
+from ....models import UNet1DModel
-from ...schedulers import SchedulerMixin
+from ....schedulers import SchedulerMixin
-from ...utils import is_torch_xla_available, logging
+from ....utils import is_torch_xla_available, logging
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import AudioPipelineOutput, DiffusionPipeline
+from ...pipeline_utils import AudioPipelineOutput, DiffusionPipeline
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/i2vgen_xl/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -17,7 +17,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -29,7 +29,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         if not (is_transformers_available() and is_torch_available()):
             raise OptionalDependencyNotAvailable()
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *  # noqa F403
+        from ....utils.dummy_torch_and_transformers_objects import *  # noqa F403
     else:
         from .pipeline_i2vgen_xl import I2VGenXLPipeline
 

src/diffusers/pipelines/deprecated/i2vgen_xl/pipeline_i2vgen_xl.py

@@ -21,19 +21,19 @@ import PIL
 import torch
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
 
-from ...image_processor import PipelineImageInput, VaeImageProcessor
+from ....image_processor import PipelineImageInput, VaeImageProcessor
-from ...models import AutoencoderKL
+from ....models import AutoencoderKL
-from ...models.unets.unet_i2vgen_xl import I2VGenXLUNet
+from ....models.unets.unet_i2vgen_xl import I2VGenXLUNet
-from ...schedulers import DDIMScheduler
+from ....schedulers import DDIMScheduler
-from ...utils import (
+from ....utils import (
     BaseOutput,
     is_torch_xla_available,
     logging,
     replace_example_docstring,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ...video_processor import VideoProcessor
+from ....video_processor import VideoProcessor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 
 
 if is_torch_xla_available():
@@ -479,7 +479,7 @@ class I2VGenXLPipeline(
 
         return image_latents
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
     def prepare_latents(
         self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents=None
     ):

src/diffusers/pipelines/deprecated/latte/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -18,7 +18,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -30,7 +30,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_latte import LattePipeline
 

src/diffusers/pipelines/deprecated/latte/pipeline_latte.py

@@ -23,11 +23,10 @@ from typing import Callable, Dict, List, Optional, Tuple, Union
 import torch
 from transformers import T5EncoderModel, T5Tokenizer
 
-from ...callbacks import MultiPipelineCallbacks, PipelineCallback
+from ....callbacks import MultiPipelineCallbacks, PipelineCallback
-from ...models import AutoencoderKL, LatteTransformer3DModel
+from ....models import AutoencoderKL, LatteTransformer3DModel
-from ...pipelines.pipeline_utils import DiffusionPipeline
+from ....schedulers import KarrasDiffusionSchedulers
-from ...schedulers import KarrasDiffusionSchedulers
+from ....utils import (
-from ...utils import (
     BACKENDS_MAPPING,
     BaseOutput,
     deprecate,
@@ -37,8 +36,9 @@ from ...utils import (
     logging,
     replace_example_docstring,
 )
-from ...utils.torch_utils import is_compiled_module, randn_tensor
+from ....utils.torch_utils import is_compiled_module, randn_tensor
-from ...video_processor import VideoProcessor
+from ....video_processor import VideoProcessor
+from ...pipeline_utils import DiffusionPipeline
 
 
 if is_torch_xla_available():
@@ -561,7 +561,7 @@ class LattePipeline(DiffusionPipeline):
 
         return caption.strip()
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
     def prepare_latents(
         self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents=None
     ):

src/diffusers/pipelines/deprecated/musicldm/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -18,7 +18,7 @@ try:
     if not (is_transformers_available() and is_torch_available() and is_transformers_version(">=", "4.27.0")):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -31,7 +31,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_musicldm import MusicLDMPipeline
 

src/diffusers/pipelines/deprecated/musicldm/pipeline_musicldm.py

@@ -26,24 +26,24 @@ from transformers import (
     SpeechT5HifiGan,
 )
 
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     is_accelerate_available,
     is_accelerate_version,
     is_librosa_available,
     logging,
     replace_example_docstring,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import AudioPipelineOutput, DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import AudioPipelineOutput, DiffusionPipeline, StableDiffusionMixin
 
 
 if is_librosa_available():
     import librosa
 
 
-from ...utils import is_torch_xla_available
+from ....utils import is_torch_xla_available
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/paint_by_example/__init__.py

@@ -5,7 +5,7 @@ import numpy as np
 import PIL
 from PIL import Image
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -22,7 +22,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -36,7 +36,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .image_encoder import PaintByExampleImageEncoder
         from .pipeline_paint_by_example import PaintByExamplePipeline

src/diffusers/pipelines/deprecated/paint_by_example/image_encoder.py

@@ -15,8 +15,8 @@ import torch
 from torch import nn
 from transformers import CLIPPreTrainedModel, CLIPVisionModel
 
-from ...models.attention import BasicTransformerBlock
+from ....models.attention import BasicTransformerBlock
-from ...utils import logging
+from ....utils import logging
 
 
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name

src/diffusers/pipelines/deprecated/paint_by_example/pipeline_paint_by_example.py

@@ -20,14 +20,14 @@ import PIL.Image
 import torch
 from transformers import CLIPImageProcessor
 
-from ...image_processor import VaeImageProcessor
+from ....image_processor import VaeImageProcessor
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...schedulers import DDIMScheduler, LMSDiscreteScheduler, PNDMScheduler
+from ....schedulers import DDIMScheduler, LMSDiscreteScheduler, PNDMScheduler
-from ...utils import deprecate, is_torch_xla_available, logging
+from ....utils import deprecate, is_torch_xla_available, logging
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion import StableDiffusionPipelineOutput
+from ...stable_diffusion import StableDiffusionPipelineOutput
-from ..stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from ...stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 from .image_encoder import PaintByExampleImageEncoder
 
 

src/diffusers/pipelines/deprecated/pia/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -17,7 +17,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects
+    from ....utils import dummy_torch_and_transformers_objects
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -28,7 +28,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         if not (is_transformers_available() and is_torch_available()):
             raise OptionalDependencyNotAvailable()
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
 
     else:
         from .pipeline_pia import PIAPipeline, PIAPipelineOutput

src/diffusers/pipelines/deprecated/pia/pipeline_pia.py

@@ -21,12 +21,17 @@ import PIL
 import torch
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
 
-from ...image_processor import PipelineImageInput
+from ....image_processor import PipelineImageInput
-from ...loaders import FromSingleFileMixin, IPAdapterMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import (
-from ...models import AutoencoderKL, ImageProjection, UNet2DConditionModel, UNetMotionModel
+    FromSingleFileMixin,
-from ...models.lora import adjust_lora_scale_text_encoder
+    IPAdapterMixin,
-from ...models.unets.unet_motion_model import MotionAdapter
+    StableDiffusionLoraLoaderMixin,
-from ...schedulers import (
+    TextualInversionLoaderMixin,
+)
+from ....models import AutoencoderKL, ImageProjection, UNet2DConditionModel, UNetMotionModel
+from ....models.lora import adjust_lora_scale_text_encoder
+from ....models.unets.unet_motion_model import MotionAdapter
+from ....schedulers import (
     DDIMScheduler,
     DPMSolverMultistepScheduler,
     EulerAncestralDiscreteScheduler,
@@ -34,7 +39,7 @@ from ...schedulers import (
     LMSDiscreteScheduler,
     PNDMScheduler,
 )
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     BaseOutput,
     is_torch_xla_available,
@@ -43,10 +48,10 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ...video_processor import VideoProcessor
+from ....video_processor import VideoProcessor
-from ..free_init_utils import FreeInitMixin
+from ...free_init_utils import FreeInitMixin
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 
 
 if is_torch_xla_available():
@@ -191,6 +196,8 @@ class PIAPipeline(
         image_encoder: CLIPVisionModelWithProjection = None,
     ):
         super().__init__()
+
+        logger.warning(f"{self.__class__.__name__} is deprecated and will no longer be actively maintained")
         if isinstance(unet, UNet2DConditionModel):
             unet = UNetMotionModel.from_unet2d(unet, motion_adapter)
 
@@ -415,7 +422,7 @@ class PIAPipeline(
 
             return image_embeds, uncond_image_embeds
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis/pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
     def decode_latents(self, latents):
         latents = 1 / self.vae.config.scaling_factor * latents
 
@@ -555,7 +562,7 @@ class PIAPipeline(
 
         return ip_adapter_image_embeds
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.prepare_latents
     def prepare_latents(
         self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents=None
     ):

src/diffusers/pipelines/deprecated/semantic_stable_diffusion/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -17,7 +17,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -31,7 +31,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_semantic_stable_diffusion import SemanticStableDiffusionPipeline
 

src/diffusers/pipelines/deprecated/semantic_stable_diffusion/pipeline_output.py

@@ -4,7 +4,7 @@ from typing import List, Optional, Union
 import numpy as np
 import PIL.Image
 
-from ...utils import BaseOutput
+from ....utils import BaseOutput
 
 
 @dataclass

src/diffusers/pipelines/deprecated/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py

@@ -5,13 +5,13 @@ from typing import Callable, List, Optional, Union
 import torch
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
-from ...image_processor import VaeImageProcessor
+from ....image_processor import VaeImageProcessor
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from ....schedulers import KarrasDiffusionSchedulers
-from ...schedulers import KarrasDiffusionSchedulers
+from ....utils import deprecate, is_torch_xla_available, logging
-from ...utils import deprecate, is_torch_xla_available, logging
+from ....utils.torch_utils import randn_tensor
-from ...utils.torch_utils import randn_tensor
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 from .pipeline_output import SemanticStableDiffusionPipelineOutput
 
 
@@ -143,7 +143,7 @@ class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
-    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
+    # Copied from diffusers.pipelines.deprecated.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,

src/diffusers/pipelines/deprecated/shap_e/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -17,7 +17,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -41,7 +41,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .camera import create_pan_cameras
         from .pipeline_shap_e import ShapEPipeline

src/diffusers/pipelines/deprecated/shap_e/pipeline_shap_e.py

@@ -21,16 +21,16 @@ import PIL.Image
 import torch
 from transformers import CLIPTextModelWithProjection, CLIPTokenizer
 
-from ...models import PriorTransformer
+from ....models import PriorTransformer
-from ...schedulers import HeunDiscreteScheduler
+from ....schedulers import HeunDiscreteScheduler
-from ...utils import (
+from ....utils import (
     BaseOutput,
     is_torch_xla_available,
     logging,
     replace_example_docstring,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline
+from ...pipeline_utils import DiffusionPipeline
 from .renderer import ShapERenderer
 
 
@@ -127,7 +127,7 @@ class ShapEPipeline(DiffusionPipeline):
             shap_e_renderer=shap_e_renderer,
         )
 
-    # Copied from diffusers.pipelines.unclip.pipeline_unclip.UnCLIPPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.unclip.pipeline_unclip.UnCLIPPipeline.prepare_latents
     def prepare_latents(self, shape, dtype, device, generator, latents, scheduler):
         if latents is None:
             latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)

src/diffusers/pipelines/deprecated/shap_e/pipeline_shap_e_img2img.py

@@ -20,16 +20,16 @@ import PIL.Image
 import torch
 from transformers import CLIPImageProcessor, CLIPVisionModel
 
-from ...models import PriorTransformer
+from ....models import PriorTransformer
-from ...schedulers import HeunDiscreteScheduler
+from ....schedulers import HeunDiscreteScheduler
-from ...utils import (
+from ....utils import (
     BaseOutput,
     is_torch_xla_available,
     logging,
     replace_example_docstring,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline
+from ...pipeline_utils import DiffusionPipeline
 from .renderer import ShapERenderer
 
 
@@ -128,7 +128,7 @@ class ShapEImg2ImgPipeline(DiffusionPipeline):
             shap_e_renderer=shap_e_renderer,
         )
 
-    # Copied from diffusers.pipelines.unclip.pipeline_unclip.UnCLIPPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.unclip.pipeline_unclip.UnCLIPPipeline.prepare_latents
     def prepare_latents(self, shape, dtype, device, generator, latents, scheduler):
         if latents is None:
             latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)

src/diffusers/pipelines/deprecated/shap_e/renderer.py

@@ -21,9 +21,9 @@ import torch
 import torch.nn.functional as F
 from torch import nn
 
-from ...configuration_utils import ConfigMixin, register_to_config
+from ....configuration_utils import ConfigMixin, register_to_config
-from ...models import ModelMixin
+from ....models import ModelMixin
-from ...utils import BaseOutput
+from ....utils import BaseOutput
 from .camera import create_pan_cameras
 
 

src/diffusers/pipelines/deprecated/stable_diffusion_attend_and_excite/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -18,7 +18,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -30,7 +30,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_stable_diffusion_attend_and_excite import StableDiffusionAttendAndExcitePipeline
 

src/diffusers/pipelines/deprecated/stable_diffusion_attend_and_excite/pipeline_stable_diffusion_attend_and_excite.py

@@ -21,13 +21,13 @@ import torch
 from torch.nn import functional as F
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
-from ...image_processor import VaeImageProcessor
+from ....image_processor import VaeImageProcessor
-from ...loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...models.attention_processor import Attention
+from ....models.attention_processor import Attention
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     deprecate,
     is_torch_xla_available,
@@ -36,10 +36,10 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion import StableDiffusionPipelineOutput
+from ...stable_diffusion import StableDiffusionPipelineOutput
-from ..stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from ...stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/stable_diffusion_diffedit/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -18,7 +18,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -30,7 +30,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_stable_diffusion_diffedit import StableDiffusionDiffEditPipeline
 

src/diffusers/pipelines/deprecated/stable_diffusion_diffedit/pipeline_stable_diffusion_diffedit.py

@@ -22,13 +22,13 @@ import torch
 from packaging import version
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
-from ...configuration_utils import FrozenDict
+from ....configuration_utils import FrozenDict
-from ...image_processor import VaeImageProcessor
+from ....image_processor import VaeImageProcessor
-from ...loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import DDIMInverseScheduler, KarrasDiffusionSchedulers
+from ....schedulers import DDIMInverseScheduler, KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     PIL_INTERPOLATION,
     USE_PEFT_BACKEND,
     BaseOutput,
@@ -39,10 +39,10 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion import StableDiffusionPipelineOutput
+from ...stable_diffusion import StableDiffusionPipelineOutput
-from ..stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from ...stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/stable_diffusion_gligen/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -18,7 +18,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -31,7 +31,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_stable_diffusion_gligen import StableDiffusionGLIGENPipeline
         from .pipeline_stable_diffusion_gligen_text_image import StableDiffusionGLIGENTextImagePipeline

src/diffusers/pipelines/deprecated/stable_diffusion_gligen/pipeline_stable_diffusion_gligen.py

@@ -20,13 +20,13 @@ import PIL.Image
 import torch
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
-from ...image_processor import VaeImageProcessor
+from ....image_processor import VaeImageProcessor
-from ...loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...models.attention import GatedSelfAttentionDense
+from ....models.attention import GatedSelfAttentionDense
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     deprecate,
     is_torch_xla_available,
@@ -35,10 +35,10 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion import StableDiffusionPipelineOutput
+from ...stable_diffusion import StableDiffusionPipelineOutput
-from ..stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from ...stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/stable_diffusion_gligen/pipeline_stable_diffusion_gligen_text_image.py

@@ -26,13 +26,13 @@ from transformers import (
     CLIPVisionModelWithProjection,
 )
 
-from ...image_processor import VaeImageProcessor
+from ....image_processor import VaeImageProcessor
-from ...loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...models.attention import GatedSelfAttentionDense
+from ....models.attention import GatedSelfAttentionDense
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     is_torch_xla_available,
     logging,
@@ -40,11 +40,11 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion import StableDiffusionPipelineOutput
+from ...stable_diffusion import StableDiffusionPipelineOutput
-from ..stable_diffusion.clip_image_project_model import CLIPImageProjection
+from ...stable_diffusion.clip_image_project_model import CLIPImageProjection
-from ..stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from ...stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/stable_diffusion_k_diffusion/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -25,7 +25,7 @@ try:
     ):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_and_k_diffusion_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_and_k_diffusion_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_and_k_diffusion_objects))
 else:
@@ -43,7 +43,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_and_k_diffusion_objects import *
+        from ....utils.dummy_torch_and_transformers_and_k_diffusion_objects import *
     else:
         from .pipeline_stable_diffusion_k_diffusion import StableDiffusionKDiffusionPipeline
         from .pipeline_stable_diffusion_xl_k_diffusion import StableDiffusionXLKDiffusionPipeline

src/diffusers/pipelines/deprecated/stable_diffusion_k_diffusion/pipeline_stable_diffusion_k_diffusion.py

@@ -26,24 +26,24 @@ from transformers import (
     CLIPTokenizerFast,
 )
 
-from ...image_processor import VaeImageProcessor
+from ....image_processor import VaeImageProcessor
-from ...loaders import (
+from ....loaders import (
     StableDiffusionLoraLoaderMixin,
     TextualInversionLoaderMixin,
 )
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers, LMSDiscreteScheduler
+from ....schedulers import KarrasDiffusionSchedulers, LMSDiscreteScheduler
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     deprecate,
     logging,
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion import StableDiffusionPipelineOutput, StableDiffusionSafetyChecker
+from ...stable_diffusion import StableDiffusionPipelineOutput, StableDiffusionSafetyChecker
 
 
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
@@ -122,6 +122,8 @@ class StableDiffusionKDiffusionPipeline(
     ):
         super().__init__()
 
+        logger.warning(f"{self.__class__.__name__} is deprecated and will no longer be actively maintained")
+
         logger.info(
             f"{self.__class__} is an experimntal pipeline and is likely to change in the future. We recommend to use"
             " this pipeline for fast experimentation / iteration if needed, but advice to rely on existing pipelines"

src/diffusers/pipelines/deprecated/stable_diffusion_k_diffusion/pipeline_stable_diffusion_xl_k_diffusion.py

@@ -25,31 +25,31 @@ from transformers import (
     CLIPTokenizer,
 )
 
-from ...image_processor import VaeImageProcessor
+from ....image_processor import VaeImageProcessor
-from ...loaders import (
+from ....loaders import (
     FromSingleFileMixin,
     IPAdapterMixin,
     StableDiffusionXLLoraLoaderMixin,
     TextualInversionLoaderMixin,
 )
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...models.attention_processor import (
+from ....models.attention_processor import (
     AttnProcessor2_0,
     FusedAttnProcessor2_0,
     XFormersAttnProcessor,
 )
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers, LMSDiscreteScheduler
+from ....schedulers import KarrasDiffusionSchedulers, LMSDiscreteScheduler
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     logging,
     replace_example_docstring,
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
+from ...stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
 
 
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
@@ -72,7 +72,7 @@ EXAMPLE_DOC_STRING = """
 """
 
 
-# Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.ModelWrapper
+# Copied from diffusers.pipelines.deprecated.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.ModelWrapper
 class ModelWrapper:
     def __init__(self, model, alphas_cumprod):
         self.model = model
@@ -158,6 +158,8 @@ class StableDiffusionXLKDiffusionPipeline(
     ):
         super().__init__()
 
+        logger.warning(f"{self.__class__.__name__} is deprecated and will no longer be actively maintained")
+
         # get correct sigmas from LMS
         scheduler = LMSDiscreteScheduler.from_config(scheduler.config)
         self.register_modules(
@@ -185,7 +187,7 @@ class StableDiffusionXLKDiffusionPipeline(
         else:
             self.k_diffusion_model = CompVisDenoiser(model)
 
-    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.set_scheduler
+    # Copied from diffusers.pipelines.deprecated.stable_diffusion_k_diffusion..pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.set_scheduler
     def set_scheduler(self, scheduler_type: str):
         library = importlib.import_module("k_diffusion")
         sampling = getattr(library, "sampling")

src/diffusers/pipelines/deprecated/stable_diffusion_ldm3d/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -18,7 +18,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -30,7 +30,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_stable_diffusion_ldm3d import StableDiffusionLDM3DPipeline
 

src/diffusers/pipelines/deprecated/stable_diffusion_ldm3d/pipeline_stable_diffusion_ldm3d.py

@@ -21,12 +21,17 @@ import PIL.Image
 import torch
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
 
-from ...image_processor import PipelineImageInput, VaeImageProcessorLDM3D
+from ....image_processor import PipelineImageInput, VaeImageProcessorLDM3D
-from ...loaders import FromSingleFileMixin, IPAdapterMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import (
-from ...models import AutoencoderKL, ImageProjection, UNet2DConditionModel
+    FromSingleFileMixin,
-from ...models.lora import adjust_lora_scale_text_encoder
+    IPAdapterMixin,
-from ...schedulers import KarrasDiffusionSchedulers
+    StableDiffusionLoraLoaderMixin,
-from ...utils import (
+    TextualInversionLoaderMixin,
+)
+from ....models import AutoencoderKL, ImageProjection, UNet2DConditionModel
+from ....models.lora import adjust_lora_scale_text_encoder
+from ....schedulers import KarrasDiffusionSchedulers
+from ....utils import (
     USE_PEFT_BACKEND,
     BaseOutput,
     deprecate,
@@ -36,9 +41,9 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from ...stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/stable_diffusion_panorama/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -18,7 +18,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -30,7 +30,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_stable_diffusion_panorama import StableDiffusionPanoramaPipeline
 

src/diffusers/pipelines/deprecated/stable_diffusion_panorama/pipeline_stable_diffusion_panorama.py

@@ -18,12 +18,12 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 import torch
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
 
-from ...image_processor import PipelineImageInput, VaeImageProcessor
+from ....image_processor import PipelineImageInput, VaeImageProcessor
-from ...loaders import IPAdapterMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import IPAdapterMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, ImageProjection, UNet2DConditionModel
+from ....models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import DDIMScheduler
+from ....schedulers import DDIMScheduler
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     deprecate,
     is_torch_xla_available,
@@ -32,10 +32,10 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion import StableDiffusionPipelineOutput
+from ...stable_diffusion import StableDiffusionPipelineOutput
-from ..stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from ...stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 
 
 if is_torch_xla_available():

src/diffusers/pipelines/deprecated/stable_diffusion_safe/__init__.py

@@ -6,7 +6,7 @@ import numpy as np
 import PIL
 from PIL import Image
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     BaseOutput,
     OptionalDependencyNotAvailable,
@@ -59,7 +59,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects
+    from ....utils import dummy_torch_and_transformers_objects
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -77,7 +77,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         if not (is_transformers_available() and is_torch_available()):
             raise OptionalDependencyNotAvailable()
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_output import StableDiffusionSafePipelineOutput
         from .pipeline_stable_diffusion_safe import StableDiffusionPipelineSafe

src/diffusers/pipelines/deprecated/stable_diffusion_safe/pipeline_output.py

@@ -4,7 +4,7 @@ from typing import List, Optional, Union
 import numpy as np
 import PIL.Image
 
-from ...utils import (
+from ....utils import (
     BaseOutput,
 )
 

src/diffusers/pipelines/deprecated/stable_diffusion_safe/pipeline_stable_diffusion_safe.py

@@ -7,14 +7,14 @@ import torch
 from packaging import version
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
 
-from ...configuration_utils import FrozenDict
+from ....configuration_utils import FrozenDict
-from ...image_processor import PipelineImageInput
+from ....image_processor import PipelineImageInput
-from ...loaders import IPAdapterMixin
+from ....loaders import IPAdapterMixin
-from ...models import AutoencoderKL, ImageProjection, UNet2DConditionModel
+from ....models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import deprecate, is_torch_xla_available, logging
+from ....utils import deprecate, is_torch_xla_available, logging
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from . import StableDiffusionSafePipelineOutput
 from .safety_checker import SafeStableDiffusionSafetyChecker
 
@@ -372,7 +372,7 @@ class StableDiffusionPipelineSafe(DiffusionPipeline, StableDiffusionMixin, IPAda
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
-    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
+    # Copied from diffusers.pipelines.deprecated.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,

src/diffusers/pipelines/deprecated/stable_diffusion_safe/safety_checker.py

@@ -16,7 +16,7 @@ import torch
 import torch.nn as nn
 from transformers import CLIPConfig, CLIPVisionModel, PreTrainedModel
 
-from ...utils import logging
+from ....utils import logging
 
 
 logger = logging.get_logger(__name__)

src/diffusers/pipelines/deprecated/stable_diffusion_sag/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -18,7 +18,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -30,7 +30,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             raise OptionalDependencyNotAvailable()
 
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *
+        from ....utils.dummy_torch_and_transformers_objects import *
     else:
         from .pipeline_stable_diffusion_sag import StableDiffusionSAGPipeline
 

src/diffusers/pipelines/deprecated/stable_diffusion_sag/pipeline_stable_diffusion_sag.py

@@ -19,12 +19,12 @@ import torch
 import torch.nn.functional as F
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
 
-from ...image_processor import PipelineImageInput, VaeImageProcessor
+from ....image_processor import PipelineImageInput, VaeImageProcessor
-from ...loaders import IPAdapterMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import IPAdapterMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, ImageProjection, UNet2DConditionModel
+from ....models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     deprecate,
     is_torch_xla_available,
@@ -33,10 +33,10 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion import StableDiffusionPipelineOutput
+from ...stable_diffusion import StableDiffusionPipelineOutput
-from ..stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from ...stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 
 
 if is_torch_xla_available():
@@ -490,7 +490,7 @@ class StableDiffusionSAGPipeline(DiffusionPipeline, StableDiffusionMixin, Textua
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
-    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
+    # Copied from diffusers.pipelines.deprecated.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,

src/diffusers/pipelines/deprecated/text_to_video_synthesis/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -17,7 +17,7 @@ try:
     if not (is_transformers_available() and is_torch_available()):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+    from ....utils import dummy_torch_and_transformers_objects  # noqa F403
 
     _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
 else:
@@ -33,7 +33,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         if not (is_transformers_available() and is_torch_available()):
             raise OptionalDependencyNotAvailable()
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *  # noqa F403
+        from ....utils.dummy_torch_and_transformers_objects import *  # noqa F403
     else:
         from .pipeline_output import TextToVideoSDPipelineOutput
         from .pipeline_text_to_video_synth import TextToVideoSDPipeline

src/diffusers/pipelines/deprecated/text_to_video_synthesis/pipeline_output.py

@@ -5,7 +5,7 @@ import numpy as np
 import PIL
 import torch
 
-from ...utils import (
+from ....utils import (
     BaseOutput,
 )
 

src/diffusers/pipelines/deprecated/text_to_video_synthesis/pipeline_text_to_video_synth.py

@@ -18,11 +18,11 @@ from typing import Any, Callable, Dict, List, Optional, Union
 import torch
 from transformers import CLIPTextModel, CLIPTokenizer
 
-from ...loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, UNet3DConditionModel
+from ....models import AutoencoderKL, UNet3DConditionModel
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     deprecate,
     is_torch_xla_available,
@@ -31,9 +31,9 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ...video_processor import VideoProcessor
+from ....video_processor import VideoProcessor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from . import TextToVideoSDPipelineOutput
 
 
@@ -363,7 +363,7 @@ class TextToVideoSDPipeline(
             extra_step_kwargs["generator"] = generator
         return extra_step_kwargs
 
-    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
+    # Copied from diffusers.pipelines.deprecated.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,

src/diffusers/pipelines/deprecated/text_to_video_synthesis/pipeline_text_to_video_synth_img2img.py

@@ -19,11 +19,11 @@ import numpy as np
 import torch
 from transformers import CLIPTextModel, CLIPTokenizer
 
-from ...loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, UNet3DConditionModel
+from ....models import AutoencoderKL, UNet3DConditionModel
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     deprecate,
     is_torch_xla_available,
@@ -32,9 +32,9 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ...video_processor import VideoProcessor
+from ....video_processor import VideoProcessor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from . import TextToVideoSDPipelineOutput
 
 
@@ -368,7 +368,7 @@ class VideoToVideoSDPipeline(
 
         return prompt_embeds, negative_prompt_embeds
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_synth.TextToVideoSDPipeline.decode_latents
     def decode_latents(self, latents):
         latents = 1 / self.vae.config.scaling_factor * latents
 

src/diffusers/pipelines/deprecated/text_to_video_synthesis/pipeline_text_to_video_zero.py

@@ -10,12 +10,12 @@ import torch.nn.functional as F
 from torch.nn.functional import grid_sample
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
-from ...image_processor import VaeImageProcessor
+from ....image_processor import VaeImageProcessor
-from ...loaders import FromSingleFileMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import FromSingleFileMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     BaseOutput,
     is_torch_xla_available,
@@ -23,9 +23,9 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
-from ..stable_diffusion import StableDiffusionSafetyChecker
+from ...stable_diffusion import StableDiffusionSafetyChecker
 
 
 if is_torch_xla_available():
@@ -464,7 +464,7 @@ class TextToVideoZeroPipeline(
 
         return latents.clone().detach()
 
-    # Copied from diffusers.pipelines.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
+    # Copied from diffusers.pipelines.deprecated.stable_diffusion_k_diffusion.pipeline_stable_diffusion_k_diffusion.StableDiffusionKDiffusionPipeline.check_inputs
     def check_inputs(
         self,
         prompt,

src/diffusers/pipelines/deprecated/text_to_video_synthesis/pipeline_text_to_video_zero_sdxl.py

@@ -16,17 +16,17 @@ from transformers import (
     CLIPVisionModelWithProjection,
 )
 
-from ...image_processor import VaeImageProcessor
+from ....image_processor import VaeImageProcessor
-from ...loaders import StableDiffusionXLLoraLoaderMixin, TextualInversionLoaderMixin
+from ....loaders import StableDiffusionXLLoraLoaderMixin, TextualInversionLoaderMixin
-from ...models import AutoencoderKL, UNet2DConditionModel
+from ....models import AutoencoderKL, UNet2DConditionModel
-from ...models.attention_processor import (
+from ....models.attention_processor import (
     AttnProcessor2_0,
     FusedAttnProcessor2_0,
     XFormersAttnProcessor,
 )
-from ...models.lora import adjust_lora_scale_text_encoder
+from ....models.lora import adjust_lora_scale_text_encoder
-from ...schedulers import KarrasDiffusionSchedulers
+from ....schedulers import KarrasDiffusionSchedulers
-from ...utils import (
+from ....utils import (
     USE_PEFT_BACKEND,
     BaseOutput,
     is_invisible_watermark_available,
@@ -34,15 +34,15 @@ from ...utils import (
     scale_lora_layers,
     unscale_lora_layers,
 )
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ...pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 
 
 if is_invisible_watermark_available():
-    from ..stable_diffusion_xl.watermark import StableDiffusionXLWatermarker
+    from ...stable_diffusion_xl.watermark import StableDiffusionXLWatermarker
 
 
-from ...utils import is_torch_xla_available
+from ....utils import is_torch_xla_available
 
 
 if is_torch_xla_available():
@@ -55,32 +55,32 @@ else:
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
 
-# Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.rearrange_0
+# Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.rearrange_0
 def rearrange_0(tensor, f):
     F, C, H, W = tensor.size()
     tensor = torch.permute(torch.reshape(tensor, (F // f, f, C, H, W)), (0, 2, 1, 3, 4))
     return tensor
 
 
-# Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.rearrange_1
+# Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.rearrange_1
 def rearrange_1(tensor):
     B, C, F, H, W = tensor.size()
     return torch.reshape(torch.permute(tensor, (0, 2, 1, 3, 4)), (B * F, C, H, W))
 
 
-# Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.rearrange_3
+# Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.rearrange_3
 def rearrange_3(tensor, f):
     F, D, C = tensor.size()
     return torch.reshape(tensor, (F // f, f, D, C))
 
 
-# Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.rearrange_4
+# Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.rearrange_4
 def rearrange_4(tensor):
     B, F, D, C = tensor.size()
     return torch.reshape(tensor, (B * F, D, C))
 
 
-# Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor
+# Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor
 class CrossFrameAttnProcessor:
     """
     Cross frame attention processor. Each frame attends the first frame.
@@ -140,7 +140,7 @@ class CrossFrameAttnProcessor:
         return hidden_states
 
 
-# Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor2_0
+# Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.CrossFrameAttnProcessor2_0
 class CrossFrameAttnProcessor2_0:
     """
     Cross frame attention processor with scaled_dot_product attention of Pytorch 2.0.
@@ -230,7 +230,7 @@ class TextToVideoSDXLPipelineOutput(BaseOutput):
     images: Union[List[PIL.Image.Image], np.ndarray]
 
 
-# Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.coords_grid
+# Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.coords_grid
 def coords_grid(batch, ht, wd, device):
     # Adapted from https://github.com/princeton-vl/RAFT/blob/master/core/utils/utils.py
     coords = torch.meshgrid(torch.arange(ht, device=device), torch.arange(wd, device=device))
@@ -238,7 +238,7 @@ def coords_grid(batch, ht, wd, device):
     return coords[None].repeat(batch, 1, 1, 1)
 
 
-# Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.warp_single_latent
+# Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.warp_single_latent
 def warp_single_latent(latent, reference_flow):
     """
     Warp latent of a single frame with given flow
@@ -266,7 +266,7 @@ def warp_single_latent(latent, reference_flow):
     return warped
 
 
-# Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.create_motion_field
+# Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.create_motion_field
 def create_motion_field(motion_field_strength_x, motion_field_strength_y, frame_ids, device, dtype):
     """
     Create translation motion field
@@ -290,7 +290,7 @@ def create_motion_field(motion_field_strength_x, motion_field_strength_y, frame_
     return reference_flow
 
 
-# Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.create_motion_field_and_warp_latents
+# Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.create_motion_field_and_warp_latents
 def create_motion_field_and_warp_latents(motion_field_strength_x, motion_field_strength_y, frame_ids, latents):
     """
     Creates translation motion and warps the latents accordingly
@@ -832,7 +832,7 @@ class TextToVideoZeroSDXLPipeline(
 
         return prompt_embeds, negative_prompt_embeds, pooled_prompt_embeds, negative_pooled_prompt_embeds
 
-    # Copied from diffusers.pipelines.text_to_video_synthesis.pipeline_text_to_video_zero.TextToVideoZeroPipeline.forward_loop
+    # Copied from diffusers.pipelines.deprecated.text_to_video_synthesis.pipeline_text_to_video_zero.TextToVideoZeroPipeline.forward_loop
     def forward_loop(self, x_t0, t0, t1, generator):
         """
         Perform DDPM forward process from time t0 to t1. This is the same as adding noise with corresponding variance.

src/diffusers/pipelines/deprecated/unclip/__init__.py

@@ -1,6 +1,6 @@
 from typing import TYPE_CHECKING
 
-from ...utils import (
+from ....utils import (
     DIFFUSERS_SLOW_IMPORT,
     OptionalDependencyNotAvailable,
     _LazyModule,
@@ -17,7 +17,7 @@ try:
     if not (is_transformers_available() and is_torch_available() and is_transformers_version(">=", "4.25.0")):
         raise OptionalDependencyNotAvailable()
 except OptionalDependencyNotAvailable:
-    from ...utils.dummy_torch_and_transformers_objects import UnCLIPImageVariationPipeline, UnCLIPPipeline
+    from ....utils.dummy_torch_and_transformers_objects import UnCLIPImageVariationPipeline, UnCLIPPipeline
 
     _dummy_objects.update(
         {"UnCLIPImageVariationPipeline": UnCLIPImageVariationPipeline, "UnCLIPPipeline": UnCLIPPipeline}
@@ -33,7 +33,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         if not (is_transformers_available() and is_torch_available() and is_transformers_version(">=", "4.25.0")):
             raise OptionalDependencyNotAvailable()
     except OptionalDependencyNotAvailable:
-        from ...utils.dummy_torch_and_transformers_objects import *  # noqa F403
+        from ....utils.dummy_torch_and_transformers_objects import *  # noqa F403
     else:
         from .pipeline_unclip import UnCLIPPipeline
         from .pipeline_unclip_image_variation import UnCLIPImageVariationPipeline

src/diffusers/pipelines/deprecated/unclip/pipeline_unclip.py

@@ -20,11 +20,11 @@ from torch.nn import functional as F
 from transformers import CLIPTextModelWithProjection, CLIPTokenizer
 from transformers.models.clip.modeling_clip import CLIPTextModelOutput
 
-from ...models import PriorTransformer, UNet2DConditionModel, UNet2DModel
+from ....models import PriorTransformer, UNet2DConditionModel, UNet2DModel
-from ...schedulers import UnCLIPScheduler
+from ....schedulers import UnCLIPScheduler
-from ...utils import is_torch_xla_available, logging
+from ....utils import is_torch_xla_available, logging
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from ...pipeline_utils import DiffusionPipeline, ImagePipelineOutput
 from .text_proj import UnCLIPTextProjModel
 
 

src/diffusers/pipelines/deprecated/unclip/pipeline_unclip_image_variation.py

@@ -25,11 +25,11 @@ from transformers import (
     CLIPVisionModelWithProjection,
 )
 
-from ...models import UNet2DConditionModel, UNet2DModel
+from ....models import UNet2DConditionModel, UNet2DModel
-from ...schedulers import UnCLIPScheduler
+from ....schedulers import UnCLIPScheduler
-from ...utils import is_torch_xla_available, logging
+from ....utils import is_torch_xla_available, logging
-from ...utils.torch_utils import randn_tensor
+from ....utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from ...pipeline_utils import DiffusionPipeline, ImagePipelineOutput
 from .text_proj import UnCLIPTextProjModel
 
 
@@ -114,7 +114,7 @@ class UnCLIPImageVariationPipeline(DiffusionPipeline):
             super_res_scheduler=super_res_scheduler,
         )
 
-    # Copied from diffusers.pipelines.unclip.pipeline_unclip.UnCLIPPipeline.prepare_latents
+    # Copied from diffusers.pipelines.deprecated.unclip.pipeline_unclip.UnCLIPPipeline.prepare_latents
     def prepare_latents(self, shape, dtype, device, generator, latents, scheduler):
         if latents is None:
             latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)