[LoRA] get rid of the legacy lora remnants and make our codebase lighter (#8623)

* get rid of the legacy lora remnants and make our codebase lighter

* fix depcrecated lora argument

* fix

* empty commit to trigger ci

* remove print

* empty

Author: sayakpaul

docs/source/en/api/attnprocessor.md

@@ -41,12 +41,6 @@ An attention processor is a class for applying different types of attention mech
 ## FusedAttnProcessor2_0
 [[autodoc]] models.attention_processor.FusedAttnProcessor2_0
 
-## LoRAAttnAddedKVProcessor
-[[autodoc]] models.attention_processor.LoRAAttnAddedKVProcessor
-
-## LoRAXFormersAttnProcessor
-[[autodoc]] models.attention_processor.LoRAXFormersAttnProcessor
-
 ## SlicedAttnProcessor
 [[autodoc]] models.attention_processor.SlicedAttnProcessor
 

examples/community/lpw_stable_diffusion_xl.py

@@ -24,12 +24,7 @@
 from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
 from diffusers.loaders import FromSingleFileMixin, IPAdapterMixin, LoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
-    XFormersAttnProcessor,
-)
+from diffusers.models.attention_processor import AttnProcessor2_0, XFormersAttnProcessor
 from diffusers.pipelines.pipeline_utils import StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion_xl.pipeline_output import StableDiffusionXLPipelineOutput
 from diffusers.schedulers import KarrasDiffusionSchedulers
@@ -1292,12 +1287,7 @@ def upcast_vae(self):
         self.vae.to(dtype=torch.float32)
         use_torch_2_0_or_xformers = isinstance(
             self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
-            ),
+            (AttnProcessor2_0, XFormersAttnProcessor),
         )
         # if xformers or torch_2_0 is used attention block does not need
         # to be in float32 which can save lots of memory

examples/community/pipeline_demofusion_sdxl.py

@@ -16,12 +16,7 @@
     TextualInversionLoaderMixin,
 )
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
-    XFormersAttnProcessor,
-)
+from diffusers.models.attention_processor import AttnProcessor2_0, XFormersAttnProcessor
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
 from diffusers.schedulers import KarrasDiffusionSchedulers
@@ -612,12 +607,7 @@ def upcast_vae(self):
         self.vae.to(dtype=torch.float32)
         use_torch_2_0_or_xformers = isinstance(
             self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
-            ),
+            (AttnProcessor2_0, XFormersAttnProcessor),
         )
         # if xformers or torch_2_0 is used attention block does not need
         # to be in float32 which can save lots of memory

examples/community/pipeline_sdxl_style_aligned.py

@@ -46,8 +46,6 @@
     Attention,
     AttnProcessor2_0,
     FusedAttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
     XFormersAttnProcessor,
 )
 from diffusers.models.lora import adjust_lora_scale_text_encoder
@@ -1153,8 +1151,6 @@ def upcast_vae(self):
             (
                 AttnProcessor2_0,
                 XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
                 FusedAttnProcessor2_0,
             ),
         )

examples/community/pipeline_stable_diffusion_xl_controlnet_adapter.py

@@ -25,12 +25,7 @@
 from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
 from diffusers.loaders import FromSingleFileMixin, StableDiffusionXLLoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, ControlNetModel, MultiAdapter, T2IAdapter, UNet2DConditionModel
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
-    XFormersAttnProcessor,
-)
+from diffusers.models.attention_processor import AttnProcessor2_0, XFormersAttnProcessor
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.controlnet.multicontrolnet import MultiControlNetModel
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
@@ -797,12 +792,7 @@ def upcast_vae(self):
         self.vae.to(dtype=torch.float32)
         use_torch_2_0_or_xformers = isinstance(
             self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
-            ),
+            (AttnProcessor2_0, XFormersAttnProcessor),
         )
         # if xformers or torch_2_0 is used attention block does not need
         # to be in float32 which can save lots of memory

examples/community/pipeline_stable_diffusion_xl_controlnet_adapter_inpaint.py

@@ -44,12 +44,7 @@
     T2IAdapter,
     UNet2DConditionModel,
 )
-from diffusers.models.attention_processor import (
-    AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
-    XFormersAttnProcessor,
-)
+from diffusers.models.attention_processor import AttnProcessor2_0, XFormersAttnProcessor
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.controlnet.multicontrolnet import MultiControlNetModel
 from diffusers.pipelines.pipeline_utils import StableDiffusionMixin
@@ -1135,12 +1130,7 @@ def upcast_vae(self):
         self.vae.to(dtype=torch.float32)
         use_torch_2_0_or_xformers = isinstance(
             self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
-            ),
+            (AttnProcessor2_0, XFormersAttnProcessor),
         )
         # if xformers or torch_2_0 is used attention block does not need
         # to be in float32 which can save lots of memory

examples/community/pipeline_stable_diffusion_xl_differential_img2img.py

@@ -37,8 +37,6 @@
 from diffusers.models import AutoencoderKL, ImageProjection, UNet2DConditionModel
 from diffusers.models.attention_processor import (
     AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
     XFormersAttnProcessor,
 )
 from diffusers.models.lora import adjust_lora_scale_text_encoder
@@ -854,8 +852,6 @@ def upcast_vae(self):
             (
                 AttnProcessor2_0,
                 XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
             ),
         )
         # if xformers or torch_2_0 is used attention block does not need

examples/community/pipeline_stable_diffusion_xl_ipex.py

@@ -34,8 +34,6 @@
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.attention_processor import (
     AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
     XFormersAttnProcessor,
 )
 from diffusers.models.lora import adjust_lora_scale_text_encoder
@@ -662,8 +660,6 @@ def upcast_vae(self):
             (
                 AttnProcessor2_0,
                 XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
             ),
         )
         # if xformers or torch_2_0 is used attention block does not need