Revert "[LoRA] introduce LoraBaseMixin to promote reusability." (#8976)

Revert "[LoRA] introduce LoraBaseMixin to promote reusability. (#8774)"

This reverts commit 527430d0.

docs/source/en/api/loaders/lora.md

@@ -12,13 +12,10 @@ specific language governing permissions and limitations under the License.
 
 # LoRA
 
-LoRA is a fast and lightweight training method that inserts and trains a significantly smaller number of parameters instead of all the model parameters. This produces a smaller file (~100 MBs) and makes it easier to quickly train a model to learn a new concept. LoRA weights are typically loaded into the denoiser, text encoder or both. The denoiser usually corresponds to a UNet ([`UNet2DConditionModel`], for example) or a Transformer ([`SD3Transformer2DModel`], for example). There are several classes for loading LoRA weights:
+LoRA is a fast and lightweight training method that inserts and trains a significantly smaller number of parameters instead of all the model parameters. This produces a smaller file (~100 MBs) and makes it easier to quickly train a model to learn a new concept. LoRA weights are typically loaded into the UNet, text encoder or both. There are two classes for loading LoRA weights:
 
-- [`StableDiffusionLoraLoaderMixin`] provides functions for loading and unloading, fusing and unfusing, enabling and disabling, and more functions for managing LoRA weights. This class can be used with any model.
-- [`StableDiffusionXLLoraLoaderMixin`] is a [Stable Diffusion (SDXL)](../../api/pipelines/stable_diffusion/stable_diffusion_xl) version of the [`StableDiffusionLoraLoaderMixin`] class for loading and saving LoRA weights. It can only be used with the SDXL model.
-- [`SD3LoraLoaderMixin`] provides similar functions for [Stable Diffusion 3](https://huggingface.co/blog/sd3).
-- [`AmusedLoraLoaderMixin`] is for the [`AmusedPipeline`].
-- [`LoraBaseMixin`] provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.
+- [`LoraLoaderMixin`] provides functions for loading and unloading, fusing and unfusing, enabling and disabling, and more functions for managing LoRA weights. This class can be used with any model.
+- [`StableDiffusionXLLoraLoaderMixin`] is a [Stable Diffusion (SDXL)](../../api/pipelines/stable_diffusion/stable_diffusion_xl) version of the [`LoraLoaderMixin`] class for loading and saving LoRA weights. It can only be used with the SDXL model.
 
 <Tip>
 
@@ -26,22 +23,10 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
 
 </Tip>
 
-## StableDiffusionLoraLoaderMixin
+## LoraLoaderMixin
 
-[[autodoc]] loaders.lora_pipeline.StableDiffusionLoraLoaderMixin
+[[autodoc]] loaders.lora.LoraLoaderMixin
 
 ## StableDiffusionXLLoraLoaderMixin
 
-[[autodoc]] loaders.lora_pipeline.StableDiffusionXLLoraLoaderMixin
-
-## SD3LoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.SD3LoraLoaderMixin
-
-## AmusedLoraLoaderMixin
-
-[[autodoc]] loaders.lora_pipeline.AmusedLoraLoaderMixin
-
-## LoraBaseMixin
-
-[[autodoc]] loaders.lora_base.LoraBaseMixin
\ No newline at end of file
+[[autodoc]] loaders.lora.StableDiffusionXLLoraLoaderMixin
\ No newline at end of file

docs/source/en/api/loaders/peft.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # PEFT
 
-Diffusers supports loading adapters such as [LoRA](../../using-diffusers/loading_adapters) with the [PEFT](https://huggingface.co/docs/peft/index) library with the [`~loaders.peft.PeftAdapterMixin`] class. This allows modeling classes in Diffusers like [`UNet2DConditionModel`], [`SD3Transformer2DModel`] to operate with an adapter.
+Diffusers supports loading adapters such as [LoRA](../../using-diffusers/loading_adapters) with the [PEFT](https://huggingface.co/docs/peft/index) library with the [`~loaders.peft.PeftAdapterMixin`] class. This allows modeling classes in Diffusers like [`UNet2DConditionModel`] to load an adapter.
 
 <Tip>
 

docs/source/en/api/loaders/unet.md

@@ -12,7 +12,7 @@ specific language governing permissions and limitations under the License.
 
 # UNet
 
-Some training methods - like LoRA and Custom Diffusion - typically target the UNet's attention layers, but these training methods can also target other non-attention layers. Instead of training all of a model's parameters, only a subset of the parameters are trained, which is faster and more efficient. This class is useful if you're *only* loading weights into a UNet. If you need to load weights into the text encoder or a text encoder and UNet, try using the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] function instead.
+Some training methods - like LoRA and Custom Diffusion - typically target the UNet's attention layers, but these training methods can also target other non-attention layers. Instead of training all of a model's parameters, only a subset of the parameters are trained, which is faster and more efficient. This class is useful if you're *only* loading weights into a UNet. If you need to load weights into the text encoder or a text encoder and UNet, try using the [`~loaders.LoraLoaderMixin.load_lora_weights`] function instead.
 
 The [`UNet2DConditionLoadersMixin`] class provides functions for loading and saving weights, fusing and unfusing LoRAs, disabling and enabling LoRAs, and setting and deleting adapters.
 

docs/source/en/tutorials/using_peft_for_inference.md

@@ -191,7 +191,7 @@ image
 
 ## Manage active adapters
 
-You have attached multiple adapters in this tutorial, and if you're feeling a bit lost on what adapters have been attached to the pipeline's components, use the [`~diffusers.loaders.StableDiffusionLoraLoaderMixin.get_active_adapters`] method to check the list of active adapters:
+You have attached multiple adapters in this tutorial, and if you're feeling a bit lost on what adapters have been attached to the pipeline's components, use the [`~diffusers.loaders.LoraLoaderMixin.get_active_adapters`] method to check the list of active adapters:
 
 ```py
 active_adapters = pipe.get_active_adapters()
@@ -199,7 +199,7 @@ active_adapters
 ["toy", "pixel"]
 ```
 
-You can also get the active adapters of each pipeline component with [`~diffusers.loaders.StableDiffusionLoraLoaderMixin.get_list_adapters`]:
+You can also get the active adapters of each pipeline component with [`~diffusers.loaders.LoraLoaderMixin.get_list_adapters`]:
 
 ```py
 list_adapters_component_wise = pipe.get_list_adapters()

docs/source/en/using-diffusers/inference_with_lcm.md

@@ -64,7 +64,7 @@ image
 </hfoption>
 <hfoption id="LCM-LoRA">
 
-To use LCM-LoRAs, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt to generate an image in just 4 steps.
+To use LCM-LoRAs, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt to generate an image in just 4 steps.
 
 A couple of notes to keep in mind when using LCM-LoRAs are:
 
@@ -156,7 +156,7 @@ image
 </hfoption>
 <hfoption id="LCM-LoRA">
 
-To use LCM-LoRAs for image-to-image, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt and initial image to generate an image in just 4 steps.
+To use LCM-LoRAs for image-to-image, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt and initial image to generate an image in just 4 steps.
 
 > [!TIP]
 > Experiment with different values for `num_inference_steps`, `strength`, and `guidance_scale` to get the best results.
@@ -207,7 +207,7 @@ image
 
 ## Inpainting
 
-To use LCM-LoRAs for inpainting, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt, initial image, and mask image to generate an image in just 4 steps.
+To use LCM-LoRAs for inpainting, you need to replace the scheduler with the [`LCMScheduler`] and load the LCM-LoRA weights with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. Then you can use the pipeline as usual, and pass a text prompt, initial image, and mask image to generate an image in just 4 steps.
 
 ```py
 import torch
@@ -262,7 +262,7 @@ LCMs are compatible with adapters like LoRA, ControlNet, T2I-Adapter, and Animat
 <hfoptions id="lcm-lora">
 <hfoption id="LCM">
 
-Load the LCM checkpoint for your supported model into [`UNet2DConditionModel`] and replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LoRA weights into the LCM and generate a styled image in a few steps.
+Load the LCM checkpoint for your supported model into [`UNet2DConditionModel`] and replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LoRA weights into the LCM and generate a styled image in a few steps.
 
 ```python
 from diffusers import StableDiffusionXLPipeline, UNet2DConditionModel, LCMScheduler
@@ -294,7 +294,7 @@ image
 </hfoption>
 <hfoption id="LCM-LoRA">
 
-Replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights and the style LoRA you want to use. Combine both LoRA adapters with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method and generate a styled image in a few steps.
+Replace the scheduler with the [`LCMScheduler`]. Then you can use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights and the style LoRA you want to use. Combine both LoRA adapters with the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] method and generate a styled image in a few steps.
 
 ```py
 import torch
@@ -389,7 +389,7 @@ make_image_grid([canny_image, image], rows=1, cols=2)
 </hfoption>
 <hfoption id="LCM-LoRA">
 
-Load a ControlNet model trained on canny images and pass it to the [`ControlNetModel`]. Then you can load a Stable Diffusion v1.5 model into [`StableDiffusionControlNetPipeline`] and replace the scheduler with the [`LCMScheduler`]. Use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights, and pass the canny image to the pipeline and generate an image.
+Load a ControlNet model trained on canny images and pass it to the [`ControlNetModel`]. Then you can load a Stable Diffusion v1.5 model into [`StableDiffusionControlNetPipeline`] and replace the scheduler with the [`LCMScheduler`]. Use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights, and pass the canny image to the pipeline and generate an image.
 
 > [!TIP]
 > Experiment with different values for `num_inference_steps`, `controlnet_conditioning_scale`, `cross_attention_kwargs`, and `guidance_scale` to get the best results.
@@ -525,7 +525,7 @@ image = pipe(
 </hfoption>
 <hfoption id="LCM-LoRA">
 
-Load a T2IAdapter trained on canny images and pass it to the [`StableDiffusionXLAdapterPipeline`]. Replace the scheduler with the [`LCMScheduler`], and use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights. Pass the canny image to the pipeline and generate an image.
+Load a T2IAdapter trained on canny images and pass it to the [`StableDiffusionXLAdapterPipeline`]. Replace the scheduler with the [`LCMScheduler`], and use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the LCM-LoRA weights. Pass the canny image to the pipeline and generate an image.
 
 ```py
 import torch

docs/source/en/using-diffusers/loading_adapters.md

@@ -116,7 +116,7 @@ import torch
 pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda")
 ```
 
-Then use the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method to load the [ostris/super-cereal-sdxl-lora](https://huggingface.co/ostris/super-cereal-sdxl-lora) weights and specify the weights filename from the repository:
+Then use the [`~loaders.LoraLoaderMixin.load_lora_weights`] method to load the [ostris/super-cereal-sdxl-lora](https://huggingface.co/ostris/super-cereal-sdxl-lora) weights and specify the weights filename from the repository:
 
 ```py
 pipeline.load_lora_weights("ostris/super-cereal-sdxl-lora", weight_name="cereal_box_sdxl_v1.safetensors")
@@ -129,7 +129,7 @@ image
     <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_lora.png" />
 </div>
 
-The [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method loads LoRA weights into both the UNet and text encoder. It is the preferred way for loading LoRAs because it can handle cases where:
+The [`~loaders.LoraLoaderMixin.load_lora_weights`] method loads LoRA weights into both the UNet and text encoder. It is the preferred way for loading LoRAs because it can handle cases where:
 
 - the LoRA weights don't have separate identifiers for the UNet and text encoder
 - the LoRA weights have separate identifiers for the UNet and text encoder
@@ -153,7 +153,7 @@ image
     <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_attn_proc.png" />
 </div>
 
-To unload the LoRA weights, use the [`~loaders.StableDiffusionLoraLoaderMixin.unload_lora_weights`] method to discard the LoRA weights and restore the model to its original weights:
+To unload the LoRA weights, use the [`~loaders.LoraLoaderMixin.unload_lora_weights`] method to discard the LoRA weights and restore the model to its original weights:
 
 ```py
 pipeline.unload_lora_weights()
@@ -161,9 +161,9 @@ pipeline.unload_lora_weights()
 
 ### Adjust LoRA weight scale
 
-For both [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] and [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`], you can pass the `cross_attention_kwargs={"scale": 0.5}` parameter to adjust how much of the LoRA weights to use. A value of `0` is the same as only using the base model weights, and a value of `1` is equivalent to using the fully finetuned LoRA.
+For both [`~loaders.LoraLoaderMixin.load_lora_weights`] and [`~loaders.UNet2DConditionLoadersMixin.load_attn_procs`], you can pass the `cross_attention_kwargs={"scale": 0.5}` parameter to adjust how much of the LoRA weights to use. A value of `0` is the same as only using the base model weights, and a value of `1` is equivalent to using the fully finetuned LoRA.
 
-For more granular control on the amount of LoRA weights used per layer, you can use [`~loaders.StableDiffusionLoraLoaderMixin.set_adapters`] and pass a dictionary specifying by how much to scale the weights in each layer by.
+For more granular control on the amount of LoRA weights used per layer, you can use [`~loaders.LoraLoaderMixin.set_adapters`] and pass a dictionary specifying by how much to scale the weights in each layer by.
 ```python
 pipe = ... # create pipeline
 pipe.load_lora_weights(..., adapter_name="my_adapter")
@@ -186,7 +186,7 @@ This also works with multiple adapters - see [this guide](https://huggingface.co
 
 <Tip warning={true}>
 
-Currently, [`~loaders.StableDiffusionLoraLoaderMixin.set_adapters`] only supports scaling attention weights. If a LoRA has other parts (e.g., resnets or down-/upsamplers), they will keep a scale of 1.0.
+Currently, [`~loaders.LoraLoaderMixin.set_adapters`] only supports scaling attention weights. If a LoRA has other parts (e.g., resnets or down-/upsamplers), they will keep a scale of 1.0.
 
 </Tip>
 
@@ -203,7 +203,7 @@ To load a Kohya LoRA, let's download the [Blueprintify SD XL 1.0](https://civita
 !wget https://civitai.com/api/download/models/168776 -O blueprintify-sd-xl-10.safetensors
 ```
 
-Load the LoRA checkpoint with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method, and specify the filename in the `weight_name` parameter:
+Load the LoRA checkpoint with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method, and specify the filename in the `weight_name` parameter:
 
 ```py
 from diffusers import AutoPipelineForText2Image
@@ -227,7 +227,7 @@ image
 Some limitations of using Kohya LoRAs with 🤗 Diffusers include:
 
 - Images may not look like those generated by UIs - like ComfyUI - for multiple reasons, which are explained [here](https://github.com/huggingface/diffusers/pull/4287/#issuecomment-1655110736).
-- [LyCORIS checkpoints](https://github.com/KohakuBlueleaf/LyCORIS) aren't fully supported. The [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method loads LyCORIS checkpoints with LoRA and LoCon modules, but Hada and LoKR are not supported.
+- [LyCORIS checkpoints](https://github.com/KohakuBlueleaf/LyCORIS) aren't fully supported. The [`~loaders.LoraLoaderMixin.load_lora_weights`] method loads LyCORIS checkpoints with LoRA and LoCon modules, but Hada and LoKR are not supported.
 
 </Tip>
 

docs/source/en/using-diffusers/merge_loras.md

@@ -14,9 +14,9 @@ specific language governing permissions and limitations under the License.
 
 It can be fun and creative to use multiple [LoRAs]((https://huggingface.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora)) together to generate something entirely new and unique. This works by merging multiple LoRA weights together to produce images that are a blend of different styles. Diffusers provides a few methods to merge LoRAs depending on *how* you want to merge their weights, which can affect image quality.
 
-This guide will show you how to merge LoRAs using the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods. To improve inference speed and reduce memory-usage of merged LoRAs, you'll also see how to use the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method to fuse the LoRA weights with the original weights of the underlying model.
+This guide will show you how to merge LoRAs using the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods. To improve inference speed and reduce memory-usage of merged LoRAs, you'll also see how to use the [`~loaders.LoraLoaderMixin.fuse_lora`] method to fuse the LoRA weights with the original weights of the underlying model.
 
-For this guide, load a Stable Diffusion XL (SDXL) checkpoint and the [KappaNeuro/studio-ghibli-style]() and [Norod78/sdxl-chalkboarddrawing-lora]() LoRAs with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method. You'll need to assign each LoRA an `adapter_name` to combine them later.
+For this guide, load a Stable Diffusion XL (SDXL) checkpoint and the [KappaNeuro/studio-ghibli-style]() and [Norod78/sdxl-chalkboarddrawing-lora]() LoRAs with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method. You'll need to assign each LoRA an `adapter_name` to combine them later.
 
 ```py
 from diffusers import DiffusionPipeline
@@ -182,9 +182,9 @@ image
 
 ## fuse_lora
 
-Both the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods require loading the base model and the LoRA adapters separately which incurs some overhead. The [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method allows you to fuse the LoRA weights directly with the original weights of the underlying model. This way, you're only loading the model once which can increase inference and lower memory-usage.
+Both the [`~loaders.UNet2DConditionLoadersMixin.set_adapters`] and [`~peft.LoraModel.add_weighted_adapter`] methods require loading the base model and the LoRA adapters separately which incurs some overhead. The [`~loaders.LoraLoaderMixin.fuse_lora`] method allows you to fuse the LoRA weights directly with the original weights of the underlying model. This way, you're only loading the model once which can increase inference and lower memory-usage.
 
-You can use PEFT to easily fuse/unfuse multiple adapters directly into the model weights (both UNet and text encoder) using the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method, which can lead to a speed-up in inference and lower VRAM usage.
+You can use PEFT to easily fuse/unfuse multiple adapters directly into the model weights (both UNet and text encoder) using the [`~loaders.LoraLoaderMixin.fuse_lora`] method, which can lead to a speed-up in inference and lower VRAM usage.
 
 For example, if you have a base model and adapters loaded and set as active with the following adapter weights:
 
@@ -199,13 +199,13 @@ pipeline.load_lora_weights("lordjia/by-feng-zikai", weight_name="fengzikai_v1.0_
 pipeline.set_adapters(["ikea", "feng"], adapter_weights=[0.7, 0.8])
 ```
 
-Fuse these LoRAs into the UNet with the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method. The `lora_scale` parameter controls how much to scale the output by with the LoRA weights. It is important to make the `lora_scale` adjustments in the [`~loaders.StableDiffusionLoraLoaderMixin.fuse_lora`] method because it won’t work if you try to pass `scale` to the `cross_attention_kwargs` in the pipeline.
+Fuse these LoRAs into the UNet with the [`~loaders.LoraLoaderMixin.fuse_lora`] method. The `lora_scale` parameter controls how much to scale the output by with the LoRA weights. It is important to make the `lora_scale` adjustments in the [`~loaders.LoraLoaderMixin.fuse_lora`] method because it won’t work if you try to pass `scale` to the `cross_attention_kwargs` in the pipeline.
 
 ```py
 pipeline.fuse_lora(adapter_names=["ikea", "feng"], lora_scale=1.0)
 ```
 
-Then you should use [`~loaders.StableDiffusionLoraLoaderMixin.unload_lora_weights`] to unload the LoRA weights since they've already been fused with the underlying base model. Finally, call [`~DiffusionPipeline.save_pretrained`] to save the fused pipeline locally or you could call [`~DiffusionPipeline.push_to_hub`] to push the fused pipeline to the Hub.
+Then you should use [`~loaders.LoraLoaderMixin.unload_lora_weights`] to unload the LoRA weights since they've already been fused with the underlying base model. Finally, call [`~DiffusionPipeline.save_pretrained`] to save the fused pipeline locally or you could call [`~DiffusionPipeline.push_to_hub`] to push the fused pipeline to the Hub.
 
 ```py
 pipeline.unload_lora_weights()
@@ -226,7 +226,7 @@ image = pipeline("A bowl of ramen shaped like a cute kawaii bear, by Feng Zikai"
 image
 ```
 
-You can call [`~loaders.StableDiffusionLoraLoaderMixin.unfuse_lora`] to restore the original model's weights (for example, if you want to use a different `lora_scale` value). However, this only works if you've only fused one LoRA adapter to the original model. If you've fused multiple LoRAs, you'll need to reload the model.
+You can call [`~loaders.LoraLoaderMixin.unfuse_lora`] to restore the original model's weights (for example, if you want to use a different `lora_scale` value). However, this only works if you've only fused one LoRA adapter to the original model. If you've fused multiple LoRAs, you'll need to reload the model.
 
 ```py
 pipeline.unfuse_lora()

docs/source/en/using-diffusers/other-formats.md

@@ -74,7 +74,7 @@ pipeline = StableDiffusionPipeline.from_single_file(
 
 [LoRA](https://hf.co/docs/peft/conceptual_guides/adapter#low-rank-adaptation-lora) is a lightweight adapter that is fast and easy to train, making them especially popular for generating images in a certain way or style. These adapters are commonly stored in a safetensors file, and are widely popular on model sharing platforms like [civitai](https://civitai.com/).
 
-LoRAs are loaded into a base model with the [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] method.
+LoRAs are loaded into a base model with the [`~loaders.LoraLoaderMixin.load_lora_weights`] method.
 
 ```py
 from diffusers import StableDiffusionXLPipeline

docs/source/ko/using-diffusers/other-formats.md

@@ -127,7 +127,7 @@ image = pipeline(prompt, num_inference_steps=50).images[0]
 
 [Automatic1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui) (A1111)은 Stable Diffusion을 위해 널리 사용되는 웹 UI로, [Civitai](https://civitai.com/) 와 같은 모델 공유 플랫폼을 지원합니다. 특히 LoRA 기법으로 학습된 모델은 학습 속도가 빠르고 완전히 파인튜닝된 모델보다 파일 크기가 훨씬 작기 때문에 인기가 높습니다.
 
-🤗 Diffusers는 [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`]:를 사용하여 A1111 LoRA 체크포인트 불러오기를 지원합니다:
+🤗 Diffusers는 [`~loaders.LoraLoaderMixin.load_lora_weights`]:를 사용하여 A1111 LoRA 체크포인트 불러오기를 지원합니다:
 
 ```py
 from diffusers import DiffusionPipeline, UniPCMultistepScheduler

examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py

@@ -57,7 +57,7 @@ from diffusers import (
     StableDiffusionPipeline,
     UNet2DConditionModel,
 )
-from diffusers.loaders import StableDiffusionLoraLoaderMixin
+from diffusers.loaders import LoraLoaderMixin
 from diffusers.optimization import get_scheduler
 from diffusers.training_utils import compute_snr
 from diffusers.utils import (
@@ -1318,11 +1318,11 @@ def main(args):
             else:
                 raise ValueError(f"unexpected save model: {model.__class__}")
 
-        lora_state_dict, network_alphas = StableDiffusionLoraLoaderMixin.lora_state_dict(input_dir)
-        StableDiffusionLoraLoaderMixin.load_lora_into_unet(lora_state_dict, network_alphas=network_alphas, unet=unet_)
+        lora_state_dict, network_alphas = LoraLoaderMixin.lora_state_dict(input_dir)
+        LoraLoaderMixin.load_lora_into_unet(lora_state_dict, network_alphas=network_alphas, unet=unet_)
 
         text_encoder_state_dict = {k: v for k, v in lora_state_dict.items() if "text_encoder." in k}
-        StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder(
+        LoraLoaderMixin.load_lora_into_text_encoder(
             text_encoder_state_dict, network_alphas=network_alphas, text_encoder=text_encoder_one_
         )
 

examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py

@@ -60,7 +60,7 @@ from diffusers import (
     StableDiffusionXLPipeline,
     UNet2DConditionModel,
 )
-from diffusers.loaders import StableDiffusionLoraLoaderMixin
+from diffusers.loaders import LoraLoaderMixin
 from diffusers.optimization import get_scheduler
 from diffusers.training_utils import _set_state_dict_into_text_encoder, cast_training_params, compute_snr
 from diffusers.utils import (
@@ -1646,7 +1646,7 @@ def main(args):
             else:
                 raise ValueError(f"unexpected save model: {model.__class__}")
 
-        lora_state_dict, network_alphas = StableDiffusionLoraLoaderMixin.lora_state_dict(input_dir)
+        lora_state_dict, network_alphas = LoraLoaderMixin.lora_state_dict(input_dir)
 
         unet_state_dict = {f'{k.replace("unet.", "")}': v for k, v in lora_state_dict.items() if k.startswith("unet.")}
         unet_state_dict = convert_unet_state_dict_to_peft(unet_state_dict)

examples/amused/train_amused.py

@@ -41,7 +41,7 @@ from transformers import (
 
 import diffusers.optimization
 from diffusers import AmusedPipeline, AmusedScheduler, EMAModel, UVit2DModel, VQModel
-from diffusers.loaders import AmusedLoraLoaderMixin
+from diffusers.loaders import LoraLoaderMixin
 from diffusers.utils import is_wandb_available
 
 
@@ -532,7 +532,7 @@ def main(args):
                 weights.pop()
 
             if transformer_lora_layers_to_save is not None or text_encoder_lora_layers_to_save is not None:
-                AmusedLoraLoaderMixin.save_lora_weights(
+                LoraLoaderMixin.save_lora_weights(
                     output_dir,
                     transformer_lora_layers=transformer_lora_layers_to_save,
                     text_encoder_lora_layers=text_encoder_lora_layers_to_save,
@@ -566,11 +566,11 @@ def main(args):
                 raise ValueError(f"unexpected save model: {model.__class__}")
 
         if transformer is not None or text_encoder_ is not None:
-            lora_state_dict, network_alphas = AmusedLoraLoaderMixin.lora_state_dict(input_dir)
-            AmusedLoraLoaderMixin.load_lora_into_text_encoder(
+            lora_state_dict, network_alphas = LoraLoaderMixin.lora_state_dict(input_dir)
+            LoraLoaderMixin.load_lora_into_text_encoder(
                 lora_state_dict, network_alphas=network_alphas, text_encoder=text_encoder_
             )
-            AmusedLoraLoaderMixin.load_lora_into_transformer(
+            LoraLoaderMixin.load_lora_into_transformer(
                 lora_state_dict, network_alphas=network_alphas, transformer=transformer
             )
 

examples/community/fresco_v2v.py

@@ -26,7 +26,7 @@ from gmflow.gmflow import GMFlow
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPVisionModelWithProjection
 
 from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
-from diffusers.loaders import StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import LoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, ControlNetModel, ImageProjection, UNet2DConditionModel
 from diffusers.models.attention_processor import AttnProcessor2_0
 from diffusers.models.lora import adjust_lora_scale_text_encoder
@@ -1252,8 +1252,8 @@ class FrescoV2VPipeline(StableDiffusionControlNetImg2ImgPipeline):
 
     The pipeline also inherits the following loading methods:
         - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
+        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
+        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
         - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
 
@@ -1456,7 +1456,7 @@ class FrescoV2VPipeline(StableDiffusionControlNetImg2ImgPipeline):
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale
@@ -1588,7 +1588,7 @@ class FrescoV2VPipeline(StableDiffusionControlNetImg2ImgPipeline):
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
             negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
 
-        if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
+        if isinstance(self, LoraLoaderMixin) and USE_PEFT_BACKEND:
             # Retrieve the original scale by scaling back the LoRA layers
             unscale_lora_layers(self.text_encoder, lora_scale)
 

examples/community/gluegen.py

@@ -7,7 +7,7 @@ from transformers import AutoModel, AutoTokenizer, CLIPImageProcessor
 
 from diffusers import DiffusionPipeline
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import StableDiffusionLoraLoaderMixin
+from diffusers.loaders import LoraLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import StableDiffusionMixin
@@ -194,7 +194,7 @@ def retrieve_timesteps(
     return timesteps, num_inference_steps
 
 
-class GlueGenStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin, StableDiffusionLoraLoaderMixin):
+class GlueGenStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin, LoraLoaderMixin):
     def __init__(
         self,
         vae: AutoencoderKL,
@@ -290,7 +290,7 @@ class GlueGenStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin, St
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale
@@ -424,7 +424,7 @@ class GlueGenStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin, St
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
             negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
 
-        if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
+        if isinstance(self, LoraLoaderMixin) and USE_PEFT_BACKEND:
             # Retrieve the original scale by scaling back the LoRA layers
             unscale_lora_layers(self.text_encoder, lora_scale)
 

examples/community/instaflow_one_step.py

@@ -21,7 +21,7 @@ from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers.configuration_utils import FrozenDict
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
@@ -53,11 +53,7 @@ def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
 
 
 class InstaFlowPipeline(
-    DiffusionPipeline,
-    StableDiffusionMixin,
-    TextualInversionLoaderMixin,
-    StableDiffusionLoraLoaderMixin,
-    FromSingleFileMixin,
+    DiffusionPipeline, StableDiffusionMixin, TextualInversionLoaderMixin, LoraLoaderMixin, FromSingleFileMixin
 ):
     r"""
     Pipeline for text-to-image generation using Rectified Flow and Euler discretization.
@@ -68,8 +64,8 @@ class InstaFlowPipeline(
 
     The pipeline also inherits the following loading methods:
         - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
+        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
+        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
 
     Args:
@@ -255,7 +251,7 @@ class InstaFlowPipeline(
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale

examples/community/ip_adapter_face_id.py

@@ -24,12 +24,7 @@ from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPV
 
 from diffusers.configuration_utils import FrozenDict
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import (
-    FromSingleFileMixin,
-    IPAdapterMixin,
-    StableDiffusionLoraLoaderMixin,
-    TextualInversionLoaderMixin,
-)
+from diffusers.loaders import FromSingleFileMixin, IPAdapterMixin, LoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.attention_processor import (
     AttnProcessor,
@@ -135,7 +130,7 @@ class IPAdapterFaceIDStableDiffusionPipeline(
     DiffusionPipeline,
     StableDiffusionMixin,
     TextualInversionLoaderMixin,
-    StableDiffusionLoraLoaderMixin,
+    LoraLoaderMixin,
     IPAdapterMixin,
     FromSingleFileMixin,
 ):
@@ -147,8 +142,8 @@ class IPAdapterFaceIDStableDiffusionPipeline(
 
     The pipeline also inherits the following loading methods:
         - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
+        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
+        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
         - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
 
@@ -523,7 +518,7 @@ class IPAdapterFaceIDStableDiffusionPipeline(
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale
@@ -655,7 +650,7 @@ class IPAdapterFaceIDStableDiffusionPipeline(
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
             negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
 
-        if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
+        if isinstance(self, LoraLoaderMixin) and USE_PEFT_BACKEND:
             # Retrieve the original scale by scaling back the LoRA layers
             unscale_lora_layers(self.text_encoder, lora_scale)
 

examples/community/kohya_hires_fix.py

@@ -395,8 +395,8 @@ class StableDiffusionHighResFixPipeline(StableDiffusionPipeline):
 
     The pipeline also inherits the following loading methods:
         - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
+        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
+        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
         - [`~loaders.IPAdapterMixin.load_ip_adapter`] for loading IP Adapters
 

examples/community/latent_consistency_interpolate.py

@@ -6,7 +6,7 @@ import torch
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.lora import adjust_lora_scale_text_encoder
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline, StableDiffusionMixin
@@ -190,11 +190,7 @@ def slerp(
 
 
 class LatentConsistencyModelWalkPipeline(
-    DiffusionPipeline,
-    StableDiffusionMixin,
-    TextualInversionLoaderMixin,
-    StableDiffusionLoraLoaderMixin,
-    FromSingleFileMixin,
+    DiffusionPipeline, StableDiffusionMixin, TextualInversionLoaderMixin, LoraLoaderMixin, FromSingleFileMixin
 ):
     r"""
     Pipeline for text-to-image generation using a latent consistency model.
@@ -204,8 +200,8 @@ class LatentConsistencyModelWalkPipeline(
 
     The pipeline also inherits the following loading methods:
         - [`~loaders.TextualInversionLoaderMixin.load_textual_inversion`] for loading textual inversion embeddings
-        - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
-        - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
+        - [`~loaders.LoraLoaderMixin.load_lora_weights`] for loading LoRA weights
+        - [`~loaders.LoraLoaderMixin.save_lora_weights`] for saving LoRA weights
         - [`~loaders.FromSingleFileMixin.from_single_file`] for loading `.ckpt` files
 
     Args:
@@ -321,7 +317,7 @@ class LatentConsistencyModelWalkPipeline(
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale
@@ -453,7 +449,7 @@ class LatentConsistencyModelWalkPipeline(
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
             negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
 
-        if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
+        if isinstance(self, LoraLoaderMixin) and USE_PEFT_BACKEND:
             # Retrieve the original scale by scaling back the LoRA layers
             unscale_lora_layers(self.text_encoder, lora_scale)
 

examples/community/llm_grounded_diffusion.py

@@ -29,12 +29,7 @@ from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer, CLIPV
 
 from diffusers.configuration_utils import FrozenDict
 from diffusers.image_processor import PipelineImageInput, VaeImageProcessor
-from diffusers.loaders import (
-    FromSingleFileMixin,
-    IPAdapterMixin,
-    StableDiffusionLoraLoaderMixin,
-    TextualInversionLoaderMixin,
-)
+from diffusers.loaders import FromSingleFileMixin, IPAdapterMixin, LoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.attention import Attention, GatedSelfAttentionDense
 from diffusers.models.attention_processor import AttnProcessor2_0
@@ -276,7 +271,7 @@ class LLMGroundedDiffusionPipeline(
     DiffusionPipeline,
     StableDiffusionMixin,
     TextualInversionLoaderMixin,
-    StableDiffusionLoraLoaderMixin,
+    LoraLoaderMixin,
     IPAdapterMixin,
     FromSingleFileMixin,
 ):
@@ -1268,7 +1263,7 @@ class LLMGroundedDiffusionPipeline(
         """
         # set lora scale so that monkey patched LoRA
         # function of text encoder can correctly access it
-        if lora_scale is not None and isinstance(self, StableDiffusionLoraLoaderMixin):
+        if lora_scale is not None and isinstance(self, LoraLoaderMixin):
             self._lora_scale = lora_scale
 
             # dynamically adjust the LoRA scale
@@ -1402,7 +1397,7 @@ class LLMGroundedDiffusionPipeline(
             negative_prompt_embeds = negative_prompt_embeds.repeat(1, num_images_per_prompt, 1)
             negative_prompt_embeds = negative_prompt_embeds.view(batch_size * num_images_per_prompt, seq_len, -1)
 
-        if isinstance(self, StableDiffusionLoraLoaderMixin) and USE_PEFT_BACKEND:
+        if isinstance(self, LoraLoaderMixin) and USE_PEFT_BACKEND:
             # Retrieve the original scale by scaling back the LoRA layers
             unscale_lora_layers(self.text_encoder, lora_scale)
 

examples/community/lpw_stable_diffusion.py

@@ -11,7 +11,7 @@ from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 from diffusers import DiffusionPipeline
 from diffusers.configuration_utils import FrozenDict
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.pipelines.pipeline_utils import StableDiffusionMixin
 from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput, StableDiffusionSafetyChecker
@@ -409,11 +409,7 @@ def preprocess_mask(mask, batch_size, scale_factor=8):
 
 
 class StableDiffusionLongPromptWeightingPipeline(
-    DiffusionPipeline,
-    StableDiffusionMixin,
-    TextualInversionLoaderMixin,
-    StableDiffusionLoraLoaderMixin,
-    FromSingleFileMixin,
+    DiffusionPipeline, StableDiffusionMixin, TextualInversionLoaderMixin, LoraLoaderMixin, FromSingleFileMixin
 ):
     r"""
     Pipeline for text-to-image generation using Stable Diffusion without tokens length limit, and support parsing