Add LoraLoaderMixin and update prepare_image_latents

Author: clarencechen

src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_diffedit.py

@@ -1,4 +1,4 @@
-# Copyright 2023 The HuggingFace Team. All rights reserved.
+# Copyright 2023 DiffEdit Authors and Pix2Pix Zero Authors and 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.
@@ -23,7 +23,7 @@
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from ...configuration_utils import FrozenDict
-from ...loaders import TextualInversionLoaderMixin
+from ...loaders import LoraLoaderMixin, TextualInversionLoaderMixin
 from ...models import AutoencoderKL, UNet2DConditionModel
 from ...schedulers import DDIMInverseScheduler, KarrasDiffusionSchedulers
 from ...utils import (
@@ -230,13 +230,20 @@ def preprocess_mask(mask, batch_size: int = 1):
     return mask
 
 
-class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderMixin):
+class StableDiffusionDiffEditPipeline(DiffusionPipeline, TextualInversionLoaderMixin, LoraLoaderMixin):
     r"""
     Pipeline for text-guided image inpainting using Stable Diffusion using DiffEdit. *This is an experimental feature*.
 
     This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the
     library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
 
+    In addition the pipeline inherits the following loading methods:
+        - *Textual-Inversion*: [`loaders.TextualInversionLoaderMixin.load_textual_inversion`]
+        - *LoRA*: [`loaders.LoraLoaderMixin.load_lora_weights`]
+
+    as well as the following saving methods:
+        - *LoRA*: [`loaders.LoraLoaderMixin.save_lora_weights`]
+
     Args:
         vae ([`AutoencoderKL`]):
             Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
@@ -771,6 +778,7 @@ def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype
         latents = latents * self.scheduler.init_noise_sigma
         return latents
 
+    # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_pix2pix_zero.StableDiffusionPix2PixZeroPipeline.prepare_image_latents
     def prepare_image_latents(self, image, batch_size, dtype, device, generator=None):
         if not isinstance(image, (torch.Tensor, PIL.Image.Image, list)):
             raise ValueError(