[Community Pipelines] add textual inversion support for stable_diffus…

…ion_ipex (huggingface#5571)

examples/community/stable_diffusion_ipex.py

@@ -21,6 +21,7 @@
 from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
 
 from diffusers.configuration_utils import FrozenDict
+from diffusers.loaders import TextualInversionLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.pipeline_utils import DiffusionPipeline
 from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput
@@ -61,7 +62,7 @@
 """
 
 
-class StableDiffusionIPEXPipeline(DiffusionPipeline):
+class StableDiffusionIPEXPipeline(DiffusionPipeline, TextualInversionLoaderMixin):
     r"""
     Pipeline for text-to-image generation using Stable Diffusion on IPEX.
 
@@ -454,6 +455,10 @@ def _encode_prompt(
             batch_size = prompt_embeds.shape[0]
 
         if prompt_embeds is None:
+            # textual inversion: procecss multi-vector tokens if necessary
+            if isinstance(self, TextualInversionLoaderMixin):
+                prompt = self.maybe_convert_prompt(prompt, self.tokenizer)
+
             text_inputs = self.tokenizer(
                 prompt,
                 padding="max_length",
@@ -514,6 +519,10 @@ def _encode_prompt(
             else:
                 uncond_tokens = negative_prompt
 
+            # textual inversion: procecss multi-vector tokens if necessary
+            if isinstance(self, TextualInversionLoaderMixin):
+                uncond_tokens = self.maybe_convert_prompt(uncond_tokens, self.tokenizer)
+
             max_length = prompt_embeds.shape[1]
             uncond_input = self.tokenizer(
                 uncond_tokens,