diff --git a/examples/community/stable_diffusion_controlnet_img2img.py b/examples/community/stable_diffusion_controlnet_img2img.py
index a8a51b5489a3..d4fe81f3d4ee 100644
--- a/examples/community/stable_diffusion_controlnet_img2img.py
+++ b/examples/community/stable_diffusion_controlnet_img2img.py
@@ -8,6 +8,8 @@
 import torch
 from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
+from diffusers.loaders import FromCkptMixin, LoraLoaderMixin, TextualInversionLoaderMixin
+
 from diffusers import AutoencoderKL, ControlNetModel, DiffusionPipeline, UNet2DConditionModel, logging
 from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput, StableDiffusionSafetyChecker
 from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_controlnet import MultiControlNetModel
@@ -130,7 +132,7 @@ def prepare_controlnet_conditioning_image(
     return controlnet_conditioning_image
 
 
-class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline):
+class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, TextualInversionLoaderMixin):
     """
     Inspired by: https://github.com/haofanwang/ControlNet-for-Diffusers/
     """
@@ -307,6 +309,10 @@ 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",
@@ -367,6 +373,10 @@ 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,