diff --git a/src/diffusers/pipelines/omnigen/pipeline_omnigen.py b/src/diffusers/pipelines/omnigen/pipeline_omnigen.py
index f6906074b3..1254b6725f 100644
--- a/src/diffusers/pipelines/omnigen/pipeline_omnigen.py
+++ b/src/diffusers/pipelines/omnigen/pipeline_omnigen.py
@@ -23,12 +23,14 @@ from ...image_processor import PipelineImageInput, VaeImageProcessor
 from ...models.autoencoders import AutoencoderKL
 from ...models.transformers import OmniGenTransformer2DModel
 from ...schedulers import FlowMatchEulerDiscreteScheduler
-from ...utils import is_torch_xla_available, logging, replace_example_docstring
+from ...utils import is_torch_xla_available, is_torchvision_available, logging, replace_example_docstring
 from ...utils.torch_utils import randn_tensor
 from ..pipeline_utils import DiffusionPipeline, ImagePipelineOutput
-from .processor_omnigen import OmniGenMultiModalProcessor
 
 
+if is_torchvision_available():
+    from .processor_omnigen import OmniGenMultiModalProcessor
+
 if is_torch_xla_available():
     XLA_AVAILABLE = True
 else:
diff --git a/src/diffusers/pipelines/omnigen/processor_omnigen.py b/src/diffusers/pipelines/omnigen/processor_omnigen.py
index be5ff82c4a..7ed11871bb 100644
--- a/src/diffusers/pipelines/omnigen/processor_omnigen.py
+++ b/src/diffusers/pipelines/omnigen/processor_omnigen.py
@@ -18,7 +18,12 @@ from typing import Dict, List
 import numpy as np
 import torch
 from PIL import Image
-from torchvision import transforms
+
+from ...utils import is_torchvision_available
+
+
+if is_torchvision_available():
+    from torchvision import transforms
 
 
 def crop_image(pil_image, max_image_size):