[Bugfix][cherry-pick]: /images/edits endpoint fails pipeline data format check (#1173)

Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>

vllm_omni/diffusion/models/longcat_image/pipeline_longcat_image_edit.py

@@ -72,11 +72,15 @@ def get_longcat_image_edit_pre_process_func(
             if "additional_information" not in prompt:
                 prompt["additional_information"] = {}
 
-            if raw_image is None or isinstance(raw_image, list):
-                raise ValueError(
-                    """Received no image or a list of image. Only a single image is supported by this model."""
-                    """Please correctly set `"multi_modal_data": {"image": <an image object or file path>, …}`"""
-                )
+            if not raw_image:  # None or empty list
+                raise ValueError("""Received no input image. This model requires one input image to run.""")
+            elif isinstance(raw_image, list):
+                if len(raw_image) > 1:
+                    raise ValueError(
+                        """Received multiple input images. Only a single image is supported by this model."""
+                    )
+                else:
+                    raw_image = raw_image[0]
 
             if isinstance(raw_image, str):
                 image = PIL.Image.open(raw_image)

vllm_omni/diffusion/models/qwen_image/pipeline_qwen_image_edit.py

@@ -75,11 +75,15 @@ def get_qwen_image_edit_pre_process_func(
                 prompt["additional_information"] = {}
 
             # Only handles single image
-            if raw_image is None or isinstance(raw_image, list):
-                raise ValueError(
-                    """Received no image or a list of image. Only a single image is supported by this model."""
-                    """Please correctly set `"multi_modal_data": {"image": <an image object or file path>, …}`"""
-                )
+            if not raw_image:  # None or empty list
+                raise ValueError("""Received no input image. This model requires one input image to run.""")
+            elif isinstance(raw_image, list):
+                if len(raw_image) > 1:
+                    raise ValueError(
+                        """Received multiple input images. Only a single image is supported by this model."""
+                    )
+                else:
+                    raw_image = raw_image[0]
 
             if isinstance(raw_image, str):
                 image = PIL.Image.open(raw_image)

vllm_omni/diffusion/models/qwen_image/pipeline_qwen_image_layered.py

@@ -79,11 +79,15 @@ def get_qwen_image_layered_pre_process_func(
             if "additional_information" not in prompt:
                 prompt["additional_information"] = {}
 
-            if raw_image is None or isinstance(raw_image, list):
-                raise ValueError(
-                    """Received no image or a list of image. Only a single image is supported by this model."""
-                    """Please correctly set `"multi_modal_data": {"image": <an image object or file path>, …}`"""
-                )
+            if not raw_image:  # None or empty list
+                raise ValueError("""Received no input image. This model requires one input image to run.""")
+            elif isinstance(raw_image, list):
+                if len(raw_image) > 1:
+                    raise ValueError(
+                        """Received multiple input images. Only a single image is supported by this model."""
+                    )
+                else:
+                    raw_image = raw_image[0]
 
             if isinstance(raw_image, str):
                 image = PIL.Image.open(raw_image)