[SVD] Return np.ndarray when output_type="np" (#6507)

[SVD] Fix output_type="np"

src/diffusers/pipelines/stable_video_diffusion/pipeline_stable_video_diffusion.py

@@ -52,6 +52,9 @@ def tensor2vid(video: torch.Tensor, processor, output_type="np"):
 
         outputs.append(batch_output)
 
+    if output_type == "np":
+        return np.stack(outputs)
+
     return outputs
 
 

tests/pipelines/stable_video_diffusion/test_stable_video_diffusion.py

@@ -185,6 +185,23 @@ class StableVideoDiffusionPipelineFastTests(PipelineTesterMixin, unittest.TestCa
     def test_inference_batch_consistent(self):
         pass
 
+    def test_np_output_type(self):
+        components = self.get_dummy_components()
+        pipe = self.pipeline_class(**components)
+        for component in pipe.components.values():
+            if hasattr(component, "set_default_attn_processor"):
+                component.set_default_attn_processor()
+
+        pipe.to(torch_device)
+        pipe.set_progress_bar_config(disable=None)
+
+        generator_device = "cpu"
+        inputs = self.get_dummy_inputs(generator_device)
+        inputs["output_type"] = "np"
+        output = pipe(**inputs).frames
+        self.assertTrue(isinstance(output, np.ndarray))
+        self.assertEqual(len(output.shape), 5)
+
     def test_dict_tuple_outputs_equivalent(self, expected_max_difference=1e-4):
         components = self.get_dummy_components()
         pipe = self.pipeline_class(**components)