From a628f166ddd7fb4cd5146d0136ef23d52edc533a Mon Sep 17 00:00:00 2001
From: Thushit Kumar R <101030274+Senume@users.noreply.github.com>
Date: Tue, 5 Dec 2023 14:28:29 +0530
Subject: [PATCH] Update scheduling_euler_discrete.py

Type Error fix. During the type conversion, it expects for NumPy array, which fails when tensor array is passed. Sol: Check the type before conversion.
---
 src/diffusers/schedulers/scheduling_euler_discrete.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/src/diffusers/schedulers/scheduling_euler_discrete.py b/src/diffusers/schedulers/scheduling_euler_discrete.py
index 53dc2ae15432..4e1b75845715 100644
--- a/src/diffusers/schedulers/scheduling_euler_discrete.py
+++ b/src/diffusers/schedulers/scheduling_euler_discrete.py
@@ -280,7 +280,12 @@ def set_timesteps(self, num_inference_steps: int, device: Union[str, torch.devic
             sigmas = self._convert_to_karras(in_sigmas=sigmas, num_inference_steps=self.num_inference_steps)
             timesteps = np.array([self._sigma_to_t(sigma, log_sigmas) for sigma in sigmas])
 
-        sigmas = torch.from_numpy(sigmas).to(dtype=torch.float32, device=device)
+        # Checking 'sigmas' type before datatype conversion
+        if isinstance(sigmas, np.ndarray)
+            sigmas = torch.from_numpy(sigmas).to(dtype=torch.float32, device=device)
+        else:
+            sigmas = sigmas.to(dtype=torch.float32, device=device)
+    
 
         # TODO: Support the full EDM scalings for all prediction types and timestep types
         if self.config.timestep_type == "continuous" and self.config.prediction_type == "v_prediction":