@@ -13,7 +13,7 @@
 # limitations under the License.
 
 import html
-from typing import Callable, Dict, List, Optional, Union, Tuple
+from typing import Callable, Dict, List, Optional, Union
 
 import numpy as np
 import regex as re
 
@@ -13,7 +13,7 @@
 # limitations under the License.
 
 import html
-from typing import Callable, Dict, List, Optional, Union, Tuple
+from typing import Callable, Dict, List, Optional, Union
 
 import numpy as np
 import regex as re
 
@@ -192,12 +192,10 @@ def test_inference(self):
 
         self.assertEqual(image.shape, (1, 3, 64, 64))
 
-
     @unittest.skip("TODO: Test does not work")
     def test_encode_prompt_works_in_isolation(self):
         pass
 
-
     @unittest.skip("TODO: revisit, Batch isnot yet supported in this pipeline")
     def test_num_images_per_prompt(self):
         pass
 
@@ -119,7 +119,6 @@ def get_dummy_components(self):
         text_encoder = Qwen2_5_VLForConditionalGeneration(qwen_config)
         tokenizer = AutoProcessor.from_pretrained("hf-internal-testing/tiny-random-Qwen2VLForConditionalGeneration")
 
-
         clip_hidden_size = 16
         torch.manual_seed(0)
         clip_config = CLIPTextConfig(
@@ -199,7 +198,6 @@ def test_inference(self):
         # 17 frames, RGB, 32×32
         self.assertEqual(video.shape, (17, 3, 32, 32))
 
-
     @unittest.skip("TODO:Test does not work")
     def test_encode_prompt_works_in_isolation(self):
         pass
 
@@ -185,7 +185,7 @@ def test_inference(self):
         output = pipe(**inputs)
         image = output.image
 
-        self.assertEqual(image.shape, (1, 3, 16,16))
+        self.assertEqual(image.shape, (1, 3, 16, 16))
 
     def test_inference_batch_single_identical(self):
         super().test_inference_batch_single_identical(expected_max_diff=5e-3)