another fix

pipeline.py

@@ -1022,8 +1022,8 @@ class StableDiffusionControlNetImg2ImgPipeline(DiffusionPipeline, TextualInversi
                         down_block_res_samples.append(down_block_res_sample)
                         mid_block_res_samples.append(mid_block_res_sample)
 
-                    down_block_res_samples = torch.cat([x.unsqueeze(0) for x in down_block_res_samples], dim=0)
-                    mid_block_res_sample = torch.cat([x.unsqueeze(0) for x in mid_block_res_samples], dim=0)
+                    down_block_res_samples = torch.cat([torch.tensor(x).unsqueeze(0) for x in down_block_res_samples], dim=0)
+                    mid_block_res_sample = torch.cat([torch.tensor(x).unsqueeze(0) for x in mid_block_res_samples], dim=0)
 
                     # down_block_res_samples = torch.cat(down_block_res_samples, dim=0)
                     # mid_block_res_sample = torch.cat(mid_block_res_samples, dim=0)