successsfully load paired self-attention number of the processor : 36 /content/StoryDiffusion-hf/examples/taylor/1.jpeg start_merge_step:10 ['a woman img, wearing a white T-shirt, blue loose hair,wake up in the bed', 'a woman img, wearing a white T-shirt, blue loose hair,have breakfast', 'a woman img, wearing a white T-shirt, blue loose hair,is on the road, go to company', 'a woman img, wearing a white T-shirt, blue loose hair,work in the company', 'a woman img, wearing a white T-shirt, blue loose hair,Take a walk next to the company at noon', 'a woman img, wearing a white T-shirt, blue loose hair,lying in bed at night'] anime artwork illustrating a woman, wearing a white t - shirt, blue loose hair, wake up in the bed. created by japanese anime studio. highly emotional. best quality, high resolution anime artwork illustrating a woman, wearing a white t - shirt, blue loose hair, have breakfast. created by japanese anime studio. highly emotional. best quality, high resolution anime artwork illustrating a woman, wearing a white t - shirt, blue loose hair, is on the road, go to company. created by japanese anime studio. highly emotional. best quality, high resolution torch.Size([3, 77, 2048]) torch.Size([3, 77, 2048]) torch.Size([3, 77, 2048]) torch.Size([3, 1280]) torch.Size([3, 1280]) torch.Size([3, 1280]) torch.Size([3, 4, 96, 96]) torch.Size([6, 6]) 0%| | 0/50 [00:00, , , ]] -2 [[, , , ], [, ]] [[, , , ], [, , , ]] 0 (214, 718) 0 (201, 717) 0 (1, 717) Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device. It is not recommended to move them to `cpu` as running them will fail. Please make sure to use an accelerator to run the pipeline in inference, due to the lack of support for`float16` operations on this device in PyTorch. Please, remove the `torch_dtype=torch.float16` argument, or use another device for inference. Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device. It is not recommended to move them to `cpu` as running them will fail. Please make sure to use an accelerator to run the pipeline in inference, due to the lack of support for`float16` operations on this device in PyTorch. Please, remove the `torch_dtype=torch.float16` argument, or use another device for inference. Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device. It is not recommended to move them to `cpu` as running them will fail. Please make sure to use an accelerator to run the pipeline in inference, due to the lack of support for`float16` operations on this device in PyTorch. Please, remove the `torch_dtype=torch.float16` argument, or use another device for inference. successsfully load paired self-attention number of the processor : 36