Inpaint Anything - ERROR - The size of tensor a (0) must match the size of tensor b (256) at non-singleton dimension 1

[waldolin]

2024-03-28` 00:23:32,966 - Inpaint Anything - ERROR - The size of tensor a (0) must match the size of tensor b (256) at non-singleton dimension 1
2024-03-28 00:24:20,692 - Inpaint Anything - INFO - input_image: (819, 1024, 3) uint8
2024-03-28 00:24:23,079 - Inpaint Anything - INFO - SamAutomaticMaskGenerator sam_vit_l_0b3195.pth
Traceback (most recent call last):
File "C:\Users\lin\stable-diffusion-webui-directml\extensions\sd-webui-inpaint-anything\scripts\inpaint_anything.py", line 187, in run_sam
sam_masks = inpalib.generate_sam_masks(input_image, sam_model_id, anime_style_chk)
File "C:\Users\lin\stable-diffusion-webui-directml\extensions\sd-webui-inpaint-anything\inpalib\samlib.py", line 139, in generate_sam_masks
sam_masks = sam_mask_generator.generate(input_image)
File "C:\Users\lin\stable-diffusion-webui-directml\venv\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "C:\Users\lin\stable-diffusion-webui-directml\extensions\sd-webui-inpaint-anything\segment_anything_fb\automatic_mask_generator.py", line 151, in generate
mask_data = self._generate_masks(image)
File "C:\Users\lin\stable-diffusion-webui-directml\extensions\sd-webui-inpaint-anything\segment_anything_fb\automatic_mask_generator.py", line 194, in _generate_masks
crop_data = self._process_crop(image, crop_box, layer_idx, orig_size)
File "C:\Users\lin\stable-diffusion-webui-directml\extensions\sd-webui-inpaint-anything\segment_anything_fb\automatic_mask_generator.py", line 240, in _process_crop
batch_data = self._process_batch(points, cropped_im_size, crop_box, orig_size)
File "C:\Users\lin\stable-diffusion-webui-directml\extensions\sd-webui-inpaint-anything\segment_anything_fb\automatic_mask_generator.py", line 283, in _process_batch
masks, iou_preds, _ = self.predictor.predict_torch(
File "C:\Users\lin\stable-diffusion-webui-directml\venv\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "C:\Users\lin\stable-diffusion-webui-directml\extensions\sd-webui-inpaint-anything\segment_anything_fb\predictor.py", line 222, in predict_torch
sparse_embeddings, dense_embeddings = self.model.prompt_encoder(
File "C:\Users\lin\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Users\lin\stable-diffusion-webui-directml\extensions\sd-webui-inpaint-anything\segment_anything_fb\modeling\prompt_encoder.py", line 155, in forward
point_embeddings = self._embed_points(coords, labels, pad=(boxes is None))
File "C:\Users\lin\stable-diffusion-webui-directml\extensions\sd-webui-inpaint-anything\segment_anything_fb\modeling\prompt_encoder.py", line 89, in _embed_points
point_embedding[labels == 0] += self.point_embeddings[0].weight
RuntimeError: The size of tensor a (0) must match the size of tensor b (256) at non-singleton dimension 1

2024-03-28 00:24:34,510 - Inpaint Anything - ERROR - The size of tensor a (0) must match the size of tensor b (256) at non-singleton dimension 1

GOOGLE CHROME:Version 122.0.6261.129 (Official version) (64-bit)
SD:version: 1.6.1  
•  python: 3.10.7  •  torch: 2.0.0+cpu  •  xformers: N/A  •  gradio: 3.41.2  •  checkpoint: a47e380db3
i can not run Inpaint Anything, the error shows sement anything failed.
The error information as above.

[Uminosachi]

The same error message as mentioned in issues #132 and #72. However, since the package is torch: 2.0.0+cpu and it's the CPU version, it might be a different issue.
Please try deleting the venv folder under stable-diffusion-webui and reinstalling the packages from scratch.