Error running postprocess_image: D:\sd\stable-diffusion-webui\extensions\sd-webui-reactor-sfw\scripts\reactor_faceswap.py

[xiongdaxsl]

First, confirm

• I have read the instruction carefully
• I have searched the existing issues
• I have updated the extension to the latest version

What happened?

Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same or input should be a MKLDNN tensor and weight is a dense tensor

Steps to reproduce the problem

1. Go to ....
2. Press ....
3. ...

Sysinfo

Error running postprocess_image: D:\sd\stable-diffusion-webui\extensions\sd-webui-reactor-sfw\scripts\reactor_faceswap.py
Traceback (most recent call last):
File "D:\sd\stable-diffusion-webui\modules\scripts.py", line 912, in postprocess_image
script.postprocess_image(p, pp, *script_args)
File "D:\sd\stable-diffusion-webui\extensions\sd-webui-reactor-sfw\scripts\reactor_faceswap.py", line 465, in postprocess_image
result, output, swapped = swap_face(
File "D:\sd\stable-diffusion-webui\extensions\sd-webui-reactor-sfw\scripts\reactor_swapper.py", line 391, in swap_face
if check_sfw_image(result_image) is None:
File "D:\sd\stable-diffusion-webui\extensions\sd-webui-reactor-sfw\scripts\reactor_swapper.py", line 359, in check_sfw_image
if not sfw.nsfw_image(tmp_img, NSFWDET_MODEL_PATH):
File "D:\sd\stable-diffusion-webui\extensions\sd-webui-reactor-sfw\scripts\reactor_sfw.py", line 15, in nsfw_image
result = predict(img)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\pipelines\image_classification.py", line 100, in call
return super().call(images, **kwargs)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\pipelines\base.py", line 1120, in call
return self.run_single(inputs, preprocess_params, forward_params, postprocess_params)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\pipelines\base.py", line 1127, in run_single
model_outputs = self.forward(model_inputs, **forward_params)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\pipelines\base.py", line 1026, in forward
model_outputs = self._forward(model_inputs, **forward_params)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\pipelines\image_classification.py", line 108, in _forward
model_outputs = self.model(**model_inputs)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\models\vit\modeling_vit.py", line 804, in forward
outputs = self.vit(
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\models\vit\modeling_vit.py", line 583, in forward
embedding_output = self.embeddings(
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\models\vit\modeling_vit.py", line 122, in forward
embeddings = self.patch_embeddings(pixel_values, interpolate_pos_encoding=interpolate_pos_encoding)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\models\vit\modeling_vit.py", line 181, in forward
embeddings = self.projection(pixel_values).flatten(2).transpose(1, 2)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "D:\sd\stable-diffusion-webui\extensions-builtin\Lora\networks.py", line 599, in network_Conv2d_forward
return originals.Conv2d_forward(self, input)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same or input should be a MKLDNN tensor and weight is a dense tensor

Relevant console log

Error running postprocess_image: D:\sd\stable-diffusion-webui\extensions\sd-webui-reactor-sfw\scripts\reactor_faceswap.py
    Traceback (most recent call last):
      File "D:\sd\stable-diffusion-webui\modules\scripts.py", line 912, in postprocess_image
        script.postprocess_image(p, pp, *script_args)
      File "D:\sd\stable-diffusion-webui\extensions\sd-webui-reactor-sfw\scripts\reactor_faceswap.py", line 465, in postprocess_image
        result, output, swapped = swap_face(
      File "D:\sd\stable-diffusion-webui\extensions\sd-webui-reactor-sfw\scripts\reactor_swapper.py", line 391, in swap_face
        if check_sfw_image(result_image) is None:
      File "D:\sd\stable-diffusion-webui\extensions\sd-webui-reactor-sfw\scripts\reactor_swapper.py", line 359, in check_sfw_image
        if not sfw.nsfw_image(tmp_img, NSFWDET_MODEL_PATH):
      File "D:\sd\stable-diffusion-webui\extensions\sd-webui-reactor-sfw\scripts\reactor_sfw.py", line 15, in nsfw_image
        result = predict(img)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\pipelines\image_classification.py", line 100, in __call__
        return super().__call__(images, **kwargs)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\pipelines\base.py", line 1120, in __call__
        return self.run_single(inputs, preprocess_params, forward_params, postprocess_params)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\pipelines\base.py", line 1127, in run_single
        model_outputs = self.forward(model_inputs, **forward_params)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\pipelines\base.py", line 1026, in forward
        model_outputs = self._forward(model_inputs, **forward_params)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\pipelines\image_classification.py", line 108, in _forward
        model_outputs = self.model(**model_inputs)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
        return self._call_impl(*args, **kwargs)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
        return forward_call(*args, **kwargs)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\models\vit\modeling_vit.py", line 804, in forward
        outputs = self.vit(
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
        return self._call_impl(*args, **kwargs)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
        return forward_call(*args, **kwargs)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\models\vit\modeling_vit.py", line 583, in forward
        embedding_output = self.embeddings(
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
        return self._call_impl(*args, **kwargs)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
        return forward_call(*args, **kwargs)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\models\vit\modeling_vit.py", line 122, in forward
        embeddings = self.patch_embeddings(pixel_values, interpolate_pos_encoding=interpolate_pos_encoding)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
        return self._call_impl(*args, **kwargs)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
        return forward_call(*args, **kwargs)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\transformers\models\vit\modeling_vit.py", line 181, in forward
        embeddings = self.projection(pixel_values).flatten(2).transpose(1, 2)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
        return self._call_impl(*args, **kwargs)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
        return forward_call(*args, **kwargs)
      File "D:\sd\stable-diffusion-webui\extensions-builtin\Lora\networks.py", line 599, in network_Conv2d_forward
        return originals.Conv2d_forward(self, input)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
        return self._conv_forward(input, self.weight, self.bias)
      File "D:\sd\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
        return F.conv2d(input, weight, bias, self.stride,
    RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same or input should be a MKLDNN tensor and weight is a dense tensor

Additional information

No response

[PatrickAgeev]

same story

[dermesut]

here too

[mykeehu]

Same here. This could be due to nsfw filtering, but then it would be useful to include a switch for the options.

[AlexSavex]

Failed to build insightface
CUDA 12.1
Error: The 'insightface==0.7.3' distribution was not found and is required by the application

Same trouble

[youhua1]

Find the reactor_sfw.py file in the root directory and modify the code to the following:

from transformers import pipeline
from PIL import Image
import logging
import torch

SCORE = 0.965

logging.getLogger('transformers').setLevel(logging.ERROR)

def nsfw_image(img_path: str, model_path: str):
    device = 'cuda' if torch.cuda.is_available() else 'cpu'
    with Image.open(img_path) as img:
        predict = pipeline("image-classification", model=model_path, device=0 if device == 'cuda' else -1)
        result = predict(img)
        score = result[0]["score"]
        return True if score > SCORE else False

[SpiritOfDeath17]

Find the reactor_sfw.py file in the root directory and modify the code to the following:

from transformers import pipeline
from PIL import Image
import logging
import torch

SCORE = 0.965

logging.getLogger('transformers').setLevel(logging.ERROR)

def nsfw_image(img_path: str, model_path: str):
device = 'cuda' if torch.cuda.is_available() else 'cpu'
with Image.open(img_path) as img:
predict = pipeline("image-classification", model=model_path, device=0 if device == 'cuda' else -1)
result = predict(img)
score = result[0]["score"]
return True if score > SCORE else False

Okay, it's worked for me and I don't see any errors in console, but after trying to img2img faceswap I have no result. It just run for 2 seconds and give me image that I put into img2img (not source reactor image)