s9roll7 / face_crop_img2img Goto Github PK

Hi, awesome extension, but unfortunately I have always issue like this :

Traceback (most recent call last):
File "I:\Github\new_webui\stable-diffusion-webui\modules\call_queue.py", line 45, in f
res = list(func(*args, **kwargs))
File "I:\Github\new_webui\stable-diffusion-webui\modules\call_queue.py", line 28, in f
res = func(*args, **kwargs)
File "I:\Github\new_webui\stable-diffusion-webui\modules\img2img.py", line 150, in img2img
processed = modules.scripts.scripts_img2img.run(p, *args)
File "I:\Github\new_webui\stable-diffusion-webui\modules\scripts.py", line 337, in run
processed = script.run(p, *script_args)
File "I:\Github\new_webui\stable-diffusion-webui\extensions\face_crop_img2img\scripts\face_crop_img2img.py", line 237, in run
bg = merge_face(bg, face_img, coord, base_img_size, mask)
File "I:\Github\new_webui\stable-diffusion-webui\extensions\face_crop_img2img\scripts\face_crop_img2img.py", line 167, in merge_face
img_array[y: y+h, x: x+w] = mask * face_array + (1-mask)*bg
ValueError: operands could not be broadcast together with shapes (101,89,3) (101,89,4)

Any chance to fix ?

i found some problem，when i using this extension
Picture splicing is not perfect

like this:

please help~plz
how could i fix this?

i've got a problem about Image style consistency

to me, use extension(face_crop_img2img) to fix face detiled, in order to get more perfect face

so i would holp that fixed-face is perfectly to siut the new whole picture style

but, when i using more, i found that was ignored

since we get the mask of face, we can do more things,

i holp:

1. we can have a button to deside whether use face mask generate directly or use it like a mask and put it into new pircture which just use prompt to creat.
2. we can have the buttons and options like [stable-diffusion-webui] in img2img-inpaint part of image.(expeciously the button of Full resolution partial redrawing, that can insure the Image style consistency)

thanks a lot

Hi, awesome extension, but unfortunately when I using YuNET, I have always issue like this :

Traceback (most recent call last):
File "C:\Users\kj4483\SD\stable-diffusion-webui\modules\call_queue.py", line 57, in f
res = list(func(*args, **kwargs))
File "C:\Users\kj4483\SD\stable-diffusion-webui\modules\call_queue.py", line 36, in f
res = func(*args, **kwargs)
File "C:\Users\kj4483\SD\stable-diffusion-webui\modules\img2img.py", line 206, in img2img
processed = modules.scripts.scripts_img2img.run(p, *args)
File "C:\Users\kj4483\SD\stable-diffusion-webui\modules\scripts.py", line 601, in run
processed = script.run(p, *script_args)
File "C:\Users\kj4483\SD\stable-diffusion-webui\extensions\face_crop_img2img\scripts\face_crop_img2img.py", line 257, in run
face_coords = detect_face(base_img, p.image_mask,face_detection_method)
File "C:\Users\kj4483\SD\stable-diffusion-webui\extensions\face_crop_img2img\scripts\face_crop_img2img.py", line 240, in detect_face
return self.detect_face(img_array)
File "C:\Users\kj4483\SD\stable-diffusion-webui\extensions\face_crop_img2img\scripts\face_crop_img2img.py", line 102, in detect_face
_, result = self.face_detector.detect(img_array)
cv2.error: OpenCV(4.8.1) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\net_impl.cpp:279: error: (-204:Requested object was not found) Layer with requested id=-1 not found in function 'cv::dnn::dnn4_v20230620::Net::Impl::getLayerData'

I've explored the above issues but have not been able to find a solution.

Any chance to fix ?