s9roll7 / face_crop_img2img Goto Github PK
View Code? Open in Web Editor NEWAUTOMATIC1111 UI custom script for img2img around face with different "Denoising Strength" settings
AUTOMATIC1111 UI custom script for img2img around face with different "Denoising Strength" settings
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'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:
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 ?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.