Go to https://github.com/mav-rik/facerestore_cf for a more up to date fork of this project.
These ComfyUI nodes can be used to restore faces in images similar to the face restore option in AUTOMATIC1111 webui.
Installation
Extract the zip and put the facerestore directory inside the ComfyUI custom_nodes directory.
If running the portable windows version of ComfyUI, run embedded_install.bat
Windows users not running the portable version can run install.bat. Linux and mac users can run install.sh
If the install fails for whatever reason, you'll need to work out how to install opencv-python yourself (you'll get a cv2 not found error otherwise)
Face Restoration Models
These models perform the face restoration. If you use automatic1111 you probably already have them but if not here are the download links.
Just put them in models/facerestore_models.
https://github.com/TencentARC/GFPGAN/releases/
https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth
https://github.com/sczhou/CodeFormer/releases/
https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth
Face detection models
The face restoration model only works with cropped face images. A face detection model is used to send a crop of each face found to the face restoration model.
These will automaticly be downloaded and placed in models/facedetection the first time each is used.
Here's the links if you'd rather download them yourself.
https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth
https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_mobilenet0.25_Final.pth
https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/yolov5l-face.pth
https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/yolov5n-face.pth
This also gets downloaded and put in the facedetection folder. It's used to put the restored faces back into the original image.
https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/parsing_parsenet.pth
Description
Fixed FileNotFoundError Issue some people are having.
Added CropFace node, which crops a face without restoring it (maybe useful for comparing the different face detectors). Returns a cropped face and the total faces found. Use index to select a face from an image with multiple faces.
FAQ
Comments (14)
It's a great tool that works very well until you want to increase batch size to > 1. Then it fails with error:->
!!! Exception during processing !!!
Traceback (most recent call last):
File "C:\AI\ComfyUI_windows\ComfyUI\execution.py", line 145, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\AI\ComfyUI_windows\ComfyUI\execution.py", line 75, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "C:\AI\ComfyUI_windows\ComfyUI\execution.py", line 68, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "C:\AI\ComfyUI_windows\ComfyUI\custom_nodes\facerestore\__init__.py", line 132, in restore_face
self.face_helper.read_image(image_np)
File "C:\AI\ComfyUI_windows\ComfyUI\custom_nodes\facerestore\facelib\utils\face_restoration_helper.py", line 131, in read_image
self.input_img = cv2.resize(self.input_img, (0,0), fx=f, fy=f, interpolation=cv2.INTER_LINEAR)
cv2.error: OpenCV(4.8.0) D:\a\opencv-python\opencv-python\opencv\modules\imgproc\src\resize.cpp:3699: error: (-215:Assertion failed) !dsize.empty() in function 'cv::hal::resize'
I can instead, of course, just press the Queue Prompt button repeatedly with 'seed' on 'increment' until I've queued the number of images I want to generate.
can u share your workflow with me?
@nanunana yes, I'd be happy to send you the json file. How do I actually do that on here? Do you have an email address?
@abline11 [email protected] i thank you very much
@nanunana Hi Mike, I've send you the JSON and associated PNG file in an email. Thanks for looking at it.
@abline11 Looks like your review image dissappeared. I'm guessing civit incorrectly auto tagged it as nsfw and removed it. I used to have preview images that showed the face restore in action but that caused this 'model' to be classified as nsfw and be unviewable to anyone not signed in with filters turned off.
@abline11 thanx a lot
You may need to use the "rebatchLatents" node before you decode them. That should then work with batches.
Don´t work:
No module named 'cv2'
See the comment left by Andress17 for how to fix that. I'll make the dependency auto-install If I get around to updating this.
@m99 i´ve solved the problem, i installed first the v1.0 than the v2.0 over it. that works otherwise something is missing
@m99 but where i find the comment ofAndress17 ???
Per flyingshutter's comment, go into the comfyui root folder from a command prompt/console and type:
.\python_embeded\python -m pip install opencv-python
It worked just fine until yesterday and now there is a problem with opencv resize :(
you need to add a requirements.txt file with this :
opencv-python-4.8.0.74