@Furkan Gözükara SECourses Have you tried finetuning on DeepFloyd IF?
@Furkan Gözükara SECourses
Have you tried finetuning on DeepFloyd IF?
Have you tried finetuning on DeepFloyd IF?
AFor what it's worth, I just tested it and it does work (I haven't tried dreambooth, only automatic 1111). I upgraded to the latest version
Here are the parameters: python: 3.10.10 • torch: 2.0.0+cu117 • xformers: 0.0.19 • gradio: 3.28.1 • commit: 5ab7f213 • checkpoint: 4c86efd062
git pull--reinstall-torch command to force it to install 2.0.0, installed the latest version of xformers directly with pip install xformers and it works correctly.Here are the parameters: python: 3.10.10 • torch: 2.0.0+cu117 • xformers: 0.0.19 • gradio: 3.28.1 • commit: 5ab7f213 • checkpoint: 4c86efd062
Zyeah i'm getting an error when ruunning find face
Zsays valueerror: face could not be detected, please confirm that the picture is a face photo or consider to set enforce_detection param fo false
Z
ZTraceback (most recent call last):
File "/home/zono50/Scripts/findBestImages.py", line 35, in <module>
detected_face = DeepFace.detectFace(org_image_path, detector_backend='opencv')
File "/home/zono50/anaconda3/envs/findbestimages/lib/python3.10/site-packages/deepface/DeepFace.py", line 820, in detectFace
face_objs = extract_faces(
File "/home/zono50/anaconda3/envs/findbestimages/lib/python3.10/site-packages/deepface/DeepFace.py", line 787, in extract_faces
img_objs = functions.extract_faces(
File "/home/zono50/anaconda3/envs/findbestimages/lib/python3.10/site-packages/deepface/commons/functions.py", line 115, in extract_faces
raise ValueError(
ValueError: Face could not be detected. Please confirm that the picture is a face photo or consider to set enforce_detection param to False.
File "/home/zono50/Scripts/findBestImages.py", line 35, in <module>
detected_face = DeepFace.detectFace(org_image_path, detector_backend='opencv')
File "/home/zono50/anaconda3/envs/findbestimages/lib/python3.10/site-packages/deepface/DeepFace.py", line 820, in detectFace
face_objs = extract_faces(
File "/home/zono50/anaconda3/envs/findbestimages/lib/python3.10/site-packages/deepface/DeepFace.py", line 787, in extract_faces
img_objs = functions.extract_faces(
File "/home/zono50/anaconda3/envs/findbestimages/lib/python3.10/site-packages/deepface/commons/functions.py", line 115, in extract_faces
raise ValueError(
ValueError: Face could not be detected. Please confirm that the picture is a face photo or consider to set enforce_detection param to False.
Fye it wasnt working for dreambooth on unix
Fit can happen in some faces
Fif it happens in your training images
Fremove them
Ffrom folder
Fyour org folder must have good pictures
Fthat face can be deteceted
Fbut i will update script
Ffor auto removal good idea
Fworking on script update
TCan stable diffusion train on bearded men? It cant seem to get good results on my own face and i think thats why
Ti mean big beards, mine is a full foot long probably more
EHello, need some help on copying some SD files from one pod to another, watched the tutorial on youtube but it errors out. Not sure if this is the right channel to ask, if not, apologies in advance.
Zyeah nothing i seem to do will get this womans face properly
Fupdated script you can redownload
Fi think yes why not
Tprobably my dataset then, I have a feeling the transparency of beards can cause issue
Zdoc my wife is going to divorce me if i don't make a good model of her
Zno pressure
II have entered discord, because I was a teacher, and they are the best tutorials for the use and installation of stable diffusion that I have seen of all the ones on youtube, not only for the explanations of how to do the things, but there is an addition where You explain, for example, in dreambooth the parameters for which they are used in detail, then you also apply different resolutions and compare the results.
It is let's say a very scientific methodology, congratulations
It is let's say a very scientific methodology, congratulations
Zis having 200 images in my dataset using 5 class reg images the same as using 10 images in my dataset using 5 class reg images
Zlike how do i get it to learn every intricate detail of someones face
Fthank you so much
Fyes I am also a teacher. Assistant professor in a private university in Turkey
Fnew video almost ready. waiting youtube to synch subtitles hopefully
ZI did a search on stable diffusion, saw an article on linkedin, guess whose it was
Zis the only point of the num class instancers per image or regularization images is to preserve the class?
Zso if it overfits, if i type woman, it will only show the woman in my dataset, and no other women?
Zcan you explain doc?
Z@Furkan Gözükara SECourses
Fnot only that
Fit also prevents overtraining
Fif you train very long, even when you dont type anything you get your trained subject
Fbecause unet becomes cooked
Zovertraining is when the images start looking warped?
Fusually
TI have a question, when you use the "ohwx man" and the <lora> to generate an image, are you still increasing the weights using ctrl+up e.g. (ohwx man:1.5) or are you keeping it at 1.1?
2nd question; Do we need both [the lora and the ohwx man] everytime we want to call our model?
2nd question; Do we need both [the lora and the ohwx man] everytime we want to call our model?
Fi usually test this because sometimes 1.1 or 1.2 works better
Fso you need to test
F2nd : yes
Tthank you!
I am seeing great results with 1.3 but gets worse higher than that
can you increase the weights on the <lora>? what effect would that have?
I am seeing great results with 1.3 but gets worse higher than that
can you increase the weights on the <lora>? what effect would that have?
Factually i didnt test increased weight of lora but you can test easily with sr prompt
TAlright, thanks again!
Zwhat's the best way to impose someones face using controlnet?