DLast year August I made this video using prompts on Google colab using deforum I think
DSince then I've been using MJ
DNow I need to get back to SD as I've ordered a GPU for my PC
DCan i get some links to where I can start?
Ffor deforum i dont have a video yet unfortunately
Fbut i am planning a good one
DIs Animation like this only possible on deforum?
Twould it be possible to train SD on the face of a newborn??
I'm an uncle for a few days and want to make some funny pictures with my nephew.
I think this could maybe hart, or? He looks like a standard baby
I'm an uncle for a few days and want to make some funny pictures with my nephew.
I think this could maybe hart, or? He looks like a standard baby
TMuhahaha if my sister could read this "He looks like a standard baby "
She would slap me in the face hahahahahaha
"She would slap me in the face
hahahahahahaFi think easiest way we can say
Fdefinitely possible
Fchose a good class
Flike baby
For maybe newborn
Tis there a need to use class images also?
Fthey improve quality
Fi think i will purchase Intel Core i9-13900K because core i7 10700f is delaying me
Fis this a good title?
FHow To Find Best Stable Diffusion Generated Images By Using DeepFace AI - DreamBooth LoRA Training
Zhey doc, your find best images, for linux we can't use bat files, should we just run the findbestimages.py script?
Fi have shown in video dont worry
Zthanks for the great work
Frendering the video
Zi'm installing the prerequisite files now
Fthank you
Zwhat would be great is to use this script with dreambooth to iterate through all your checkpoints and find the one that closely resembles your subject the most
Zor give each checkpoint a score or percentage of closeness to your subject
Fwell script cant do that. but you can generate images from each check point then let script sort
Fand then you can find best checkpoint
Fa good idea i can make a tutorial for that :d
Fupdated all extensions manually and deleted venv. looks like this was necessary :d
AHi @Furkan Gözükara SECourses. Automatic1111 has had many merges since the end of last month, I see that torch 2.0 and possibly a newer version of xformers is already in use. Is this a problem when using runpod? I used to follow your tutorial https://www.youtube.com/watch?v=zA4LksIVas8 along with this file: https://gist.github.com/FurkanGozukara/fdfb1c24a38509c8ec0184951ba12abf
but now it may be outdated.
but now it may be outdated.
YouTubeSECourses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. How to install latest version of Automatic1111 Web UI and #DreamBooth on #RunPod. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
Playlist of #StableDiffusi...
https://www.patreon.com/SECoursesPlaylist of #StableDiffusi...
Gist
How to run and install Automatic1111 Web UI and DreamBooth on RunPod with latest xformers - runpod xformers.txt
Ftorch 2 was not working
Flet me test again
Falso how is looking thumbnail
F
W@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-torchpip install xformersHere 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