@Dr. Furkan Gözükara yolov8 is out, should we be using this model in auto-cropper instead of the yo
@Dr. Furkan Gözükara yolov8 is out, should we be using this model in auto-cropper instead of the yolov7 in your donwload?
Fyou dont need python class
Fthis video exactly for you https://youtu.be/-NjNy7afOQ0
YouTubeSECourses
Welcome to the Pillars of AI Application Libraries: How to Install Tutorial! 
Are you ready to embark on a journey of installing AI libraries and applications with ease? 
In this video, we'll guide you through the process of installing Python, Git, Visual Studio C++ Compile tools, and FFmpeg on your Windows 10 machine. 
We'll also show you ho...
Are you ready to embark on a journey of installing AI libraries and applications with ease? In this video, we'll guide you through the process of installing Python, Git, Visual Studio C++ Compile tools, and FFmpeg on your Windows 10 machine. We'll also show you ho...
�i was not asking related to the hugging face thing, just in general
Fi couldnt make yolo v8 work :/
ROk no worries, i dont think the difference would be that massive
Rthanks anyway!
Rhope you're well
Fmy udemy course taken down. other than that i am good thankfully
Rwhy was it taken down????
Rpolitics?
Fbecause of my tweet.
Fyes politics
Rwhat tweet?
Roh damn
Rreally
Fa tweet sent from my twitter
Fyes
Fnothing related to udemy platform
Ri can imagine about palestine?
Fyep
Romg
Rthat is bs
Fthey cancelled me too haha
Rpolitics
Rwell, you are on the right side of the fence (and history)
Rthese people one day will have karma up their ass
Rit all comes back around
Ftrue
Rwoke culture. it will come back to bite them
Rbut otherwise i am happy you are good
Fthanks
Vxformers no longer hitting on cu118 dev branch?
VI'm all good - found fix via search
Psomething I'm working on ATM. Looking good so far.
Fnice
Pthis is my first illustration character in SDXL. It's a lot easier than training a real person. Also a lot easier to put into context, even though all training images had white background.
RHey @Dr. Furkan Gözükara i am running your autocropper_v7 but no cropping is taking place
Rcropper-2.py3.62KB
Rhere's my config for the variables (normally in the cropper_v7.py script. I am getting the full output to different ar folders, but the images are not actually cropped...
R
Rbut the images in subfolders are all exactly like original portraits
Roriginal image
R1024_1024 crop folder
Ri am on visual studio copilot. not giving me a crop atm
R
Rok well i can see some minor cropping, just i guess is due to model trying to preserve areas around face like neck. So i suppose i have to still run some manual cropping at Topaz stage of upscaling or with Birme. unless there is a threshold slider to force the model to crop
Hhttps://www.patreon.com/posts/89213064 am I correct in thinking we generally dont need to amend any settings not provided in the JSON files here? For example I noticed using /workspace/24GB_TextEncoder.json I have 8 epoch with 40 repeating steps. I don't need to change anything just because I have higher training images right? say 50 or 100? the training steps seem to work out still according to the formula about 35k when I print the training command
Vcareful if youtube retaliates in a similar fashion
Ri really dont know what cropper does. its definitely not cropping to the aspect ration it says it is doing