Ah ok. Maybe ill just try your 2x upscale instead, should make most faces good without face inpaint
Ah ok. Maybe ill just try your 2x upscale instead, should make most faces good without face inpaint
๏ฟฝCouldn't make yolo model work. Ended up using <segment:face,0.6,0.5> which did work fine
Fyou probably didnt delete older model and downloaded new one. but this is also fine
Fi reported this issue but swarmui dev has no interest to fix
Fhe also doesnt accept my fixes too
๏ฟฝThats weird. He posted your 90 minute swarmui tutorial video and seemed happy for your support last year. Would think he would listen to your inputs.
Fyep his transformation is weird
Fi may fork repo and add some features and make our installers to use them
DI just finished watching the sdxl lora training using massed computes.. and doing my first training as we speak.. however .. training is 20% complete and i already have 2 loras downloaded.. but they look like nothing in the training images.. should i be concerned... just like in the video and all the presets.. donloaded from your patreon.. currently training is at epoch 44 out of 200.. 2 downloaded and they dont look like the training pics.. my prompt has included the ohwx woman...
Fyou tested on where? swarmui?_
Fnormally with 20% it should start looking a like
Fare you using our presets?
Dyes i am.. downloaded from patreon.. via massed computes i logged into my mimic pc account and tested them in my comfy ui workflow..
Fcan you also test it inside swarmui installed in massed compute
Fi wonder if your training images setup is wrong
F@Dr. Odin we dont allow nsfw here
Fyou can test example dataset
Dsorry about that.. my apologies
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Dokay
Fthat is a good one to verify your training setup
Dlemme see
KHow many epochs would you recommend for training 50 images for a 1024x1024 close-up face?
KSmall question: if I train my fine-tuned flux model, could I use it for inpainting, or do I need other parameters in koyas_ss to make it work a bit like flux fill?
KShould I do my training with flux fill instead of flux dev?
SYou can use your finetuned checkpoint to do impainting
Finetuning of flux fill isn't possible
Finetuning of flux fill isn't possible
SBetween 100 and 200. Around 150 is often the sweet spot with flux.dev, it depends on your dataset. I would recommend to save every 20 or 25 epochs, and compare on swarmui using the grid generation tool
Kok thx i will do this and follow the tutorial
K@skyrrr By any chance, are you familiar with face detection and Comfy UI? I'm struggling to create a workflow that would detect faces with Yolofacev8 or RetinaFace and then inpaint the face area, which would allow me to regenerate that part with my trained fluxfinetuned. But I can't find a good node. I tried installing โComfyUI Yolov8โ but I got an import error, so I guess it's not compatible. There's no information about this on GitHub.
๏ฟฝi'm scared to use this part of kohya, dont wanna waste a night of training and the model files werent saved anywhere...
๏ฟฝbut would be practical for sure
Ki scared to haha
Ki didi'nt do the tutorial yet
Kbut i wish everything will work for my flux fine tuned
Kbecause time is money on cloudGPU :((
KIt's hell trying to find a simple node that allows me to simply only mask a face.
Ksomething like that
Kbut more simple i wish
Fand compare
Fit works right away as flux fill
Fyou can do inpainting
Fi tested once or twice never worked
KThx Furkan ! Do u kwn something good for me to face detection and mask ?
KI thought I had found the perfect thing for me, but apparently comfyui has decided to give me more errors, as always.
Kok i think it's maybe beacause python 3.10 only not above 
JHow many repeats and learning rate for 150 images at 20-25 epochs?
Fthat is why i still use python 3.10.11
Fmost widely supported version
Fuse our presets dont change
