I am training my photos for sdxl lora today. I used ohwx woman for my wife , can i use same ohwx man
I am training my photos for sdxl lora today. I used ohwx woman for my wife , can i use same ohwx man ? or ohwx should be different ?
Dok i am using bbuk man for me and ohwx woman for my wife
Dthis should help me to create photos of us nboth i think
DNeed clarity on sdxl Lora training kaggle notebook code
DThere is different run code for Lora training after koyass webui run
DIt's giving me old error
RHi, @Dr. Furkan Gözükara some questions about Kohya training for SD. I would like to train clothing based on a culture. Basically, using any checkpoint, I can just invoke them to wear the clothing with just a keyword. Would a Lora be the best option? Also, when training, how do you best caption the dataset so that the Lora does not remember the background, the face, color of the clothing, physical weight of the person, etc. I only want the clothing, and want to be able to determine the colors. How many images would be minimum for clothing? And what's the best way to caption? I have tried so many different ways, and haven't been very successful.
Bhttps://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.7.0-RC
Automatic1111 is soon releasing 1.7.0
Automatic1111 is soon releasing 1.7.0
GitHub
How to use: wiki.
Features:
settings tab rework: add search field, add categories, split UI settings page into many
add altdiffusion-m18 support (#13364)
support inference with LyCORIS GLora netwo...
Features:
settings tab rework: add search field, add categories, split UI settings page into many
add altdiffusion-m18 support (#13364)
support inference with LyCORIS GLora netwo...
Dok i think i found the issue (possibly)
In json , there is add parameter ""additional_parameters": "--max_grad_norm=0.0 --no_half_vae --train_text_encoder","
removing --train_text_encoder solved teh sdxl_train.py error
i might be wrong , or this text shouldnt be removed.. @Dr. Furkan Gözükara should only confirm
In json , there is add parameter ""additional_parameters": "--max_grad_norm=0.0 --no_half_vae --train_text_encoder","
removing --train_text_encoder solved teh sdxl_train.py error
i might be wrong , or this text shouldnt be removed.. @Dr. Furkan Gözükara should only confirm
Dsince we are doing lora training and this parameter seems to be for dreambooth , this is causing the error likely
DKindly provide two different notebook files , one for dreambooth and another for lora , so that it wont confused , also the dreambooth_best json file keep overwriting the locally saved , whenever we need to rerun the kohyaass gui. Wish there was other option
Dso when i use two different face trained lora , how am i supposed to use adetailer ? and that too correctly on male and female faces ?
Fi think i had shown it but cant remember in which lecture it was
Fyou should have seperate model
Dlike ?
Fif you can collect 1000s of images
Fyou can caption with llava
Fand really obtain improved model
Fi would do dreambooth and then extract lora instead of lora training
Fi am reading changes
Fuse latest configs
Fthey are made for latest gui
Dmy wife lora is ready.. "
I am creating mine now.
So lets say i use something like
<lora:wife:1>,(ohwx woman) standing with <lora:husband:1>,(bbuk man) in an island
I am creating mine now.
So lets say i use something like
<lora:wife:1>,(ohwx woman) standing with <lora:husband:1>,(bbuk man) in an island
Dit will create two faces , in adetailer what prompt should we give ?
Di think it was there in notebook
Dit was inherited from "Kaggle_SDXL_DreamBooth_Best.json"
Dif we want to train lora , we cant skip moving this file to our folder if we run the code exactly
D
DSomeone help me with creating images with two different face lora
DAdetailer in particular
Mwould like to understand this as well. There is a SEP function in adetailer but have not gotten it to work yet.
MIs pixart-a compatible with fp8?
JHello I need some advice with a Dreambooth error when starting a training session "Exception training model: ''G:\IMG\training\Dijana\1024x1024\XDijanaX(8).jpeg' is not in list'."
It just stops any suggestions how to fix this ?
It just stops any suggestions how to fix this ?
RThank you for the answer. Do you have a video of captioning with llava and dreambooth and extracting lora? Thank you in advance.
AIs there adetailer in comfyui?
Fmaybe you can inpaint 2 faces
Fwith using 2 tabs
Fand each one focus on different face
Fdifferent prompt
Fyes it has fp8 loading of text encoder
Fi added to patreon
Fprepare dataset yourself
Fand copy paths
Fuse prepare dataset option of kohya gui
Fnot yet :/ but i plan to do hopefully
Fi think yes but i couldnt find how to make it work haha
Fpreparing an auto installer for new repo
Fmagic-animate
Shaving trouble getting the tensorrt extension to work. I get the no onnx error but it still doesnt work. Had to install manually since patreon "all files v2" install_TensorRT wouldnt work
Fwhat is your error can you show?
SIll be home in about an hour and a half and will share then if you’re available