Software Engineering Courses (SECourses)•3y ago

ok i think i found the issue (possibly) In json , there is add parameter ""additional_parameters":

ok 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

DR.SivaOP•12/4/23, 10:19 AM

since we are doing lora training and this parameter seems to be for dreambooth , this is causing the error likely

DR.SivaOP•12/4/23, 10:21 AM

Kindly 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

DR.SivaOP•12/4/23, 10:26 AM

so when i use two different face trained lora , how am i supposed to use adetailer ? and that too correctly on male and female faces ?

WWalter white.@Dr. Furkan Gözükara i am on the 2nd episode of your course on udemy, have you i...

Furkan Gözükara SECourses•12/4/23, 10:32 AM

i think i had shown it but cant remember in which lecture it was

DDR.Siva I am training my photos for sdxl lora today. I used ohwx woman for my wife , can...

Furkan Gözükara SECourses•12/4/23, 10:32 AM

you should have seperate model

DR.SivaOP•12/4/23, 10:33 AM

like ?

RRelentlessDung Hi, @Dr. Furkan Gözükara some questions about Kohya training for SD. I would lik...

Furkan Gözükara SECourses•12/4/23, 10:33 AM

if you can collect 1000s of images

Furkan Gözükara SECourses•12/4/23, 10:33 AM

you can caption with llava

Furkan Gözükara SECourses•12/4/23, 10:33 AM

and really obtain improved model

Furkan Gözükara SECourses•12/4/23, 10:33 AM

i would do dreambooth and then extract lora instead of lora training

BBenjamin https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.7.0-RC ...

Furkan Gözükara SECourses•12/4/23, 10:33 AM

i am reading changes

DDR.Siva ok i think i found the issue (possibly) In json , there is add parameter ""addi...

Furkan Gözükara SECourses•12/4/23, 10:33 AM

use latest configs

Furkan Gözükara SECourses•12/4/23, 10:33 AM

they are made for latest gui

DR.SivaOP•12/4/23, 10:35 AM

my 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

DR.SivaOP•12/4/23, 10:35 AM

it will create two faces , in adetailer what prompt should we give ?

FFurkan Gözükara SECourses use latest configs

DR.SivaOP•12/4/23, 10:35 AM

i think it was there in notebook

DR.SivaOP•12/4/23, 10:37 AM

it was inherited from "Kaggle_SDXL_DreamBooth_Best.json"

DR.SivaOP•12/4/23, 10:37 AM

if we want to train lora , we cant skip moving this file to our folder if we run the code exactly

DR.SivaOP•12/4/23, 10:56 AM

DR.SivaOP•12/4/23, 6:12 PM

Someone help me with creating images with two different face lora

DR.SivaOP•12/4/23, 6:12 PM

Adetailer in particular

DDR.Siva Someone help me with creating images with two different face lora

mtnmecca•12/4/23, 7:10 PM

would like to understand this as well. There is a SEP function in adetailer but have not gotten it to work yet.

Metaphysix•12/4/23, 7:34 PM

Is pixart-a compatible with fp8?

Jova•12/4/23, 7:50 PM

Hello 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 ?

FFurkan Gözükara SECourses you can caption with llava

RelentlessDung•12/4/23, 9:22 PM

Thank you for the answer. Do you have a video of captioning with llava and dreambooth and extracting lora? Thank you in advance.

AIGambino•12/4/23, 9:40 PM

Is there adetailer in comfyui?

DDR.Siva Someone help me with creating images with two different face lora

Furkan Gözükara SECourses•12/4/23, 11:24 PM

maybe you can inpaint 2 faces

Furkan Gözükara SECourses•12/4/23, 11:24 PM

with using 2 tabs

Furkan Gözükara SECourses•12/4/23, 11:24 PM

and each one focus on different face

Furkan Gözükara SECourses•12/4/23, 11:24 PM

different prompt

MMetaphysix Is pixart-a compatible with fp8?

Furkan Gözükara SECourses•12/4/23, 11:24 PM

yes it has fp8 loading of text encoder

Furkan Gözükara SECourses•12/4/23, 11:24 PM

i added to patreon

JJova Hello I need some advice with a Dreambooth error when starting a training sessio...

Furkan Gözükara SECourses•12/4/23, 11:25 PM

prepare dataset yourself

Furkan Gözükara SECourses•12/4/23, 11:25 PM

and copy paths

Furkan Gözükara SECourses•12/4/23, 11:25 PM

use prepare dataset option of kohya gui

RRelentlessDung Thank you for the answer. Do you have a video of captioning with llava and dream...

Furkan Gözükara SECourses•12/4/23, 11:25 PM

not yet :/ but i plan to do hopefully

AAIGambino Is there adetailer in comfyui?

Furkan Gözükara SECourses•12/4/23, 11:25 PM

i think yes but i couldnt find how to make it work haha

Furkan Gözükara SECourses•12/4/23, 11:25 PM

preparing an auto installer for new repo

Furkan Gözükara SECourses•12/4/23, 11:25 PM

magic-animate

shortdwarf•12/4/23, 11:39 PM

having 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

Sshortdwarf having trouble getting the tensorrt extension to work. I get the no onnx error b...

Furkan Gözükara SECourses•12/4/23, 11:58 PM

what is your error can you show?

shortdwarf•12/5/23, 12:25 AM

Ill be home in about an hour and a half and will share then if you’re available

Sshortdwarf Ill be home in about an hour and a half and will share then if you’re available

Furkan Gözükara SECourses•12/5/23, 12:38 AM

i may be sleeping but can commet tomorrow hopefully

FFurkan Gözükara SECourses not yet :/ but i plan to do hopefully

RelentlessDung•12/5/23, 1:46 AM

Thank you, looking forward to it

J.•12/5/23, 2:44 AM

does anyone know how to do fooocus+ get an api? I read some github issue where it said to just click on API with Gradio, but it just leads to a bunch of nonsense as far as i can tell. doesn't really give any docs or endpoints that seem to do anything.

Not too familiar with the whole gradio ecosystem.

aliattaran•12/5/23, 2:50 AM

@Dr. Furkan Gözükara hi, which tier should i join to have the face swap code setup on my system?

DoluBura- esat•12/5/23, 5:19 AM

Good morning
3 days ago I was able to print 2048x2048 images with 4060 8gb vram, but now I can not print.
If idle vram usage can help me in this case, thank you very much in advance.

DoluBura- esat•12/5/23, 5:21 AM

RuntimeError: Not enough memory, use lower resolution (max approx. 1600x1600). Need: 6.0GB free, Have:4.2GB free

DoluBura- esat•12/5/23, 5:21 AM

DoluBura- esat•12/5/23, 5:23 AM

With no models or lora installed, vram usage is 2.8 vram.

ok i think i found the issue (possibly) In json , there is add parameter ""additional_parameters":

Similar Threads