Software Engineering Courses (SECourses)•2y ago

<@205854764540362752> I am running One-Trainer and trying to control the training process by saving

@Furkan Gözükara SECourses I am running One-Trainer and trying to control the training process by saving samples every 20 epochs. I use config tier2_SD15_fast_15GB.json and change parameters in config: config["sample_after"] = 20
config["sample_after_unit"] = "EPOCH". My prompt is like ""portrait photo of ohwx man, in white business shirt, dark gray graybackground, neat hairstyle, handsome, smile, hd, sharp focus"" But I have 2 problems. 1) There is just no difference between samples after approximately 40 epochs. 2) The samples look strange: problems with hair, blured shirt.

Please tell me what could be the problem

Ssmoke Has anyone ever tried TPUs?

Furkan Gözükara SECourses•7/9/24, 2:11 PM

TPUs requires special software as far as i know

ФФёдор Коноваленко <@205854764540362752> I am running One-Trainer and trying to control the trainin...

Furkan Gözükara SECourses•7/9/24, 2:12 PM

could be fully overtrained

Furkan Gözükara SECourses•7/9/24, 2:12 PM

how many training images you have?

papanton•7/9/24, 2:40 PM

Hi @Furkan Gözükara SECourses what speed are you getting using: tier1_SD15_fastest_48GB.json from this post? https://www.patreon.com/posts/very-best-config-97381002?utm_medium=clipboard_copy&utm_source=copyLink&utm_campaign=postshare_fan&utm_content=web_share

Patreon

The Very Best OneTrainer Workflow & Config For SD 1.5 Based Models ...

Get more from SECourses: Tutorials, Guides, Resources, Training, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözükara on Patreon

kareem9000•7/10/24, 11:51 AM

Can someone point me to the latest dreambooth patreon guide link

kareem9000•7/10/24, 11:51 AM

I always get lost in the links on there

Dazzastrous [4090]•7/10/24, 11:51 AM

yeh me too

TheToday•7/10/24, 12:02 PM

If in our dataset we have images with different expressions and emotions, would it be advisable to make the corresponding caption or would ohwx woman simply work?

papanton•7/10/24, 1:27 PM

any idea what would cause the trained model to spit out images like this?

Maxivi•7/10/24, 2:33 PM

looks like te2 is training at its full rate on the latest kohya.

in case anyone is having issues with it.

input this in the advanced tab

--learning_rate_te2 0

Maxivi•7/10/24, 2:37 PM

@kareem9000 @Dazzastrous [4090]

SDXL - https://www.patreon.com/posts/very-best-for-of-89213064
SD1.5 - https://www.patreon.com/posts/very-best-kohya-97379147

Patreon

The Very Best Workflow For SDXL DreamBooth / Full Fine Tuning - Res...

Get more from SECourses: Tutorials, Guides, Resources, Training, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözükara on Patreon

Patreon

The Very Best Kohya GUI Workflow & Config For SD 1.5 Based Models D...

Get more from SECourses: Tutorials, Guides, Resources, Training, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözükara on Patreon

maverickk•7/10/24, 5:15 PM

I have to do style training with sdxl Lora

MMaxivi <@447551264339787797> <@871389071686135838> SDXL - https://www.patreon.com/pos...

kareem9000•7/10/24, 7:30 PM

are u sure those are the latest

Darth Teethius•7/10/24, 11:52 PM

Anyone kick the tires on the sd3 training on one trainer yet?

Kkareem9000 are u sure those are the latest

Maxivi•7/11/24, 5:42 AM

im pretty sure, patreon is pretty confusing, which they could organize it better

Ppapanton any idea what would cause the trained model to spit out images like this?

Gen-AI•7/11/24, 6:25 AM

Your results are very similar to mine. I wonder why these results are coming out and I want to find out how to solve them. Does anyone else have similar errors like this?

GGen-AI Your results are very similar to mine. I wonder why these results are coming out...

J2_Nedo•7/11/24, 7:34 AM

if you invert the colors in photoshop, the colors become correct but the resolution is terrible

Kkareem9000 Can someone point me to the latest dreambooth patreon guide link

Furkan Gözükara SECourses•7/11/24, 9:57 AM

https://www.patreon.com/posts/very-best-for-of-89213064

Patreon

The Very Best Workflow For SDXL DreamBooth / Full Fine Tuning - Res...

Get more from SECourses: Tutorials, Guides, Resources, Training, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözükara on Patreon

Furkan Gözükara SECourses•7/11/24, 9:58 AM

and download and look at runpod_8400_Steps.png attachments

Furkan Gözükara SECourses•7/11/24, 9:58 AM

@Dazzastrous [4090]

Ppapanton any idea what would cause the trained model to spit out images like this?

Furkan Gözükara SECourses•7/11/24, 9:58 AM

config error

TTheToday If in our dataset we have images with different expressions and emotions, would ...

Furkan Gözükara SECourses•7/11/24, 9:58 AM

i would do 2 training and compare and see which one worked better

Furkan Gözükara SECourses•7/11/24, 9:59 AM

but i think ohwx man may work better than captioning still try it

MMaxivi looks like te2 is training at its full rate on the latest kohya. in case anyon...

Furkan Gözükara SECourses•7/11/24, 9:59 AM

yes this should be provided. in my config i provide it

DDarth Teethius Anyone kick the tires on the sd3 training on one trainer yet?

Furkan Gözükara SECourses•7/11/24, 9:59 AM

i am waiting merged into main still has errors

GGen-AI Your results are very similar to mine. I wonder why these results are coming out...

Furkan Gözükara SECourses•7/11/24, 10:00 AM

i trained 6 models like 2 days ago

Furkan Gözükara SECourses•7/11/24, 10:00 AM

worked perfect with my config.

FFurkan Gözükara SECourses i trained 6 models like 2 days ago

Gen-AI•7/11/24, 10:08 AM

I just solved a problem I had. When CompyUI connected vae to vae decoder through the vae loader node, the image was created normally. I was using the config file you shared with Patreon.

GGen-AI I just solved a problem I had. When CompyUI connected vae to vae decoder through...

Furkan Gözükara SECourses•7/11/24, 10:09 AM

makes sense because training werent broken

FFurkan Gözükara SECourses makes sense because training werent broken 😄

Gen-AI•7/11/24, 10:14 AM

I trained the model using your config file, but when I didn't connect the VAE loader, the images came out the same as before. Is it possible that the model didn't train properly? I used the config file you shared on Patreon and trained with normalized images.

GGen-AI Your results are very similar to mine. I wonder why these results are coming out...

kareem9000•7/11/24, 10:22 AM

Spooky

GGen-AI I trained the model using your config file, but when I didn't connect the VAE lo...

Furkan Gözükara SECourses•7/11/24, 10:37 AM

use models in auto1111 and if they work directly then model trained accurately

Maxivi•7/11/24, 11:06 AM

@Furkan Gözükara SECourses have you tried trainings with sdxl noise offset of 0.0357 and the scheduled huber loss settings

Maxivi•7/11/24, 12:10 PM

@Furkan Gözükara SECourses when you get some time can you try this prompt out on your training?

Postive - cinematic photo Portrait of ohwx man as super Mario, red hat, fantasy, highly detailed, digital painting, artstation, concept art, sharp focus, illustration, art by Tony Sart and artgerm and randy vargas. 35mm photograph, film, bokeh, professional, 4k, highly detailed

Negative - drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render

DPM ++2sa Karras

1024x1024

CFG - 7

can you check if you get good likness

Théo•7/11/24, 2:09 PM

After 30 training and 5 dataset retake to have the best one, i finally achieve the - p e r f e c t - result thanks to @Furkan Gözükara SECourses however, mid-distance or distance shot are Totally destroyed, my dataset is perfect, used cinema grade camera, used cropper and resizer, tried mask training, adetailer, changing the number of step only for face, changing the denoising strengh, i can only make p r e f e c t close-up, selfie or whatever, but when the subject is in midrange like your picture in civtai, or fullbody, it's totally crap, even the face is not really "human" more like destroyed, any idea ? thanks for everything (also tried with and without reg)

TThéo After 30 training and 5 dataset retake to have the best one, i finally achieve t...

Maxivi•7/11/24, 2:11 PM

are you training on realvis4 and using the model on a different checkpoint?

Théo•7/11/24, 2:32 PM

traing on realvis4, using on realvis4

Théo•7/11/24, 2:33 PM

i have to admit i spent the last weeks understanding every little things possible and even myself cannot recognize a (fake) picture from myself, ,even my family, but im limited to close-up

Maxivi•7/11/24, 3:12 PM

and all your images are cropped at 1024x1024?

Théo•7/11/24, 3:22 PM

ok i understood, to be possible to inpaint in a far away face, you need to Hires a lot, so the Adetailer can actually see the face to inpaint

Maxivi•7/11/24, 3:23 PM

use adetailer with correct settings, and with hires fix use 4x ultrasharp or any other good upscalers

Théo•7/11/24, 3:24 PM

my problem was that i wasnt upscalling enough, 1.25 or 1.5 is not good enough for the adetailer to work properly

Théo•7/11/24, 3:25 PM

but 2x upscaling is good, now i have the (body proportion) problem but its easier to fix than not be able to inpaint

Maxivi•7/11/24, 4:50 PM

yeah i usually upscale with 1.75x to 2x with 60 steps on adetailer

MMaxivi <@205854764540362752> when you get some time can you try this prompt out on your...

Furkan Gözükara SECourses•7/11/24, 10:51 PM

some prompts will overwrite your likeliness

Furkan Gözükara SECourses•7/11/24, 10:51 PM

like super Mario

Furkan Gözükara SECourses•7/11/24, 10:51 PM

because the model will assosicate it with a certain man

Furkan Gözükara SECourses•7/11/24, 10:51 PM

super Mario - original dataset

Furkan Gözükara SECourses•7/11/24, 10:51 PM

or super man

Furkan Gözükara SECourses•7/11/24, 10:51 PM

it is like ohwx man as brad pitt same