Software Engineering Courses (SECourses)•3y ago

I take back what I said about Kohya Lora training. @Steel has shown me the light. Thanks mate, incre

I take back what I said about Kohya Lora training. @Steel has shown me the light. Thanks mate, incredible results.

Aurora 神名河•3/8/23, 8:12 AM

What is your training setting sir? Could you share it here?

PP1pSl1p I take back what I said about Kohya Lora training. @Steel has shown me the light...

Trimac•3/8/23, 8:12 AM

How many images and Learning rate you used? loooks good tho.

P1pSl1pOP•3/8/23, 8:14 AM

77 images. not cropped. full resolution

P1pSl1pOP•3/8/23, 8:14 AM

learning rate 0.0002

P1pSl1pOP•3/8/23, 8:15 AM

but there were a lot of custom settings he walked me through.

P1pSl1pOP•3/8/23, 8:15 AM

I'll try to compile a .txt file

P1pSl1pOP•3/8/23, 8:15 AM

just testing the Lora now tho

P1pSl1pOP•3/8/23, 8:16 AM

checking the flexibility

HolmesCage•3/8/23, 8:32 AM

im trying to generate a safetensors file from my lora but it always saves it like a model and it always has 5gb size what im doing wrong can anyone help me?

vjavad1443•3/8/23, 8:33 AM

@Dr. Furkan Gözükara Hi Dr, I'm truly appreciate for your time and effort. I've learned a lot from your channel & going to implement your tutorial. Just I had a question

Do you think it's better to work on dreambooth by using xformer 0.0.17 nightly or without it ?

vjavad1443•3/8/23, 8:35 AM

Just forgot to say on SD 1.5 I mean

vjavad1443•3/8/23, 8:38 AM

my second question is I wanted to know have you tried the below format for learning rate field instead of 0.00001 ?

0.05:10,0.02:20,0.01:60,0.005:200,0.002:500,0.001:3000,0.0005

I heard it gets better result but wanted to know your opinion as well

AAurora 神名河 What is your training setting sir? Could you share it here?

P1pSl1pOP•3/8/23, 8:45 AM

I'll put together a .txt

P1pSl1pOP•3/8/23, 8:45 AM

just playing around with the lora at the moment

P1pSl1pOP•3/8/23, 8:46 AM

I've never used a lora before so I'm new to the concept of using one to get accurate results

P1pSl1pOP•3/8/23, 8:48 AM

P1pSl1pOP•3/8/23, 8:49 AM

pretty insane if you ask me

gatsby•3/8/23, 8:51 AM

Hey, I want to add the pruned v1.5 and was wondering how I do this? Do I copy the hugging face url and do wget in stable-diffusion-webui / models?

P1pSl1pOP•3/8/23, 8:51 AM

add it to the models folder in your stable diffusion main

P1pSl1pOP•3/8/23, 8:52 AM

download it from huggingface

P1pSl1pOP•3/8/23, 8:52 AM

then move it into your models folder

PP1pSl1p then move it into your models folder

gatsby•3/8/23, 8:53 AM

Thanks, will try that

P1pSl1pOP•3/8/23, 8:53 AM

P1pSl1pOP•3/8/23, 8:53 AM

inside models you will see Stable-diffusion

P1pSl1pOP•3/8/23, 8:53 AM

put it in there

PP1pSl1p I'll put together a .txt

Aurora 神名河•3/8/23, 9:11 AM

Okay thank you!

HolmesCage•3/8/23, 9:15 AM

cant anyone help me :(

AAurora 神名河 Okay thank you!

P1pSl1pOP•3/8/23, 9:18 AM

realistic vision v1.3

Blip caption photos

batch size 2

LoRA type - Standard

training parameters:

Train Batch size - 2
Epoch - 1
Save every N epoch - 1
caption Extension - .txt

mixed precision - save precision - bf16
number of CPU threads per core - 8
Seed - 1234
cache latent - Check

learning rate - 0.0002
LR Scheduler - constant
LR warmup - 0
Optimizer - AdamW8bit

Text Encoder Learning Rate - 0.00005
Unet learning rate - 0.00008
Network Rank - 128
Network Alpha - 64

Max Rexolution - 768,768
Stop text encoder training - 0
Enable buckets - Check

Advance Settings - Default
Use xformers - Check

P1pSl1pOP•3/8/23, 9:18 AM

these were the training settings I used

Trimac•3/8/23, 9:22 AM

Can i see ur original photo?

P1pSl1pOP•3/8/23, 9:23 AM

which original photo? my dataset?

Trimac•3/8/23, 9:23 AM

Yes

Trimac•3/8/23, 9:24 AM

Just few or maybe 2

Trimac•3/8/23, 9:24 AM

im curios

P1pSl1pOP•3/8/23, 9:24 AM

P1pSl1pOP•3/8/23, 9:25 AM

and with captions

P1pSl1pOP•3/8/23, 9:25 AM

P1pSl1pOP•3/8/23, 9:25 AM

I plan to build a better dataset with more photos and variety

gatsby•3/8/23, 9:27 AM

Does anyone know if when generating class images I can use more than one word? For example instead of “painting” is it okay to use “fine art painting of a woman”

Ggatsby Does anyone know if when generating class images I can use more than one word? F...

P1pSl1pOP•3/8/23, 9:28 AM

when I tried to train on dreambooth originally with my dataset I had to be more specific in my class image generation because "photo of a woman" didn't give good results for me

PP1pSl1p when I tried to train on dreambooth originally with my dataset I had to be more ...

gatsby•3/8/23, 9:29 AM

Okay, so what did you have to use instead for better results?

P1pSl1pOP•3/8/23, 9:29 AM

since my wife is thai. I used "photo of a thai woman"

PP1pSl1p Click to see attachment

Trimac•3/8/23, 9:29 AM

Looks like lora copied perfectly your data set but not doing creativity. Well if that what you want then good for you

PP1pSl1p since my wife is thai. I used "photo of a thai woman"

gatsby•3/8/23, 9:30 AM

Ah okay. And then in your instance prompt did you use something like “ohwx photo of a Thai woman”?