What is your training setting sir? Could you share it here?
What is your training setting sir? Could you share it here?
THow many images and Learning rate you used? loooks good tho.
P77 images. not cropped. full resolution
Plearning rate 0.0002
Pbut there were a lot of custom settings he walked me through.
PI'll try to compile a .txt file
Pjust testing the Lora now tho
Pchecking the flexibility
Him 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?
V@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 ?
Do you think it's better to work on dreambooth by using xformer 0.0.17 nightly or without it ?
VJust forgot to say on SD 1.5 I mean
Vmy 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
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
PI'll put together a .txt
Pjust playing around with the lora at the moment
PI've never used a lora before so I'm new to the concept of using one to get accurate results
P
Ppretty insane if you ask me
GHey, 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?
Padd it to the models folder in your stable diffusion main
Pdownload it from huggingface
Pthen move it into your models folder
GThanks, will try that
P
Pinside models you will see Stable-diffusion
Pput it in there
AOkay thank you!
Hcant anyone help me :(
Prealistic 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
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
Pthese were the training settings I used
TCan i see ur original photo?
Pwhich original photo? my dataset?
TYes
TJust few or maybe 2
Tim curios
P
Pand with captions
P
PI plan to build a better dataset with more photos and variety
GDoes 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”
Pwhen 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
GOkay, so what did you have to use instead for better results?
Psince my wife is thai. I used "photo of a thai woman"
TLooks like lora copied perfectly your data set but not doing creativity. Well if that what you want then good for you
GAh okay. And then in your instance prompt did you use something like “ohwx photo of a Thai woman”?
Pit did a great job for a start. now I need to add more images to the dataset and try again. I'm looking for something very flexible.
P
Pstill good tho
Pjust photo of ohwx woman
GThanks so much for your help. Will test it out now
TThats good. Can you please try more like a futuristic look prompts? it feels like i wanna try to go back in khoya lora. Im working wd my dreamboot now, wont give me precise face
