I'm using it now and so far is working! Thanks!

RRclemente27 I'm using it now and so far is working! Thanks!

F

Furkan Gözükara SECourses•6/1/23, 10:30 PM

yep

Ccode hey looks like it works ``` [!] xformers NOT installed. [+] torch version 2.0.1+...

F

Furkan Gözükara SECourses•6/1/23, 10:30 PM

nice

C

code•6/1/23, 10:39 PM

One quick question, is there currently a updated config on what to use, everything seems to be months old.

Trying to train objects

Ccode One quick question, is there currently a updated config on what to use, everythi...

F

Furkan Gözükara SECourses•6/1/23, 11:15 PM

yes i explained in this video best settings : https://youtu.be/sRdtVanSRl4

F

Furkan Gözükara SECourses•6/1/23, 11:15 PM

i plan to make a new video when dev branch merged into main

N

Nom•6/2/23, 2:03 AM

anyone here know how to make class images work with the dev branch of dreambooth? It currently gives this error

  File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 729, in start_training
2023-06-02T02:02:02.775039785Z     result = main(class_gen_method=class_gen_method)
2023-06-02T02:02:02.775041455Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 1546, in main
2023-06-02T02:02:02.775043305Z     return inner_loop()
2023-06-02T02:02:02.775044975Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/memory.py", line 119, in decorator
2023-06-02T02:02:02.775052425Z     return function(batch_size, grad_size, prof, *args, **kwargs)
2023-06-02T02:02:02.775054175Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 246, in inner_loop
2023-06-02T02:02:02.775055935Z     count, instance_prompts, class_prompts = generate_classifiers(
2023-06-02T02:02:02.775057635Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/utils/gen_utils.py", line 153, in generate_classifiers
2023-06-02T02:02:02.775059405Z     builder = ImageBuilder(
2023-06-02T02:02:02.775060995Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/helpers/image_builder.py", line 46, in __init__
2023-06-02T02:02:02.775062715Z     self.target = pbar.target
2023-06-02T02:02:02.775064365Z AttributeError: 'mytqdm' object has no attribute 'target'

  File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 729, in start_training
2023-06-02T02:02:02.775039785Z     result = main(class_gen_method=class_gen_method)
2023-06-02T02:02:02.775041455Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 1546, in main
2023-06-02T02:02:02.775043305Z     return inner_loop()
2023-06-02T02:02:02.775044975Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/memory.py", line 119, in decorator
2023-06-02T02:02:02.775052425Z     return function(batch_size, grad_size, prof, *args, **kwargs)
2023-06-02T02:02:02.775054175Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 246, in inner_loop
2023-06-02T02:02:02.775055935Z     count, instance_prompts, class_prompts = generate_classifiers(
2023-06-02T02:02:02.775057635Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/utils/gen_utils.py", line 153, in generate_classifiers
2023-06-02T02:02:02.775059405Z     builder = ImageBuilder(
2023-06-02T02:02:02.775060995Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/helpers/image_builder.py", line 46, in __init__
2023-06-02T02:02:02.775062715Z     self.target = pbar.target
2023-06-02T02:02:02.775064365Z AttributeError: 'mytqdm' object has no attribute 'target'

  File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 729, in start_training
2023-06-02T02:02:02.775039785Z     result = main(class_gen_method=class_gen_method)
2023-06-02T02:02:02.775041455Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 1546, in main
2023-06-02T02:02:02.775043305Z     return inner_loop()
2023-06-02T02:02:02.775044975Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/memory.py", line 119, in decorator
2023-06-02T02:02:02.775052425Z     return function(batch_size, grad_size, prof, *args, **kwargs)
2023-06-02T02:02:02.775054175Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 246, in inner_loop
2023-06-02T02:02:02.775055935Z     count, instance_prompts, class_prompts = generate_classifiers(
2023-06-02T02:02:02.775057635Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/utils/gen_utils.py", line 153, in generate_classifiers
2023-06-02T02:02:02.775059405Z     builder = ImageBuilder(
2023-06-02T02:02:02.775060995Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/helpers/image_builder.py", line 46, in __init__
2023-06-02T02:02:02.775062715Z     self.target = pbar.target
2023-06-02T02:02:02.775064365Z AttributeError: 'mytqdm' object has no attribute 'target'

  File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 729, in start_training
2023-06-02T02:02:02.775039785Z     result = main(class_gen_method=class_gen_method)
2023-06-02T02:02:02.775041455Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 1546, in main
2023-06-02T02:02:02.775043305Z     return inner_loop()
2023-06-02T02:02:02.775044975Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/memory.py", line 119, in decorator
2023-06-02T02:02:02.775052425Z     return function(batch_size, grad_size, prof, *args, **kwargs)
2023-06-02T02:02:02.775054175Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 246, in inner_loop
2023-06-02T02:02:02.775055935Z     count, instance_prompts, class_prompts = generate_classifiers(
2023-06-02T02:02:02.775057635Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/utils/gen_utils.py", line 153, in generate_classifiers
2023-06-02T02:02:02.775059405Z     builder = ImageBuilder(
2023-06-02T02:02:02.775060995Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/helpers/image_builder.py", line 46, in __init__
2023-06-02T02:02:02.775062715Z     self.target = pbar.target
2023-06-02T02:02:02.775064365Z AttributeError: 'mytqdm' object has no attribute 'target'

C

code•6/2/23, 4:12 AM

With my 4090 and torch 2 it takes around ~50 seconds to generate two x 2048x1024
With xformers and torch 1 it takes 16 seconds.

Not even comparable.

R

Rclemente27OP•6/2/23, 4:44 AM

So I'm still watching this tutorial and in the minute 8:15 he selects a model from a folder call "0 models". But I don't have it. Do you know how can I get those models? https://www.youtube.com/watch?v=TpuDOsuKIBo

YouTubeSECourses

Generate Studio Quality Realistic Photos By Kohya LoRA Stable Diffu...

#Kohya SS web GUI DreamBooth #LoRA training full tutorial. You don't need technical knowledge to follow this tutorial. In this tutorial I have explained how to generate professional photo studio quality portrait / self images for free with Stable Diffusion training.

Our Discord server

https://bit.ly/SECoursesDiscord

If I have been of assis...

Fflowwolf terminal > make sure no venv is active > `cd \kohya_ss\ [whereever it is]` `pi...

▲

▲•6/2/23, 4:49 AM

thanks i'm gonna try this, cause i havent solved yet

▲

▲•6/2/23, 4:50 AM

however, beware of latest nvidia driver update. it slow down my SD to terrible speed

▲

▲•6/2/23, 4:50 AM

i had to roll back driver

RRclemente27 So I'm still watching this tutorial and in the minute 8:15 he selects a model fr...

▲

▲•6/2/23, 4:54 AM

there's plenty of models on hugginface or civitAI

▲▲however, beware of latest nvidia driver update. it slow down my SD to terrible s...

F

flowwolf•6/2/23, 5:11 AM

is fine here

Fflowwolf is fine here

▲

▲•6/2/23, 5:21 AM

runned your code
had to choose "yes" to tons of question on uninstall
reinstalled
still not working
i dunno what to do anymore

FFurkan Gözükara SECourses testing your template @ashleyk right now

A

ashley•6/2/23, 5:23 AM

How did it go?

▲

▲•6/2/23, 5:23 AM

not only, now my stable diffusion runs at 1/its

▲

▲•6/2/23, 5:24 AM

i guess i shut off my computer for today and go to ride my bycicle in nature

S

shameforest•6/2/23, 6:18 AM

Hey Guys!
Do you recommend any good tips, workflows or strategies on how to create specific graphic novel framing and images? Not on an amateur level, just creating some random comic images, but with specific camera framing and characters with specific facial expressions, etc?
If you have any ideas or material to recommend, that would be very helpful. Thanks!

E

Enlil Wolf•6/2/23, 11:16 AM

Hey there guys, anyone here facing any issues where you have already uploaded pre-set classification images but Dreambooth starts to create a batch of new images? It shouldn't be happening as the process itself is so slow.

EEnlil Wolf Hey there guys, anyone here facing any issues where you have already uploaded pr...

A

ashley•6/2/23, 11:28 AM

That happens when your directory to the classification images is incorrect

A

ashley•6/2/23, 11:29 AM

Check that you never made a tying error when entering it

F

felixsanz•6/2/23, 11:39 AM

@Dr. Furkan Gözükara haven't you find that training a face on realistic vision model is usually a very bad idea? i don't know if i'm doing it wrong, etc. but my results are horrible always

Aashley How did it go?

F

Furkan Gözükara SECourses•6/2/23, 11:46 AM

it asked password to connect jupyter i did a new installation :d

Ffelixsanz @Dr. Furkan Gözükara haven't you find that training a face on realistic vision m...

F

Furkan Gözükara SECourses•6/2/23, 11:47 AM

i am working on a new workflow

F

Furkan Gözükara SECourses•6/2/23, 11:47 AM

generated over 8k 768x1024 class images. trying to remove nsfw automatically haha

F