Is that when you don't have pregenerated classification images? There is a new commit on the Dreamb

T

there is a good guide to follow in order to have dreambooth working under windows? i managed to start it, but gives me warnings about cuda setup (with linux path errors)

TThe Elessar [OBOI]there is a good guide to follow in order to have dreambooth working under window...

A

ashleyOP•6/3/23, 9:53 AM

What error are you getting?

Aashley What error are you getting?

T

The Elessar [OBOI]•6/3/23, 9:54 AM

Applying optimization: xformers... done.
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching /usr/local/cuda/lib64...
CUDA SETUP: WARNING! libcuda.so not found! Do you have a CUDA driver installed? If you are on a cluster, make sure you are on a CUDA machine!
CUDA SETUP: Loading binary C:\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cpu.so...
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching /usr/local/cuda/lib64...
CUDA SETUP: WARNING! libcuda.so not found! Do you have a CUDA driver installed? If you are on a cluster, make sure you are on a CUDA machine!
CUDA SETUP: Loading binary C:\A1111\stable-diffusion-webui\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cpu.so...
CUDA SETUP: Problem: The main issue seems to be that the main CUDA library was not detected.
CUDA SETUP: Solution 1): Your paths are probably not up-to-date. You can update them via: sudo ldconfig.
CUDA SETUP: Solution 2): If you do not have sudo rights, you can do the following:
CUDA SETUP: Solution 2a): Find the cuda library via: find / -name libcuda.so 2>/dev/null
CUDA SETUP: Solution 2b): Once the library is found add it to the LD_LIBRARY_PATH: export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:FOUND_PATH_FROM_2a
CUDA SETUP: Solution 2c): For a permanent solution add the export from 2b into your .bashrc file, located at ~/.bashrc
Running on local URL: http://127.0.0.1:7860

TThe Elessar [OBOI]Applying optimization: xformers... done. CUDA_SETUP: WARNING! libcudart.so not f...

A

ashleyOP•6/3/23, 9:55 AM

Is that with CUDA version 12.1 ?

A

ashleyOP•6/3/23, 9:56 AM

bitsandbytes doesn't work properly with 12.1, you have to compile it from source, rather use CUDA 11.8

T

The Elessar [OBOI]•6/3/23, 9:57 AM

looks like i dont' have any CUDA library dev installed, it is that?

A

ashleyOP•6/3/23, 9:57 AM

You need to install a CUDA driver, not sure how to do that for Windows

T

The Elessar [OBOI]•6/3/23, 9:58 AM

found an installer, let's see if this sorts

T

The Elessar [OBOI]•6/3/23, 9:58 AM

thank you

A

ashleyOP•6/3/23, 9:59 AM

Just try 11.8 and not 12.1, 12.1 has alpha features which tend to cause issues and I don't think the bitsandbytes Python module which provides the 8bit Adam optimizer supports it without compiling the module from source.

T

The Elessar [OBOI]•6/3/23, 10:00 AM

yes, i found an archived 11.8 version on nvidia website

NNom how do you mean? Do you mean that you dont get error using class images? Just t...

F

Furkan Gözükara SECourses•6/3/23, 10:13 AM

on runpod currently i am using dev version it is working

Jjulius @Dr. Furkan Gözükara I'm curious after watching a few of your tutorials – what d...

F

Furkan Gözükara SECourses•6/3/23, 10:14 AM

currently i am working on a new workflow. until that time i find dreambooth + realistic vision

F

Furkan Gözükara SECourses•6/3/23, 10:15 AM

looks like time to time we need to delete venv entirely

F

Furkan Gözükara SECourses•6/3/23, 10:15 AM

my previous installation was adding noise to the generated images

F

Furkan Gözükara SECourses•6/3/23, 10:15 AM

new installation didnt make

F

Furkan Gözükara SECourses•6/3/23, 10:19 AM

generated over 5k 768x1024 px class images

F

Furkan Gözükara SECourses•6/3/23, 10:19 AM

also tested different models for realism

F

Furkan Gözükara SECourses•6/3/23, 10:19 AM

and realistic vision is still the best realistic one

F

Furkan Gözükara SECourses•6/3/23, 10:43 AM

there was a github repo which had real photos of real people

F

Furkan Gözükara SECourses•6/3/23, 10:43 AM

do you remember its address

F

Furkan Gözükara SECourses•6/3/23, 11:44 AM

very weird

F

Furkan Gözükara SECourses•6/3/23, 11:44 AM

1 extension is causing defects in image

FFurkan Gözükara SECourses 1 extension is causing defects in image

A

ashleyOP•6/3/23, 11:54 AM

Which extension?

Aashley Which extension?

F

Furkan Gözükara SECourses•6/3/23, 12:08 PM

dont know yet

F

Furkan Gözükara SECourses•6/3/23, 12:08 PM

i have these

F

Furkan Gözükara SECourses•6/3/23, 12:08 PM

F

Furkan Gözükara SECourses•6/3/23, 12:09 PM

preparing the best ever class images dataset

F

Furkan Gözükara SECourses•6/3/23, 12:20 PM

cant find a good model that can properly identify abnormal images :/

F

Furkan Gözükara SECourses•6/3/23, 12:39 PM

maybe i should fetch real images from unsplash

D

David Ce•6/3/23, 2:18 PM

if you get this, is the best thing to do wait or to transfer to another gpu instance

Aashley Is that when you don't have pregenerated classification images? There is a new ...

N

Nom•6/3/23, 2:24 PM

yes I want it to generate class images because I dont have any. DrFurkan said dev is working for him so maybe its just a matter of updating it for the template somehow?

DDavid Ce if you get this, is the best thing to do wait or to transfer to another gpu inst...

A

ashleyOP•6/3/23, 2:31 PM

Depends whether you are able to wait or not, you can try waiting, otherwise transfer your data to another pod if you don't want to wait, because you have no idea how long you will have to wait for a GPU to become available.

DDavid Ce if you get this, is the best thing to do wait or to transfer to another gpu inst...

F

Furkan Gözükara SECourses•6/3/23, 2:31 PM

yes

F

Furkan Gözükara SECourses•6/3/23, 2:31 PM

i decided to collect real images

F

Furkan Gözükara SECourses•6/3/23, 2:31 PM

written script to download from unsplah

F

Furkan Gözükara SECourses•6/3/23, 2:32 PM

can be used even for fine tuning

NNom yes I want it to generate class images because I dont have any. DrFurkan said de...

A

ashleyOP•6/3/23, 2:32 PM

Just pull the dev branch

cd /workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension
git pull

cd /workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension
git pull

cd /workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension
git pull

cd /workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension
git pull

F

Furkan Gözükara SECourses•6/3/23, 2:44 PM

Downloading class images

F

Furkan Gözükara SECourses•6/3/23, 2:45 PM

Aashley Just pull the dev branch ``` cd /workspace/stable-diffusion-webui/extensions/sd_...

N

Nom•6/3/23, 2:47 PM

ok let me try report back

N

Nepper•6/3/23, 3:26 PM

Hello guys!
Got errors on Step 5: pip install -r requirements.txt

F

Furkan Gözükara SECourses•6/3/23, 3:34 PM

i wonder should i train a realistic model for humans :d

NNepper Hello guys! Got errors on Step 5: pip install -r requirements.txt 🤔

F

Furkan Gözükara SECourses•6/3/23, 3:34 PM

that means requirements file is problematic

F

Furkan Gözükara SECourses•6/3/23, 3:34 PM

need to be fixed

F

Furkan Gözükara SECourses•6/3/23, 3:35 PM

before installing you can try this

F

Furkan Gözükara SECourses•6/3/23, 3:35 PM

git checkout 61c8f06c98055b8e0c3ced91ec35a23273bad694

F

Furkan Gözükara SECourses•6/3/23, 3:36 PM

that is a working verison

F

Furkan Gözükara SECourses•6/3/23, 3:36 PM

make a new venv

N

Nom•6/3/23, 3:59 PM

@ashleyk I updated the dev branch and it even has a popup that says fixed class images. But I tried it again, same error @Dr. Furkan Gözükara any ideas?

2023-06-03T15:57:40.583215104Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 729, in start_training
2023-06-03T15:57:40.583220784Z     result = main(class_gen_method=class_gen_method)
2023-06-03T15:57:40.583224064Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 1546, in main
2023-06-03T15:57:40.583227194Z     return inner_loop()
2023-06-03T15:57:40.583229735Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/memory.py", line 119, in decorator
2023-06-03T15:57:40.583246165Z     return function(batch_size, grad_size, prof, *args, **kwargs)
2023-06-03T15:57:40.583249145Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 246, in inner_loop
2023-06-03T15:57:40.583252465Z     count, instance_prompts, class_prompts = generate_classifiers(
2023-06-03T15:57:40.583255115Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/utils/gen_utils.py", line 153, in generate_classifiers
2023-06-03T15:57:40.583257975Z     builder = ImageBuilder(
2023-06-03T15:57:40.583260385Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/helpers/image_builder.py", line 46, in __init__
2023-06-03T15:57:40.583263265Z     self.target = pbar.target
2023-06-03T15:57:40.583265755Z AttributeError: 'mytqdm' object has no attribute 'target'

2023-06-03T15:57:40.583215104Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 729, in start_training
2023-06-03T15:57:40.583220784Z     result = main(class_gen_method=class_gen_method)
2023-06-03T15:57:40.583224064Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 1546, in main
2023-06-03T15:57:40.583227194Z     return inner_loop()
2023-06-03T15:57:40.583229735Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/memory.py", line 119, in decorator
2023-06-03T15:57:40.583246165Z     return function(batch_size, grad_size, prof, *args, **kwargs)
2023-06-03T15:57:40.583249145Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 246, in inner_loop
2023-06-03T15:57:40.583252465Z     count, instance_prompts, class_prompts = generate_classifiers(
2023-06-03T15:57:40.583255115Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/utils/gen_utils.py", line 153, in generate_classifiers
2023-06-03T15:57:40.583257975Z     builder = ImageBuilder(
2023-06-03T15:57:40.583260385Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/helpers/image_builder.py", line 46, in __init__
2023-06-03T15:57:40.583263265Z     self.target = pbar.target
2023-06-03T15:57:40.583265755Z AttributeError: 'mytqdm' object has no attribute 'target'

2023-06-03T15:57:40.583215104Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 729, in start_training
2023-06-03T15:57:40.583220784Z     result = main(class_gen_method=class_gen_method)
2023-06-03T15:57:40.583224064Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 1546, in main
2023-06-03T15:57:40.583227194Z     return inner_loop()
2023-06-03T15:57:40.583229735Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/memory.py", line 119, in decorator
2023-06-03T15:57:40.583246165Z     return function(batch_size, grad_size, prof, *args, **kwargs)
2023-06-03T15:57:40.583249145Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 246, in inner_loop
2023-06-03T15:57:40.583252465Z     count, instance_prompts, class_prompts = generate_classifiers(
2023-06-03T15:57:40.583255115Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/utils/gen_utils.py", line 153, in generate_classifiers
2023-06-03T15:57:40.583257975Z     builder = ImageBuilder(
2023-06-03T15:57:40.583260385Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/helpers/image_builder.py", line 46, in __init__
2023-06-03T15:57:40.583263265Z     self.target = pbar.target
2023-06-03T15:57:40.583265755Z AttributeError: 'mytqdm' object has no attribute 'target'

2023-06-03T15:57:40.583215104Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/ui_functions.py", line 729, in start_training
2023-06-03T15:57:40.583220784Z     result = main(class_gen_method=class_gen_method)
2023-06-03T15:57:40.583224064Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 1546, in main
2023-06-03T15:57:40.583227194Z     return inner_loop()
2023-06-03T15:57:40.583229735Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/memory.py", line 119, in decorator
2023-06-03T15:57:40.583246165Z     return function(batch_size, grad_size, prof, *args, **kwargs)
2023-06-03T15:57:40.583249145Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/train_dreambooth.py", line 246, in inner_loop
2023-06-03T15:57:40.583252465Z     count, instance_prompts, class_prompts = generate_classifiers(
2023-06-03T15:57:40.583255115Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/dreambooth/utils/gen_utils.py", line 153, in generate_classifiers
2023-06-03T15:57:40.583257975Z     builder = ImageBuilder(
2023-06-03T15:57:40.583260385Z   File "/workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension/helpers/image_builder.py", line 46, in __init__
2023-06-03T15:57:40.583263265Z     self.target = pbar.target
2023-06-03T15:57:40.583265755Z AttributeError: 'mytqdm' object has no attribute 'target'

Is that when you don't have pregenerated classification images? There is a new commit on the Dreamb

Similar Threads