the progressive training weights for TI from the video arent working well for me
the progressive training weights for TI from the video arent working well for me
Fyou don't need TI
Fwit RTX 3090
Fbest one is dreambooth
Ii have dreambooth now
SHello everyone, greetings from Brazil, first of all thank you so much for your incredible work @Furkan Gözükara SECourses and for sharing it.
I'm looking for help, I'm following most recent dreambooth tutorial (and some of the older ones)
I'm trying to run dreambooth on runpod but If i use --share launching webui dreambooth if I don't use it it shows with no problem, am I missing something?
It's disoriating how fast the versions of everything change
I'm looking for help, I'm following most recent dreambooth tutorial (and some of the older ones)
I'm trying to run dreambooth on runpod but If i use --share launching webui dreambooth if I don't use it it shows with no problem, am I missing something?
It's disoriating how fast the versions of everything change
SON a different setup I was trying to run on pytorch 2 and tensor flow linux on aws , i got everything running trough a nginx reverse proxy in a g5.xlarge instance, I got everything running dreambooth always crash mid training, with 24ram avaiable but using less than 10gb of vRAM, anyone who might point me to the right direction?
Ishoot what does this error mean when trying to start TI?
IError completing request
Arguments: ('task(bhgh83d1mzyxyvk)', 'nodnarb', '0.005', 4, 2, 'C:\Users\Brandon\Downloads\elite training', 'textual_inversion', 512, 512, False, 3000, 'disabled', '0.1', True, 0, 'deterministic', False, 25, 50, 'style_filewords.txt', True, False, '', '', 20, 0, 7, -1.0, 512, 512) {}
Traceback (most recent call last):
File "C:\Users\Brandon\stable-diffusion-webui\modules\call_queue.py", line 56, in f
res = list(func(args, **kwargs))
File "C:\Users\Brandon\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(args, *kwargs)
File "C:\Users\Brandon\stable-diffusion-webui\modules\textual_inversion\ui.py", line 33, in train_embedding
embedding, filename = modules.textual_inversion.textual_inversion.train_embedding(args)
File "C:\Users\Brandon\stable-diffusion-webui\modules\textual_inversion\textual_inversion.py", line 417, in train_embedding
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method, varsize=varsize, use_weight=use_weight)
File "C:\Users\Brandon\stable-diffusion-webui\modules\textual_inversion\dataset.py", line 80, in init
filename_text = file.read()
File "C:\Users\Brandon\AppData\Local\Programs\Python\Python310\lib\codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xff in position 0: invalid start byte
Arguments: ('task(bhgh83d1mzyxyvk)', 'nodnarb', '0.005', 4, 2, 'C:\Users\Brandon\Downloads\elite training', 'textual_inversion', 512, 512, False, 3000, 'disabled', '0.1', True, 0, 'deterministic', False, 25, 50, 'style_filewords.txt', True, False, '', '', 20, 0, 7, -1.0, 512, 512) {}
Traceback (most recent call last):
File "C:\Users\Brandon\stable-diffusion-webui\modules\call_queue.py", line 56, in f
res = list(func(args, **kwargs))
File "C:\Users\Brandon\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(args, *kwargs)
File "C:\Users\Brandon\stable-diffusion-webui\modules\textual_inversion\ui.py", line 33, in train_embedding
embedding, filename = modules.textual_inversion.textual_inversion.train_embedding(args)
File "C:\Users\Brandon\stable-diffusion-webui\modules\textual_inversion\textual_inversion.py", line 417, in train_embedding
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method, varsize=varsize, use_weight=use_weight)
File "C:\Users\Brandon\stable-diffusion-webui\modules\textual_inversion\dataset.py", line 80, in init
filename_text = file.read()
File "C:\Users\Brandon\AppData\Local\Programs\Python\Python310\lib\codecs.py", line 322, in decode
(result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xff in position 0: invalid start byte
Iit was working last night
Fhello welcome
Fon unix you need to use torch 1.13 or do some dll linking
Ffor running on runpod you dont have to use share
FYouTubeSECourses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. How to install latest version of Automatic1111 Web UI and #DreamBooth on #RunPod. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
Playlist of #StableDiffusi...
https://www.patreon.com/SECoursesPlaylist of #StableDiffusi...
Fthis one still working
Flooks like txt file reading error
SThank you for your prompt response, I think I missed that one, will look into that and share the results later, thx once again
Fyep this one newest. you are welcome
Ithanks, figured out which one was causing the issue
Zi've noticed that when i do photo of ohwx , the of carries the most weight in daam. Also if i try to use one of my lora models with the epi_noiseoffset lora model, it doesn't even register on the heatmap for daam. Have you seen that before @Furkan Gözükara SECourses
Fi dont think daam is able to utilize lora but not sure
Iok im ready for something better than TI, which tutorial do you recommend?
Ioh nvm found the one from beore
Ioh, is this for a model? i was thinking just a lora
Fok there are several ones
Fyou really should watch this - it is old but it teaches fundamentals
FYouTubeSECourses
Our Discord : https://discord.gg/HbqgGaZVmr. The most advanced tutorial of Stable Diffusion Dreambooth Training. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
Playlist of Stable Diffusion Tutorials, Automatic1111 and Google Colab ...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, Automatic1111 and Google Colab ...
Fthen for installation this one
FYouTubeSECourses
Discord : https://bit.ly/SECoursesDiscord. Torch 2 / Pytorch 2 is now supported along with new DreamBooth Automatic1111 Web UI extension. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
In this video, I am explaining how you can man...
https://www.patreon.com/SECoursesIn this video, I am explaining how you can man...
Fand finally for best settings and configuration this one
FYouTubeSECourses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Web UI DreamBooth got epic update and we tested all new features to find the best settings (10). If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
Playlist of...
https://www.patreon.com/SECoursesPlaylist of...
Ii have dreambooth and torch 2 already
Fok you can skip installation
Fif you also not interested in fundementals
Fjust watch this one
FYouTubeSECourses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Web UI DreamBooth got epic update and we tested all new features to find the best settings (10). If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
Playlist of...
https://www.patreon.com/SECoursesPlaylist of...
Zmy prompt is listed as such - photo,of,ohwx,<lora:Krysta_2000:1>, <lora:epiNoiseoffset_v2:1>
Fi think you can ask the developer but not sure they would answer or not
Zi'll probably play around with the weights and see what happens
Zi erased my negative prompt and now it seems to be working, i swear negative prompts seem to do more tharm than good when it comes to custom lora moddels
Zi used bad-hands5 negative prompt and kept turning her african
Fhaha :d ye sometimes simpler prompts much better
Zcan you explain a little bit how the tokenizer works, and how i can use it to help my prompting?
Zor does it not really matter cause they all get combined anyways
AThis looks amazing 
Zdo you recommend kohya or automatic1111 dreambooth for lora generation? or does it matter?
A@Furkan Gözükara SECourses After a week of struggling to understand and to get things to run and not crash in the middle of training I have finally managed to get some acceptable results. Thanks to your tutorials and advice. Now on to style training...
Zif i write multiple words in my prompt, should i surround them with parenthesis?
Zlike i'm doing an indian, and i wrote "face with intricate warpaint"
JInteresting, just watched the LoRA training guide, there's a lot of talk about Network Rank, it seems that lower network ranks seem to work well for some people, whereas the higher ranks seem preferable in other instances
JI experimented a bit on my face, and I feel the higher network rate is much better, especially for finer details and 'ideas'