I didn’t have any good results with LORA but with the regular dreambooth yes
I didn’t have any good results with LORA but with the regular dreambooth yes
PYeah, I'm really curious to see the results of Dreambooth on a bigger dataset.
�Guys
�i found free image generation ai model with no barriers
�(sometimes)
MA familiar trick. So first you create a "character generator" Lora, which is not flexible, then you use the generated images to create a tagged database and train a flexible Lora.
LThanks I was looking for that
LThis might be a dumb question, if you use dreambooth instead of Lora for the training, is the safetensors still used in the Lora folder like a Lora or the checkpoint folder? Or can you do either? And which is best if so?
G@Dr. Furkan Gözükara thanks for the quick response, Yes the file was acquired from patreon, my patreon emails is different than my discord email: aljohns
(venv) N:\AI\Stable_Diffusion\ClassImages\SECourses\Deepface>python
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>>
(venv) N:\AI\Stable_Diffusion\ClassImages\SECourses\Deepface>python
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>>
PYeah. Sort of. It’s all about efficiency. A good base should not take longer than a day including 2 trainings.
VUdemy also removed access to those that purchased and are offering a refund. Ridiculous.
PSome of you asked for it so I wrote a rather detailed article (warning dry content with no images, just plain detailed insights): https://blib.la/blog/mastering-character-consistency-in-stable-diffusion-sdxl-a-detailed-guide
Creating consistent characters in AI art, especially with tools like Stable Diffusion SDXL, requires a blend of creativity, precision, and the right techniques.
P
PTensor core models seem pointless for batch use...
PNot sure what all the hype is.
VMind adding RSS to your site? Would like to follow the blog.
MSpeaking of keywords, tonight I made a Lora model that I first trained with a keyword that was in the anime models but not (or had little chance of being) in the photo models. It performed relatively well on the photo models, but it confounded the anime models.
I then created a custom keyword from several words and it performed better on both model types.
And one more thing about repetition: I was training poses, and so I didn't use reg images. At first I doubled the number of repetitions, but I got a strong model. After going back to the "100/number of images" formula and using 4 reps instead of 8 (I have 25 images), I got a more flexible model. It was still a bit strong. I trained on Prodigy and 4/4 weights with 0.3 d_coef, I can't go below those values anymore.
I then created a custom keyword from several words and it performed better on both model types.
And one more thing about repetition: I was training poses, and so I didn't use reg images. At first I doubled the number of repetitions, but I got a strong model. After going back to the "100/number of images" formula and using 4 reps instead of 8 (I have 25 images), I got a more flexible model. It was still a bit strong. I trained on Prodigy and 4/4 weights with 0.3 d_coef, I can't go below those values anymore.
MOne more thing about flexibility: I can combine my own loras very well, so I can combine people with poses, styles, and they perform well on several models. A lot of the models that others have made have been so heavily trained that they simply can't be combined, and I'm thinking of generating images with them and re-creating them myself. Plus, some of them are so lousy that it takes tricks to get a good result. I admit I've never been a fan of weighting, because where you have to use a lot of weight, the model doesn't understand what I want. I know anime models love it, but I really find it unnecessary, but sometimes you have to use it for those crappy loras.
Ffull checkpoints goes into model folder and loras goes into lora folder
Fboth has .safetensors extension
Fhello. sorry for late reply. have you fixed your issue?
Fyep 100%. i am still waiting answer from them.
Fi tried only batch size 1 and getting over 70% speed up
G@Dr. Furkan Gözükara No I'm still having the error described above, any advice is greatly appreciated , thanks!
Fi would do this
Funinstall all python
Finstall as shown here
FYouTubeSECourses
Welcome to the Pillars of AI Application Libraries: How to Install Tutorial! 
Are you ready to embark on a journey of installing AI libraries and applications with ease? 
In this video, we'll guide you through the process of installing Python, Git, Visual Studio C++ Compile tools, and FFmpeg on your Windows 10 machine. 
We'll also show you ho...
Are you ready to embark on a journey of installing AI libraries and applications with ease? In this video, we'll guide you through the process of installing Python, Git, Visual Studio C++ Compile tools, and FFmpeg on your Windows 10 machine. We'll also show you ho...Falso install script directly into C drive
Flike c:/deepface
Fpretty sure it will get fixed
Gok I'll give that a try after my next checkpoint finishes
Gand report back, thanks
Fyour error
Findicating that
FFile "N:\AI\Stable_Diffusion\ClassImages\SECourses\Deepface\venv\lib\site-packages\tensorflow\python\tf2.py", line 21, in <module>
from tensorflow.python.platform import _pywrap_tf2
ImportError: DLL load failed while importing _pywrap_tf2: A dynamic link library (DLL) initialization routine failed.
from tensorflow.python.platform import _pywrap_tf2
ImportError: DLL load failed while importing _pywrap_tf2: A dynamic link library (DLL) initialization routine failed.
Fi will also now do a fresh install to test
Falso you installed install-gpu.bat right?
Fand using
FfindBestImagesV4.py
F
Gumm hmmmmmmmmmmm
Glet me check
GNo I don't think I did
GI only followed the 1 oct 2023 update so that's my mistake
GDo I need to start over (i.e. with find best images)
Gor can I just run the install-gpu.bat and it may fix it?
Fi would do a fresh install
Fit is working
Falso give a full folder path