tested dreambooth but its like 75gb vram for decent quality
tested dreambooth but its like 75gb vram for decent quality
Fthere are so many optimizations 75gb dreambooth sounds too extreme 
Fi expect under 24 gb
Shi guys, just subscribed to patreon page to train my lora. Downloaded the given zip file, start Windows_Install_Step_1 and getting bunch of errors
S'pip' is not recognized as an internal or external command, same for python and git. Do I need to install something before I run this Windows_Install_Step_1.bat?
Fyes you are missing requirements
SI found out that I need python and in the video you say to use version 3.10, but it is no longer available on the python official webiste
Fwatch without skip please
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...
Syes, I'm wathcing it right now and there you recommend python version 3.10.x
F
Ffirst test of trained style :
Lis there any updates as to whether or not to install torch 2.5 dev on windows for that speed boost in terms of errors and / or quality?
L@Dr. Furkan Gözükara
Fyes install it for 24 gb cards
Fand 16 gb cards
Ffor single layers i didnt see much improvement
Falso 2.4.1 is about to get published
Fofficially
LOk, I've got a 24gb card so I'm installing it, thanks. Will I need to run a manual update command when it is published? Or will a kohya update or one of your custom bat update files cover this?
Fi will update my file
LExcellent
LThanks
Fyou are welcome
Fstyle training results early tests are amazing
Fit learnt the style very well with captions
Fjoy captions
ZI am trying to train a Flux-style Lora; one thing I wanna ask is whether I still can use the same rank 5 configuration files for 16GB GPU RAM?
Fyes you can use
Falso check the dataset of captions here
Fit really works well generating grid
ZThanks! Can not wait for your style training tutorial!
Dwdym only unet? are you trying to finetune t5?
�Thanks for showing us your process of using the Grid Generator tool in SwarmUI for Lora testing in the latest video @Dr. Furkan Gözükara I think the problem I was having with generating grids was because I was loading 40 Loras at once lol. It was all my saved checkpoints from a training session. Do you think it's even possible to load that many at once or do you think it's a limitation from Swarm or maybe VRAM? I was using the A6000 so I thought it would be able to handle it
Sso I installed python, git, cuda, now again running Windows_Install_Step_1.bat and it says ERROR: could not find a version that satisfies with the requirement xformers==0.0.27.post2 (from versions: none). Please help, there was no xformers in the tutorial, do I need to download it separately?
Sit comes with stable-diffusion-webui, but I downloaded it as shown in the video tutorial
Fsadly i dont know you can ask to swarmui developer
Fcontinue step 2
Fit fixes it
Ldo you know if joy captions happens to apply some sort of automatic 'shuffling' with it's descriptions? Or would applying shuffling be a seperate step?
Sthank you!
Fkohya has it
L@Dr. Furkan Gözükara Did you use bucketing enabled with your style training? I remember you talking about it but I don't remember where you talked about it.
L(I think you said it hurt the quality of the result in the case of getting a person's likeness but I don't think there was a consensus on styles)
Fwas 1024x1024
Fgrid is being generated
LGreat I'll keep it off for mine and stick to 1024, thank you!