Thank you so much. let me run it now.
Thank you so much. let me run it now.
Fwill let you know once i finish testing. will update to v25 even with better libraries torch 2.6. testing
Storch.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacity of 14.74 GiB of which 14.12 MiB is free. Process 16031 has 14.72 GiB memory in use. Of the allocated memory 14.26 GiB is allocated by PyTorch, and 344.88 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.
SI'm getting out of memory error
Fi just tested and it works
Feven multi gpu works
Fmake sure your all images are 1024x1024
Flet me update the notebook
F
Ftraining on 2x gpu thus 2x faster 
Fyou can use our configs auto downloaded
F
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
SThanks for the quick response. In my case, I see only one GPU is used. I'll tweak the accelerate launch parameters and try again.
Fyes but single gpu should work too
Fi tested both
Fmake sure all images 1024x1024
Fand using our config
Simages are 1024X1024 only, I'll try again with v25 tomorrow
Sv25 worked. Thanks for the help. But I couldn't use both the gpus, when I've selected multi_gpu and Number of processes=2 it is throwing an error. I ran it with one gpu.
Fon windows not working as far as i know
Fon linux lora works with 48 gb gpus
SI'm running it in kaggle, providing gpu ids as 0,1 worked. I was able to do the training with both the gpus.
Ffor SDXL yes it works
Fon kaggle
SI saved 3 models during the training steps (1 at every 601 steps). apart from these 3, there are 6 models in the same folder namely Kaggle_SDXL_Base_DreamBooth-000001.safetensors. what are these models? can these be used to extract lora from dreambooth models(Kaggle_SDXL_Base_DreamBooth-step00001803.safetensors)
Fyou saved both epoch based
Fand steps based
Sgot it, now I understand why the memory ran out 
SI'm testing the model results, I see in some generated photos the background and clothes of training images are coming up. If I include captions while training, will this issue be resolved?
SHi Dr Furkan, Shaun here. I'm planning to fine-tune an SDXL model checkpoint on a large number of images, hoping to improve its base performance. Some examples are like JuggernautXL , RealVis XL etc. Were they trained using dreambooth as well? Is dreambooth the best method to train a general model? As a lot of the examples of dreambooth seem to be only about training on a specific subject.
Fin inference instead change your prompt
Fdefine them
Fso they wont come
Fdefine something else instead like new background new clothing
Factually if you improve dataset that is best
Fyes they do dreambooth without regularization thus it is fine tuning
Fif you prepare a large enough dataset with proper captions it should work
DWhat ıs the promt?
JHello, I am new to training DreamBooth. May I ask if the Kaggle Notebook on Patreon can be used to train the Illustrious XL model?
SI'm using 13 images now with 4 unique backgrounds and clothes, can you tell me how many images are needed? how many steps should I train? config file has train batch size as 2, should I try train batch size =1. Does it help if I remove the background in the train images?
GOn massive compute, is it possible for dreamboth to access my dataset in a Cloud? Space is too limited on massive compute
Fyes but it may require new hyper parameters
Fkaggle book we have supports SDXL with dual GPU
Fmore better
F13 low
Fi recommend hugging face but you can use any
Fby the way first you have to download