@Dr. Furkan Gözükara can you explain why you are using a vae in your latest sdxl dreambooth training
@Dr. Furkan Gözükara can you explain why you are using a vae in your latest sdxl dreambooth training config?
B"vae": "stabilityai/sdxl-vae"
Dalso Jpeg / PNG , i saw in one of your comment that to convert jpeg to PNG in case there are errors . training better with jpeg or png ?
DAlso since kaggle gives 20Gb , for lora training , do we need to stop and deleted the regul folder once its gets copied into results ? this step can be skipped , so that we dont mess with the lora training setting ?
DI am getting error when trying to paste the training command
accelerate launch --num_cpu_threads_per_process=4 "./sdxl_train_network.py" --pretrained_model_name_or_path="stabilityai/stable-diffusion-xl-base-1.0" --train_data_dir="/kaggle/working/results/img" --reg_data_dir="/kaggle/working/results/reg" --resolution="1024,1024" --output_dir="/kaggle/working/results/model" --logging_dir="/kaggle/working/results/log" --network_alpha="1" --save_model_as=safetensors --network_module=networks.lora --text_encoder_lr=0.0004 --unet_lr=0.0004 --network_dim=64 --output_name="Lora_Gowthu" --lr_scheduler_num_cycles="8" --no_half_vae --learning_rate="0.0004" --lr_scheduler="constant" --train_batch_size="1" --max_train_steps="7200" --save_every_n_epochs="1" --mixed_precision="fp16" --save_precision="fp16" --cache_latents_to_disk --optimizer_type="Adafactor" --optimizer_args scale_parameter=False relative_step=False warmup_init=False weight_decay=0.01 --max_data_loader_n_workers="0" --bucket_reso_steps=64 --save_every_n_steps="1300" --mem_eff_attn --gradient_checkpointing --full_fp16 --xformers --bucket_no_upscale --noise_offset=0.0 --max_grad_norm=0.0 --no_half_vae --train_text_encoder --vae="stabilityai/sdxl-vae"
accelerate launch --num_cpu_threads_per_process=4 "./sdxl_train_network.py" --pretrained_model_name_or_path="stabilityai/stable-diffusion-xl-base-1.0" --train_data_dir="/kaggle/working/results/img" --reg_data_dir="/kaggle/working/results/reg" --resolution="1024,1024" --output_dir="/kaggle/working/results/model" --logging_dir="/kaggle/working/results/log" --network_alpha="1" --save_model_as=safetensors --network_module=networks.lora --text_encoder_lr=0.0004 --unet_lr=0.0004 --network_dim=64 --output_name="Lora_Gowthu" --lr_scheduler_num_cycles="8" --no_half_vae --learning_rate="0.0004" --lr_scheduler="constant" --train_batch_size="1" --max_train_steps="7200" --save_every_n_epochs="1" --mixed_precision="fp16" --save_precision="fp16" --cache_latents_to_disk --optimizer_type="Adafactor" --optimizer_args scale_parameter=False relative_step=False warmup_init=False weight_decay=0.01 --max_data_loader_n_workers="0" --bucket_reso_steps=64 --save_every_n_steps="1300" --mem_eff_attn --gradient_checkpointing --full_fp16 --xformers --bucket_no_upscale --noise_offset=0.0 --max_grad_norm=0.0 --no_half_vae --train_text_encoder --vae="stabilityai/sdxl-vae"
D2023-11-26 10:40:23.363084: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2023-11-26 10:40:23.363138: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2023-11-26 10:40:23.363201: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2023-11-26 10:40:23.366439: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2023-11-26 10:40:23.366486: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2023-11-26 10:40:23.366538: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
/opt/conda/lib/python3.10/site-packages/scipy/init.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.24.3
warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
/opt/conda/lib/python3.10/site-packages/scipy/init.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.24.3
warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
usage: sdxl_train_network.py [-h] [--v2] [--v_parameterization]
[--pretrained_model_name_or_path PRETRAINED_MODEL_NAME_OR_PATH]
2023-11-26 10:40:23.363138: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2023-11-26 10:40:23.363201: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2023-11-26 10:40:23.366439: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2023-11-26 10:40:23.366486: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2023-11-26 10:40:23.366538: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
/opt/conda/lib/python3.10/site-packages/scipy/init.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.24.3
warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
/opt/conda/lib/python3.10/site-packages/scipy/init.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.24.3
warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
usage: sdxl_train_network.py [-h] [--v2] [--v_parameterization]
[--pretrained_model_name_or_path PRETRAINED_MODEL_NAME_OR_PATH]
D
Dam i doing something wrong ?
Dfor some weird reason it worked when i used your setting , but now its failing .. 
DDok hitting "start training" within koayaa_gui seems to work. When we copy the code - stop the code- remove the folder - paster the code - start the code from kaggle ,doesnt seems to work
Dsdxl_train_network.py [-h] [--v2] [--v_parameterization] this .py doesnt seem to get started when we execute the training command separately.
FHello, guys, Now I'm looking for someone who is experienced in .Net. (US, UK prefered, Fluent English Level, European or American). Please DM if anybody is interested in.
Dgot stuck at point and had to restart.. Have to reinstall fully ? Is there a way to retain all the files/setups ? before i come to hit the train button ,gpu time of 1 hour is lost..
Is there a way to retain all the files/setups ? before i come to hit the train button ,gpu time of 1 hour is lost.. Datlast... 1st epoch finished
DNow i think why dreambooth training could have failed.. I think hitting train within the koyaa GUI works better on kaggle , rather than executing the same code from notebook. After the lora gets created , tomorrow will try once more to train on dreambooth.
S@Dr. Furkan Gözükara Hello will you create anytime soon Stable diffusion video generator tutorial? Or img to video?
Nhello, i get this error in my log
Ni'm using xl model with xl controlnet
Dits late night now , can i leave kaggle running and just keep browser and pc running ?
Dits now 50% over with 7 epochs generated
Dstill 9 to go .. 3.3hrs remaining
Dhelp
Fnow you can directly run from gui
Fno need to stop
Fwe are embedding very best vae into the model
Fhopefully planning soon
Fwhich automatic111 are you using?
Fif you are using dreambooth extension version it is an old version
Fyes you can
Fbut max 12 hour is per session i think
Fjust leave kaggle window open
Fyou cna stop training and download checkpoints
Fbefore going to sleep
DSet alarm, just woke up, it's 3am now.. Downloaded all loras. Tom will do xyz of all loras, and see which is good.
Will give dreambooth training one more try. Have only 10 hours of gpu time.
Once again thanks a lot @Dr. Furkan Gözükara .thanks for replying for each of our messages..
Will give dreambooth training one more try. Have only 10 hours of gpu time.
Once again thanks a lot @Dr. Furkan Gözükara .thanks for replying for each of our messages..
DGn guys
![Digital [Starburst]](https://cdn.discordapp.com/avatars/220961909447458817/8ecbbb3132fc6e44312f3d6d2ae3df69.webp?size=40)
DI learned something about using ControlNet with SDXL. Not every option in ControlNet has an SDXL model. I suspect that is why some say that ControlNet is only partially compatible with SDXL.
![Digital [Starburst]](https://cdn.discordapp.com/avatars/220961909447458817/8ecbbb3132fc6e44312f3d6d2ae3df69.webp?size=16)
Faccurate
Fyou need to have XL in the name of the selected model
Fclass images datasets updated : https://civitai.com/articles/2285/massive-4k-resolution-woman-and-man-class-ground-truth-stable-diffusion-regularization-images-dataset
Download link > https://www.patreon.com/posts/87700469 The best ever released Stable Diffusion classification / regularization images dataset ju...
ZWhat's the best way to upscale human photos to get the best detail?
DJust need a clarification, if we stop training midway, can we continue again?
Also how can we prevent installing from the start for each notebook we create on kaggle or any platform?
In case we can preserve the setup, we can simply go and change, say, the training images, and simply hit train.. Last time on runpod, it was consuming space, so I was loosing money.
I
Also how can we prevent installing from the start for each notebook we create on kaggle or any platform?
In case we can preserve the setup, we can simply go and change, say, the training images, and simply hit train.. Last time on runpod, it was consuming space, so I was loosing money.
I
DFor those who get Automatic1111 stuck in cmd , here is the solution : https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/2452
TLDR : Just go to properties of CMD and uncheck "Quick Edit Mode"
TLDR : Just go to properties of CMD and uncheck "Quick Edit Mode"
GitHub
No error when this happen In Windows, i noticed some recently version have this problem, when i set hundred to thousand batch count, it just stucked random at batch xx (sometime at batch 2, sometim...
FOpenModelDB
OpenModelDB is a community driven database of AI Upscaling models. We aim to provide a better way to find and compare models than existing sources.
Fyou can continue by starting a new training from last checkpoint as a base model
Fi always mention this in tutorials hit enter if you see cmd stuck 
Fi got huge results with llava
Fwhen training a style
Djust did a massive x/y/z plot with various models :
- Some lora`s are bad independent of which epoch it is (higher)
- Even starting Epochs are good sometimes .
- Each models(from civitai) produce different face with different Lora/epoch.
Dwhere should we use the checkpoint ? ok , dont want to go into that , may be it will be useful for someone.. , dont want to waste your time.
I and many would love if you can do a detailed explanation on Automatic1111 , because i feel there is loads of potential / tinkering to be done on it.. and also on absolute necessary extension , for eg adetailer ,
I and many would love if you can do a detailed explanation on Automatic1111 , because i feel there is loads of potential / tinkering to be done on it.. and also on absolute necessary extension , for eg adetailer ,