Instead of using the base sd xl for training with kohya could we use turbovisionxl for superior trai
Instead of using the base sd xl for training with kohya could we use turbovisionxl for superior trainings?
A@Dr. Furkan Gözükara I'm getting this error when Kaggle training now:
Your notebook tried to allocate more memory than is available. It has restarted.
Your notebook tried to allocate more memory than is available. It has restarted.
Athat was after the first 20%/safetensor
Mfocused on this today and so far this works. 1. Use Kohya to merge either two loras in ckpt or into one lora. 2. In adetailer use detection K of 2 with adetailer prompt similar to: person 1 <lora 1> [SEP] person 2 <lora2> 3. depending on the image generated with two people and which face has a stronger face detection then you may have to switch step 2 to get the proper detailing.
Fcomfy ui manager
Fyou can try and compare
Fyou see 29 gb ram right?
AHave you tried this before? Using something other than base sd xl model
Fhavent had chance yet
AYes 29GB max
Aonly thing I did different this time was use stablediffusionapi/juggernaut-xl-v7
Ainstead of sdxl base
AWhats going on with this yolo script
A
A
DWill give it a try
Dany special argument ? keywords ? etc to be used ? Or ohwx / bbuk woman and man keys will be taken from lora automatically ? I dont want to create a ckpt/safetensor , it will limit my usuage to be used with other good models. I will see if thre is possibility of merging them into one lora for two faces. Or @Dr. Furkan Gözükara is it possible to traing lora for two faces with captions ? That will be easy i guess ?
Bsounds interesting, do you mind sharing your training settings?
7They are not showing Up in comfyui manager
7I have already installed all missing custom nodes from that tab, but still missing these
HI am trying to follow the tutorial on https://www.patreon.com/posts/kohya-sdxl-lora-88397937
when I try to 'start training' I get an output
09:59:46-038102 INFO Start training Dreambooth...
09:59:46-039759 INFO Image folder does not exist
not clear to me which Image folder it doesn't like... here is my inputs and my kaggle file... what am I doing wrong?
when I try to 'start training' I get an output
09:59:46-038102 INFO Start training Dreambooth...
09:59:46-039759 INFO Image folder does not exist
not clear to me which Image folder it doesn't like... here is my inputs and my kaggle file... what am I doing wrong?
DClick on prepare training data firts then copy info to folder
Haha did the trick thank you
DYou are welcome
Hdoes anyone know what might be causing the training to fail?
message.txt2.53KB
Await so, you recreate your UI results with the json api call with 40% succesrate ? SUS
DThe number of images must take at least 30 to catche
DYour catche must be finished inside 30 minutes
DYour training killed in 1577 images catched so resuce your training dataset images to 1550
DHow many training inages in your data set
Eon magic animate i get this error and it stuck like this :
pipeline_animation.py:624: FutureWarning: Accessing config attribute
num_channels_latents = self.unet.in_channels
0%| | 0/25 [00:00<?, ?it/s]
pipeline_animation.py:624: FutureWarning: Accessing config attribute
in_channels directly via 'UNet3DConditionModel' object attribute is deprecated. Please access 'in_channels' over 'UNet3DConditionModel's config object instead, e.g. 'unet.config.in_channels'.num_channels_latents = self.unet.in_channels
0%| | 0/25 [00:00<?, ?it/s]
DDuring extract lora from my checkpoint in kaggle i got error out of memory how to solve the problem and use gpu during the process
HI have 174 images in training dataset, although the regularization I think has 5200? if I re-run will it continue to cache them until it caches them all? or does it start caching from the start each time?
DIt will start catche from 0
Hthe error says 1577/5374 which I think makes sense. 5200 regularization images + 174 of my own training images. not anything to do with my internet upload speed since everything is already uploaded to Kaggle? it still seems quite a low number to timeout at (not even going through all the regularization images)
DReduce your training images to 50
DIt has nothing to do with regulationsimages
DJust reduce your training images to 50
DIf you reduce to 50 images it will do the job for you
Bwhat analysis does your script?
DAnyone will help me with
DWhen i do extract lora from my dreambooth checkpoint error comes that your notebook allocates more memory than available it is not utilising gpu
B1st. I create the payload with UI
2nd. I work on improving the payload, iteratively as described, by adjusting parameters: prompt, noise, CFG, additional scripts, etc.
The project workscope. >100 tuned models; >20 JSON payloads.
So that one payload might work well for a particular model, but poorly for another model.
Success rate (average 40%) - for all models, for all payloads. We generate thousands of images and remove 60%, manually. SD (stand dev) is quite high though. Can be improved, but I don't care that much.
2nd. I work on improving the payload, iteratively as described, by adjusting parameters: prompt, noise, CFG, additional scripts, etc.
The project workscope. >100 tuned models; >20 JSON payloads.
So that one payload might work well for a particular model, but poorly for another model.
Success rate (average 40%) - for all models, for all payloads. We generate thousands of images and remove 60%, manually. SD (stand dev) is quite high though. Can be improved, but I don't care that much.
Bpretty basic statistical analysis: tables with mean and sd
Hhmm reduced to 50 training images, it seems to be timing out at a similar point
message.txt2.42KB
Di used only 13
Deven at 18 it was timing out.. i was training lora sdxl
Dalso check in the argument in kohyass to remove "text_encoder_learner" something
Hshould I try reduce my training images further? (from 50 to 10?) and uncheck "text_encoder_learner"? (where do I find this?) feel like I am missing something fundamental...
D13 with 1024,1024 working good
DAs you are using 512,512 maybe more images around 15 to 20 will also work
