When I extract lora from checkpoint in kohya gui in kaggle allocate more memory errors please help m
When I extract lora from checkpoint in kohya gui in kaggle allocate more memory errors please help me
Ftry to select cpu instead of cuda
Fah you mean in kaggle
Fif you can record that moment i can tell developer to fix
Tthanks. error python.
Bhas anyone used a different base model for sdxl dreambooth training than sdxl base and gotten better results?
DI am using base model sdxl base
ATy for all input, lazy answers are also appriciated. Assume this for understanding:
-> part of this is a1111 specific, what happends if i que it while its running, but not sure how i can force that as a test, locally, or in runpod on the cloud.
-> part of this is runpod specific im assuming, like how the worker in serverless handless extra requests, depending on sync mode or not, but cant find info on that.
-> for admins, maybe this question is annoying, thats ok, i/you can just delete or move it.
-> part of this is a1111 specific, what happends if i que it while its running, but not sure how i can force that as a test, locally, or in runpod on the cloud.
-> part of this is runpod specific im assuming, like how the worker in serverless handless extra requests, depending on sync mode or not, but cant find info on that.
-> for admins, maybe this question is annoying, thats ok, i/you can just delete or move it.
DHas anyone been having issues with the Custom Node "Reactor" in ComfyUI on RunPod?
It keeps crshing each time when I use it, iv updated all the nodes, updated comfy tired unistalling and installing it again via ComfyUi manager but still having the same issue. Log wise all I can see that thee crash occurs when reactor is analysing the source image.
2023-12-06T16:50:39.783388007Z [ReActor] 16:50:39 - STATUS - Working: source face index [0], target face index [0]
2023-12-06T16:50:39.787583130Z [ReActor] 16:50:39 - STATUS - Analyzing Source Image...
It keeps crshing each time when I use it, iv updated all the nodes, updated comfy tired unistalling and installing it again via ComfyUi manager but still having the same issue. Log wise all I can see that thee crash occurs when reactor is analysing the source image.
2023-12-06T16:50:39.783388007Z [ReActor] 16:50:39 - STATUS - Working: source face index [0], target face index [0]
2023-12-06T16:50:39.787583130Z [ReActor] 16:50:39 - STATUS - Analyzing Source Image...
SHello,
I am ML engineer and currently developing image generation engine with sd-1.5 dreambooth lora.
I am trying to train a model with 1 product photo and have some issues to do that.
I am ML engineer and currently developing image generation engine with sd-1.5 dreambooth lora.
I am trying to train a model with 1 product photo and have some issues to do that.
BI never heard someone was successful doing that with only 1 photo
SThis is the example product image.
S
SWhat I am doing is augement background and use them as training data
SAnd I am using diffusers to train dreambooth lora
SCould you tell me hyperparameters for dreambooth lora sd-1.5?
DHave you checked the videos from Furkan he covers many points on Lora and Dreambooth training, following his settings and having a good variety of of you dataset 20images approx and captioning them well then training it on the model that you want to use should give you good results to start with. Also suggest doing via run pod so that the training is quick to test various iterations
SI am using diffusers currently
SHow can I use captions for images when I use diffusers?
SGitHub
Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch - huggingface/diffusers
Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch - huggingface/diffusersSI am currently using this code to train lora model
Zhey boss, any eta on when the video to densepose runpod scripts will bea vailable? @Dr. Furkan Gözükara
MHello everyone! How many images do I have have to put in dataset to train dreambooth kohya as and what length of prompts is optimal to describe images in dataset, what model is better to use to describe images in dataset?
TValueError: Cannot load <class 'magicanimate.models.appearance_encoder.AppearanceEncoderModel'> from F:\AI\ComfyUI_windows_portable\ComfyUI\models\MagicAnimate\densepose_controlnet because the following keys are missing:
....
Please make sure to pass
can u help me. thanks
....
Please make sure to pass
low_cpu_mem_usage=False and device_map=None if you want to randomly initialize those weights or else make sure your checkpoint file is correct.can u help me. thanks
Zwhat's the best cudatoolkit version to use now that is compatible with most of the ai software out there now?
J12.1 or above i think
Ji think most things use 11.8
Jand i have seen some use 12.0
J@Dr. Furkan Gözükara Spam from Hinga.inc
Zi'm a install 11.8
Fwill check messages
Fpreparing kaggle foocus notebook
Lwhat is the fastest way to train reliable checkpoint or lore? i have heared about instant lora and how long does it take?
FGetting super fast speed on sdxl on 4090
FDepends SDXL or SD1.5? for me around 10-15 mins for sd.15 and 30-50 mins on sdxl
Linstant lora just uses ipadapter, it's not actually lora related at all and doesnt yield nearly as good results
Lthats too much
Lyeah i know i saw another video with semilia name , i hoped there would be something faster
Lu know anything faster than that?
Fbest bet is roop or one of those face swappers but quality isnt the best
Lyeah i also want it for animals, pets
Fwhen do you get this error?
Fi am yet to test
Fit is doable. but procudes same pose. i am teaching this with private consultation
Fhopefully today
Fright now making a notebook for foocus on kaggle
Fworking great
Fmostly cuda 11.8
Fcheckpoint best
Fif you need lora extract it
Fwow nice. on windows?
