I don't think anything else is using my VRAM, unless it's starting simultaneously. This is right be
I don't think anything else is using my VRAM, unless it's starting simultaneously.
This is right before:
This is right before:
S
SThis is after:
S
CWhat is your favorite SDXL model? 
KJuggernaught
CAlright thx, I checked around civit and gonna test out Realism Engine SDXL and New Reality XL
CDo you know difference of Juggarnaut V7+RunDiffusion and V7 FP16 VAE Fix ?
KNope
KPrecission maybe
KDon't think there is a big difference
OHey guys, I've been trying to train lora SDXL but I seem to always run out of CUDA in runpod, despite not running anything.
My parameters are just like in SEcourse videos, i'm running in 3090 runpod with 24gb vram
My parameters are just like in SEcourse videos, i'm running in 3090 runpod with 24gb vram
O
OI also got Untyped Storage error like this
MAfter a couple of weeks I find that d_coef 0.75 is enough for SD 1.5 Lora prodigy training, but if it is strong, 0.6 helps. You don't need to make it stronger to train persons. This is true for 5 reps for 20 pictures, 4 reps for 25 pictures (20x5=25x4=100).
Bhey, where you get that cuda? i get an error saying i need it
Owhat do you mean? i mean if you use nvidia gpu it already has cuda memory no?
Byea nah i have an AMD Radeon RX 6600XT. if i had an nvidia id probably have less problems
PI tried training on 1.5 in Kohya but it has been performing very slowly. If I discover the settings I will let you know.
Blook up the messages from mikemenders in this channel here, he researched a lot and posted a lot of tipps and configurations for sd 1.5
JHi guys, If I want to create a fictitious person (that does not exist as a base) how should I do? I want to create a model girl
JBecause I learned about creating with a base person, but now I want to create from a fictitious person
DHello everyone, I have a quick question. I'm currently training a stable diffusion model using Kaggle, and I'm wondering about the required resolution for the training images. Do they need to be 1024x1024 pixels? I'm asking because my images are currently 512x512 pixels. I'm looking for clarification on this point,
as suggested by the information in this video: Stable Diffusion Training Guide on YouTube.
as suggested by the information in this video: Stable Diffusion Training Guide on YouTube.
YouTubeSECourses
Master Stable Diffusion XL Training on Kaggle for Free! Welcome to this comprehensive tutorial where I'll be guiding you through the exciting world of setting up and training Stable Diffusion XL (SDXL) with Kohya on a free Kaggle account. This video is your one-stop resource for learning everything from initiating a Kaggle session with dual ...
Master Stable Diffusion XL Training on Kaggle for Free! Welcome to this comprehensive tutorial where I'll be guiding you through the exciting world of setting up and training Stable Diffusion XL (SDXL) with Kohya on a free Kaggle account. This video is your one-stop resource for learning everything from initiating a Kaggle session with dual ...
Dif it a sdxl model, I think you need 1024x1024 images for training
Dwho do you mean by create ? you want to make one picture, a video, a instragram ? If it just one picture, you have multiple way, if you want to make a lot of pic, you probably need to create a lora for you fictional charater
DThanks for the clarification.
JMultiple images, I want to create a real character, a woman.
JNormally, I put 40 real photos of the person as a base, in this case, I have not them because I want to create it, do you understand what I mean?
Dyeah, you want to know how to create food for you future lora
JCorrect, what should I do?
DI think you need first to define the look of you're character and you try to make one good face and one good body
Dthen you use IPadator and reactor to put the face on other situation
Dand then you can create you're food, but you don't really need it, it just create a more simpler workflow (1 lora vs ipa + reactor)
JBut can I create the face from scratch with that or how? I never used it
Dyou can but I think to create you're first face, a good promting with a Sdxl model would be better, execpt if you want some facials features (not sure if it's the right term ^^') like a specific nose you can't get with prompting, then you can use IPa
Dall you really need is one good first face
JOk perfect, then after generated, how many photos should I do to start generating the final ones? 100 200?
Dyou use IPa and reactor to deepfake that face in many picture as possible if you want a lora
Dsince you've got the face, you can juste deepfake it in many pic and said job done
JOk perfect brother thank you
Dthat should help you with IPa, reactor is really for the deepface part
Dmy pleasure, don't forget to ping to show the result ;p
MrealvisXL 2.0 and juggernautXL_v7 - both excellent at human figure and details, no experience with generating other type of art.
Fonly fp16 vs bf16 differs
Fbetween different gpus
Fyes 1 gb is good
Fyou need to start as half precision
Fhello welcome
Fit must be due to you are failing to kill automatically started SD web ui instance