added the train.py file
added the train.py file
train.py19.47KB
Flooks like number of training samples and testing samples are not accurate
Fhow many you have did you check?
M6 vram
Fyes 6 may not be sufficient :/
Fi can make a notebook for kaggle i think
Fare you my patreon subscriber?
Mlive in iran cant use paypal or something like that our banks are bloked ( live in sanction )
Fyou can purchase udemy i think?
Mif i want to buy them which i have to use iranian websites which is not from real srouce so money wont reach to the real maker , they also selling them cheaper or even free in some websites and it is not ok i think this is all pirates
DI tried one minute audio sample it didn't work then I tried 10 minutes samples that also didn't work,
in 1 minute audio trained data is empty , 10 minutes sample I can see only few lines in it
in 1 minute audio trained data is empty , 10 minutes sample I can see only few lines in it
Fi used 2 hours training data
Di only have less data files, is it possible to do from small files ?
F2 hours data is split into small files
Fhow many small files you have
Di have only one minute clip , and other file have 10 minute clip (this ten minute clip I merged multiple files into one using audacity)
Fi think that is why
Fprobably you need minimum 10 training data
GWhat's the current best way to generate yourself in images? SDXL or 1.5? Dreambooth or LORA?
GAlso, can a model of yourself have both your entire body and face accurately? Or does model face quality reduce if you include your whole body?
Fsdxl dreambooth is undisputedly best
Fwe use adetailer and face details are still good
GAwesome, thanks for the info. I am new to SD. Is it possible to run SDXL Dreambooth on a 3060 12GB GPU or will I only be able to do a LORA?
Fyou can do sdxl drembooth on kaggle possibly. right now testing it
Fotherwise yes only lora
GOkay, thanks! 
GI'll try LORA first
NHi @Furkan Gözükara SECourses I just came from your YouTube video on dolly 2.0 can you please help me with an error
NValueError: The current
device_map had weights offloaded to the disk. Please provide an offload_folder for them. Alternatively, make sure you have safetensors installed if the model you are using offers the weights in this format.Fwhat is your GPU?
N
Fye probably you cant use with that
FGitHub
A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, llama.cpp (GGUF), Llama models. - GitHub - oobabooga/text-generation-webui: A Gradio web UI for Large Language Models. S...
NIs this shown in the video from 8:55?
Fno this is not shown in video
NDo you have a video on how this works ?
Fnot yet but will do hopefully
NThank you very much for help 
G
G
GI'm using 45 training images and multiplying by 25 for regularization like in the tutorial. Too many training images?
GOkay it's down to 29 hours estimated now
Ai discovered something pretty cool @Furkan Gözükara SECourses
While playing around with animateDiff, I was trying to trigger the camera words but did it wrong and instead of typing in the zoom in trigger word, I typed it in wrong and noticed the subject moving forward instead....
SO i thought, hey its prompting action words!!! So i prompted "running" and she ran.
Made me wonder how we can train action words?
While playing around with animateDiff, I was trying to trigger the camera words but did it wrong and instead of typing in the zoom in trigger word, I typed it in wrong and noticed the subject moving forward instead....
SO i thought, hey its prompting action words!!! So i prompted "running" and she ran.
Made me wonder how we can train action words?
A
DHello, anyone getting good results with voice cloning?
Fdepends on image quality
Fwith action images and action captions
FYouTubeSECourses
Today, we're going to dive into the cutting-edge world of voice cloning and speech synthesis, a technology that has the potential to revolutionize communication as we know it. We're going to make use of TorToiSe TTS, an incredibly powerful yet user-friendly open-source tool for training and generating speech. And the best part? With TorToiSe TTS...
GThanks. Estimate now is ending up at only 14 hours or so, down from 60.
Image quality is all good. I selected best from a set I took with a DSLR w/ 50mm
Image quality is all good. I selected best from a set I took with a DSLR w/ 50mm
DThanks! Does it give good results? I tried few and was not able to get consistent results, I dont know how evenlabs do it