Software Engineering Courses (SECourses)•3y ago

@Dr. Furkan Gözükara I figured out that noise issue from the other day. My learning rate was way too

@Dr. Furkan Gözükara I figured out that noise issue from the other day. My learning rate was way too high! Thought I was using 1e-5, but turns out it was 4e-4.

SuperTurboHero•10/13/23, 11:51 AM

Silly question. How do I enter Yes to continue in Kaggle?

SuperTurboHero•10/13/23, 11:51 AM

It's not like CMD

stillmotionOP•10/13/23, 11:53 AM

@superturbohero try adding the -y flag to apt install

stillmotionOP•10/13/23, 11:53 AM

apt install -y ...apt install -y ...

SuperTurboHero•10/13/23, 11:55 AM

ok. i see that helped

thanks

BBenjamin it's what I do to be on the safe side. As @Dr. Furkan Gözükara mentioned or else...

Furkan Gözükara SECourses•10/13/23, 12:04 PM

well persistence not working very good but can be tried

Tt800se when you say checkpoints, do you mean downloading created files from the browser...

Furkan Gözükara SECourses•10/13/23, 12:04 PM

yes

Tt800se I assume they are the .safetensors files:

Furkan Gözükara SECourses•10/13/23, 12:04 PM

yes

Sstillmotion @Dr. Furkan Gözükara I figured out that noise issue from the other day. My learn...

Furkan Gözükara SECourses•10/13/23, 12:05 PM

accurate

Furkan Gözükara SECourses•10/13/23, 12:05 PM

it cooks the model

Furkan Gözükara SECourses•10/13/23, 12:05 PM

so you get noise output

SSuperTurboHero Silly question. How do I enter Yes to continue in Kaggle? 😄

Furkan Gözükara SECourses•10/13/23, 12:05 PM

i updated the notebook on patreon

Furkan Gözükara SECourses•10/13/23, 12:05 PM

use latest one

FFurkan Gözükara SECourses check out this video : https://youtu.be/PNA9p94JmtY

Elisoli•10/13/23, 12:20 PM

Think we can use this as captions for training photos?

SuperTurboHero•10/13/23, 12:49 PM

How do you guys train SDXL models? With Kohya_ss? Or with Dreambooth extension for Automatic1111?

EElisoli Think we can use this as captions for training photos?

Furkan Gözükara SECourses•10/13/23, 2:09 PM

yes

SSuperTurboHero How do you guys train SDXL models? With Kohya_ss? Or with Dreambooth extension f...

Furkan Gözükara SECourses•10/13/23, 2:09 PM

with kohya

tita6070•10/13/23, 2:34 PM

Hi, I have a issue with my automatic1111, it says that Torch is not able to use GPU and propose to skip it, how can I fix it? Thanks a lot

tita6070•10/13/23, 2:34 PM

I want to use it for the wav2lip extension

thesilvermoth•10/13/23, 3:26 PM

Hello @Dr. Furkan Gözükara I have a question about Kohya. If I want to use the scheduler cosine_with_restarts, how do I set the restarts? I is something like this? "lrSchedulerNumCycles": 3

iloveh8•10/13/23, 4:49 PM

can we create a video by 'looping' GPT4V and DALL-3 'recursively'

Zono50•10/13/23, 5:32 PM

anyone use comfyui and reactor? some reason I'm always getting blurry faces

Zono50•10/13/23, 5:33 PM

and i can get good looking faces in automatica1111, but not sure why I can't in comfy

virginia•10/13/23, 6:20 PM

Furkan's kaggle notebook for training is pretty good.

FFurkan Gözükara SECourses yes

Stefanoid9343•10/13/23, 9:14 PM

How much the training improve with the caption?

Stefanoid9343•10/13/23, 9:14 PM

I’m planning to train logos

Ttita6070 Hi, I have a issue with my automatic1111, it says that Torch is not able to use ...

Furkan Gözükara SECourses•10/13/23, 10:45 PM

what is your gpu

Tthesilvermoth Hello @Dr. Furkan Gözükara I have a question about Kohya. If I want to use the s...

Furkan Gözükara SECourses•10/13/23, 10:46 PM

i am not sure never used

Furkan Gözükara SECourses•10/13/23, 10:46 PM

but if you do that

Furkan Gözükara SECourses•10/13/23, 10:46 PM

follow LR during training

Furkan Gözükara SECourses•10/13/23, 10:46 PM

use wandb

Iiloveh8 can we create a video by 'looping' GPT4V and DALL-3 'recursively'

Furkan Gözükara SECourses•10/13/23, 10:46 PM

probably not. not very accurate for that

SStefanoid9343 How much the training improve with the caption?

Furkan Gözükara SECourses•10/13/23, 10:47 PM

i am in still research

Furkan Gözükara SECourses•10/13/23, 10:47 PM

for a very poor game character

Furkan Gözükara SECourses•10/13/23, 10:47 PM

i got quite decent

Furkan Gözükara SECourses•10/13/23, 10:47 PM

but i will test on myself later

Furkan Gözükara SECourses•10/13/23, 10:47 PM

this is for a client currently i am testing

vp•10/14/23, 12:54 AM

I’m seeing your comment on Github re LLaVA req for venv installer. Did you succeed?

FFurkan Gözükara SECourses i am in still research

Stefanoid9343•10/14/23, 2:57 AM

Thank you!

mayna•10/14/23, 10:26 AM

Hi all, Anyone know how this can be solved please while training on KOhya SS

wandb: ERROR The API key you provided is either invalid or missing. If the WANDB_API_KEYWANDB_API_KEY environment variable is set, make sure it is correct. Otherwise, to resolve this issue, you may try running the 'wandb login --relogin' command. If you are using a local server, make sure that you're using the correct hostname. If you're not sure, you can try logging in again using the 'wandb login --relogin --host [hostname]' command.(Error 401: Unauthorized)

mayna•10/14/23, 10:27 AM

where to run wandb login --relogin ?

FFurkan Gözükara SECourses what is your gpu

tita6070•10/14/23, 10:36 AM

RTX 3060

mayna•10/14/23, 1:32 PM

anyone know how to pause resume a trainign ? been running for 3h still 3h ..

mayna•10/14/23, 1:32 PM

my machine is burning

FFurkan Gözükara SECourses yes

Elisoli•10/14/23, 1:37 PM

This only use RAM and not gpu? when using the model you use on the video (the advance one) - it takes about 1 hour per image, does that make sense?

Elisoli•10/14/23, 1:37 PM

3060 gpu, 64gm ram

iloveh8•10/14/23, 4:07 PM

havent seen any real example that produces good video, any suggestion for very specific use case that has higher chance of success - video looks really good? this is for ecommerce use case / product showcasing

Mmikemenders I have now tried the Prodigy Lora training with another parameter that is also r...

Constipated•10/14/23, 4:20 PM

Can you share your full training settings?

CConstipated Can you share your full training settings?

mikemenders•10/14/23, 5:04 PM

With Prodigy, I find that it's very sensitive to the face, so you definitely need a Compreface in front of it to get images with a score of 0.99-1 only, smaller ones will distort the face badly.
I use two types of parameters: a strong one that will take most of the body but needs a strong prompt, and a flexible weaker one that will take the face but less the body.

Mykee_-_Prodigy_-_RealisticVision_-_Person_Flexible.json2.9KB

Mykee_-_Prodigy_-_RealisticVision_-_Person.json2.88KB

mikemenders•10/14/23, 5:05 PM

I train for 25 pictures with 4 repetitions

@Dr. Furkan Gözükara I figured out that noise issue from the other day. My learning rate was way too

Similar Threads

Similar Threads

Similar Threads