Software Engineering Courses (SECourses)•3y ago

@Dr. Furkan Gözükara any idea why my latents are caching so slow on koyahss dreambooth? i have 4090

DobbyOP•12/14/23, 8:09 PM

im gonna restart env just in case

DDobby @Dr. Furkan Gözükara any idea why my latents are caching so slow on koyahss drea...

Furkan Gözükara SECourses•12/14/23, 8:10 PM

super slow

Furkan Gözükara SECourses•12/14/23, 8:10 PM

i think it is a bug of nvidia driver

DobbyOP•12/14/23, 8:11 PM

im going to resintall whole koya env lets see

FFurkan Gözükara SECourses you need to start as half precision

Sarcasticest•12/14/23, 10:01 PM

Wouldn't whatever is happening effect every process I try and run? If you can run

Clip_Interrogator.py

Clip_Interrogator.py

and use Clip_Interrogator Gradio Web UI with ViT-bigG-14/laion2b_s39b_b160k and blip2-2.7b with short generation time, and I have almost the same GPU, shouldn't I be able to do the same?

hozaggers•12/14/23, 10:17 PM

does anyone have any tips for further training on kaggle after uploading to hugging face? I have a model I am training but I will run out of qouta before it finishes, the 83% checkpout should save before my qouta runs out though. If I set the initial training for 100 steps, and save at 83% how do I re-upload it to train it the remaining 17% for the next checkpoint?

SSarcasticest Wouldn't whatever is happening effect every process I try and run? If you can ru...

Furkan Gözükara SECourses•12/14/23, 10:18 PM

you know full precision uses almost double of half

Hhozaggers does anyone have any tips for further training on kaggle after uploading to hugg...

Furkan Gözükara SECourses•12/14/23, 10:18 PM

yes give it as a base model

Mnova•12/14/23, 10:19 PM

hey i've been trying to train a model in dreambooth. but this always ends up happening

FFurkan Gözükara SECourses yes give it as a base model

hozaggers•12/14/23, 10:20 PM

sorry which field do I need to amend to upload as a base model? is it these? is it one or both? Then I just need to amend the training steps as appropriate?

MMnova hey i've been trying to train a model in dreambooth. but this always ends up hap...

Furkan Gözükara SECourses•12/14/23, 10:36 PM

you should use my colab

Furkan Gözükara SECourses•12/14/23, 10:36 PM

https://youtu.be/mnCY8uM7E50

YouTubeSECourses

Transform Your Selfie into a Stunning AI Avatar with Stable Diffusi...

Our Discord : https://discord.gg/HbqgGaZVmr. How to do free Stable Diffusion DreamBooth training on Google Colab for free. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on

https://www.patreon.com/SECourses

Playlist of Stable Diffusion Tutorials, Automatic1111 and Goo...

Hhozaggers sorry which field do I need to amend to upload as a base model? is it these? is ...

Furkan Gözükara SECourses•12/14/23, 10:36 PM

yes download it onto kaggle

Furkan Gözükara SECourses•12/14/23, 10:37 PM

then give its path

Furkan Gözükara SECourses•12/14/23, 10:37 PM

you need to do that

Furkan Gözükara SECourses•12/14/23, 10:37 PM

like we give path on runpod

Furkan Gözükara SECourses•12/14/23, 10:37 PM

https://youtu.be/-xEwaQ54DI4

YouTubeSECourses

How To Do SDXL LoRA Training On RunPod With Kohya SS GUI Trainer & ...

If you don't have a GPU, or have a strong GPU, or you are using Mac and your computer not supporting Stable Diffusion training, SDXL training, then this is the tutorial you are looking for. In this tutorial, we will use a cheap cloud GPU service provider RunPod to use both Stable Diffusion Web UI Automatic1111 and Stable Diffusion trainer Kohya ...

FFurkan Gözükara SECourses you know full precision uses almost double of half

Sarcasticest•12/14/23, 10:58 PM

Yes, of course.

I guess I'm confused because in your video https://youtu.be/PNA9p94JmtY?t=380 at 6:20 you state that the Gradio application ran with

Clip_Interrogator.py

Clip_Interrogator.py

with "best models" uses 19GB VRAM. Maybe I misunderstood?

YouTubeSECourses

Caption Images or Learn How To Prompt With Clip Vision of SDXL and ...

Download scripts from here

https://www.patreon.com/posts/sota-very-best-90744385

Full length Twitter video here

https://twitter.com/GozukaraFurkan/status/1712665890259447831

SOTA (The Very Best) Image Captioning Models Script For Stable Diffusion And More

1 Click install and use SOTA image captioning models on your computer. Supports 8 ...

SSarcasticest Yes, of course. I guess I'm confused because in your video https://youtu.be/PNA...

Furkan Gözükara SECourses•12/14/23, 11:00 PM

let me test on my system right now

Furkan Gözükara SECourses•12/14/23, 11:00 PM

i am doing a fresh install

SSarcasticest Yes, of course. I guess I'm confused because in your video https://youtu.be/PNA...

Furkan Gözükara SECourses•12/14/23, 11:04 PM

you are trying run_Clip_Interrogator.bat right?

FFurkan Gözükara SECourses you are trying run_Clip_Interrogator.bat right?

Sarcasticest•12/14/23, 11:05 PM

Correct

SSarcasticest Correct

Furkan Gözükara SECourses•12/14/23, 11:07 PM

then you selected these 2?

Furkan Gözükara SECourses•12/14/23, 11:07 PM

FFurkan Gözükara SECourses then you selected these 2?

Sarcasticest•12/14/23, 11:07 PM

Yes

Furkan Gözükara SECourses•12/14/23, 11:10 PM

before the app

Furkan Gözükara SECourses•12/14/23, 11:11 PM

FFurkan Gözükara SECourses you should use my colab

Mnova•12/14/23, 11:11 PM

I've been trying to install the requirements, but I#m already failing at this step

Furkan Gözükara SECourses•12/14/23, 11:11 PM

while app running

Furkan Gözükara SECourses•12/14/23, 11:11 PM

@Sarcasticest it is using 17 GB or lesser

MMnova I've been trying to install the requirements, but I#m already failing at this st...

Furkan Gözükara SECourses•12/14/23, 11:11 PM

use my colab

FFurkan Gözükara SECourses use my colab

Mnova•12/14/23, 11:12 PM

the one thats linked in the video?

MMnova the one thats linked in the video?

Furkan Gözükara SECourses•12/14/23, 11:12 PM

yes

Mnova•12/14/23, 11:13 PM

okay will try thank you very much

FFurkan Gözükara SECourses @Sarcasticest it is using 17 GB or lesser

Sarcasticest•12/14/23, 11:15 PM

So it captioned the image quickly?
Could there be something wrong with the model I have? I'm not sure where to start.
With the default models in your video I get same or better VRAM usage. So there is something specific happening to this one.

SSarcasticest So it captioned the image quickly? Could there be something wrong with the model...

Furkan Gözükara SECourses•12/14/23, 11:15 PM

yes