Software Engineering Courses (SECourses)•11mo ago

Hi everyone! <@205854764540362752> can you give me a hint? I have this error: RuntimeError: CUDA err

Hi everyone!
@Furkan Gözükara SECourses can you give me a hint?
I have this error:
RuntimeError: CUDA error: out of memory
"CUDA kernel errors may be reported asynchronously by some other API call, so the stack trace below may not be correct.
For debugging, consider passing CUDA_LAUNCH_BLOCKING=1"
I tried 8gb and 3080 10gb config
I have 48gb RAM and 10gb VRAM.
What can help me?

cyleap•2/24/25, 2:48 PM

@Furkan Gözükara SECourses Hey. I saw your yt community post, and wondering will there be a tutorial coming for sd3.5? maybe on patreon post early.

Wwardensc2 Hi <@205854764540362752> are there anyway to convert back fp8 model into fp16 ag...

Furkan Gözükara SECourses•2/24/25, 3:58 PM

nope all data lost once you convert into fp8

�𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮 Why don't you try simpletunner?

Furkan Gözükara SECourses•2/24/25, 3:58 PM

i dont plan to invest time into that one

AAstraBat I've been using config files from KOhya_FLUX_DreamBooth_v17, after installing th...

Furkan Gözükara SECourses•2/24/25, 3:59 PM

this can happen

Furkan Gözükara SECourses•2/24/25, 3:59 PM

if you loaded lora into dreambooth

Furkan Gözükara SECourses•2/24/25, 3:59 PM

or dreambooth into lora

AAstraBat It isn't super-slow, by the way, running at 5.00 - 7.00 sec/it.

Furkan Gözükara SECourses•2/24/25, 3:59 PM

5 second it is good

Furkan Gözükara SECourses•2/24/25, 3:59 PM

for flux dreambooth

FFurkan Gözükara SECourses i dont plan to invest time into that one

�

𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮•2/24/25, 3:59 PM

Way better than ai toolkit btw

CCBuH Hi everyone! <@205854764540362752> can you give me a hint? I have this error: Ru...

Furkan Gözükara SECourses•2/24/25, 3:59 PM

hi when you have it?

Furkan Gözükara SECourses•2/24/25, 3:59 PM

you are out of VRAM

�𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮 Way better than ai toolkit btw

Furkan Gözükara SECourses•2/24/25, 3:59 PM

i dont like the developer, the guy attacked me so many times without any reason

Ccyleap <@205854764540362752> Hey. I saw your yt community post, and wondering will ther...

Furkan Gözükara SECourses•2/24/25, 4:00 PM

could be currently i am doing research for a client

FFurkan Gözükara SECourses i dont like the developer, the guy attacked me so many times without any reason ...

�

𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮•2/24/25, 4:01 PM

Yes he is rude sometimes but a great developer and he very well documented everything and very active in discord servers.

FFurkan Gözükara SECourses could be currently i am doing research for a client

cyleap•2/24/25, 4:03 PM

nice looking forward to this, since flux have its own disadvantages, im still using sdxl. hoping sd3.5 will amaze me.

cyleap•2/24/25, 4:04 PM

can we use regularization imgs with sd3.5?

Ccyleap can we use regularization imgs with sd3.5?

Furkan Gözükara SECourses•2/24/25, 4:04 PM

i think people said same as flux but havent tested yet

Furkan Gözükara SECourses•2/24/25, 4:04 PM

will test

cyleap•2/24/25, 4:05 PM

looking forward to this

cyleap•2/24/25, 4:18 PM

looking forward to this

�𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮 Way better than ai toolkit btw

smoke•2/24/25, 4:32 PM

Would it be possible for you to perhaps share any results? I am also looking into simpletuner and would love to see if someone has achieved some reasonable results. Would really appreciate it, I won't share ^^

Ssmoke Would it be possible for you to perhaps share any results? I am also looking int...

�

𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮•2/24/25, 6:04 PM

I have not yet tested it but I plan to do that next month. I have heard many people talk good about it. Here is a video that goes deep into it and compares it with ai toolkit - https://youtu.be/se3qpLkJnrk?si=7MhyT8i3DALGK9L5

YouTubekasukanra

Kasucast #26 - FLUX.1 [dev]: Training LoRA with SimpleTuner and AI-...

#flux #simpletuner #bghira #ComfyUI #LoRA #finetune #stablediffusion #style #styletraining

This is an FLUX.1 [dev] LoRA training log for art style and concepts. I document my thought process, experiments, mistakes, and analysis of quantitative and qualitative results. Hopefully, this can be a good starting guide for people looking to train LoRA...

�𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮 I have not yet tested it but I plan to do that next month. I have heard many peo...

smoke•2/24/25, 6:35 PM

So your opinion "Way better than ai toolkit btw" is based on a video? You haven't tried it yourself yet?

smoke•2/24/25, 6:36 PM

Interesting

Ssmoke So your opinion "Way better than ai toolkit btw" is based on a video? You haven'...

�

𝗡𝗶𝘁𝗶𝗻 𝗣𝗮𝗿𝗲𝘃𝗮•2/24/25, 6:39 PM

See the video you will know. I have done a lot of trainings with ai toolkit btw

novsky•2/24/25, 8:44 PM

can some explain how to reduce flux lora size with no (almost) quality loss? Because I've made bunch of them and 1gb loras is eating my storage) or maybe there is video with explanation?

novsky•2/24/25, 10:37 PM

never mind, found in patreon posts

Nnovsky never mind, found in patreon posts

Furkan Gözükara SECourses•2/24/25, 11:34 PM

saving as fp8

FFurkan Gözükara SECourses saving as fp8

novsky•2/24/25, 11:40 PM

yep, reduced to 260mb instead of 1GB, thx

Nnovsky yep, reduced to 260mb instead of 1GB, thx

Furkan Gözükara SECourses•2/24/25, 11:43 PM

you are welcome

Guy Bertental•2/25/25, 12:22 PM

Hi @Furkan Gözükara SECourses , do you have an idea how to create a consistent character for image generation from a single image?

GGuy Bertental Hi <@205854764540362752> , do you have an idea how to create a consistent charac...

Furkan Gözükara SECourses•2/25/25, 12:24 PM

yes 2 step training

Furkan Gözükara SECourses•2/25/25, 12:24 PM

1st traing with single image

Furkan Gözükara SECourses•2/25/25, 12:24 PM

add cropped version zoom out etc

Furkan Gözükara SECourses•2/25/25, 12:24 PM

then generate images

Furkan Gözükara SECourses•2/25/25, 12:24 PM

then train again

Guy Bertental•2/25/25, 12:42 PM

Interesting idea, I'll try it. Thanks

Guy Bertental•2/25/25, 12:45 PM

I saw this tutorial, I wonder if they do it the same way behind the scenes

https://youtu.be/UY_aRiOK6gY?si=6U4TAXFPa0lxPPU0

Guy Bertental•2/25/25, 12:48 PM

What about this process using different posing on a single image?

https://youtu.be/MbQv8zoNEfY?si=oufZgsSpJJSBMGD9

GGuy Bertental Interesting idea, I'll try it. Thanks

Furkan Gözükara SECourses•2/25/25, 2:53 PM

same logic. if you can get more poses from single image can help

Furkan Gözükara SECourses•2/25/25, 2:54 PM

but still i recommend twice training

Aikage•2/26/25, 5:03 PM

Single Image training is pretty good but will work exponentially better if you can get at least three from different angles from my experience

Aikage•2/26/25, 5:03 PM

you will save yourself a lot of time and headache

Aikage•2/26/25, 5:04 PM

If you have Comfy there are some workflows floating around which will attempt to create these angles from the image - you can randomly hit on some with a few rolls of the dice

FFurkan Gözükara SECourses add cropped version zoom out etc

Luiz xd•2/26/25, 5:22 PM

under this logic, not having so many images, could you recommend some configuration to train with a minimum of 5 or 10 images, how many steps, etc.

LLuiz xd under this logic, not having so many images, could you recommend some configurat...

Furkan Gözükara SECourses•2/26/25, 5:26 PM

it is always same the config

Furkan Gözükara SECourses•2/26/25, 5:26 PM

only number of epochs may change

Furkan Gözükara SECourses•2/26/25, 5:26 PM

like do more epoch

FFurkan Gözükara SECourses like do more epoch

Luiz xd•2/26/25, 5:33 PM

Perfect! To test then... Thanks

Hi everyone! <@205854764540362752> can you give me a hint? I have this error: RuntimeError: CUDA err

Similar Threads