Furkan Gözükara
patreon
Now You Can Full Fine Tune / DreamBooth Stable Diffusion XL (SDXL) with only 10.3 GB VRAM via OneTrainer
🕑 Added 2024-03-26 04:44:32 +0000 UTCNow You Can Full Fine Tune / DreamBooth Stable Diffusion XL (SDXL) with only 10.3 GB VRAM via OneTrainer — Both U-NET and Text Encoder 1 is trained — Compared 14 GB config vs slower 10.3 GB Config
Full config and instructions are shared here : https://www.patreon.com/posts/96028218
Used SG161222/RealVisXL_V4.0 as a base model and OneTrainer to train on Windows 10 : https://github.com/Nerogar/OneTrainer
The posted example x/y/z checkpoint comparison images are not cherry picked. So I can get perfect images with multiple tries.
Trained 150 epochs, 15 images and used my ground truth 5200 regularization images : https://www.patreon.com/posts/massive-4k-woman-87700469
In each epoch only 15 of regularization images used to make DreamBooth training affect
As a caption only “ohwx man” is used, for regularization images just “man”
You can download configs and full instructions here : https://www.patreon.com/posts/96028218
Hopefully full public tutorial coming within 2 weeks. I will show all configuration as well
The tutorial will be on our channel : https://www.youtube.com/SECourses
Training speeds are as below thus durations:
RTX 3060 — slow preset : 3.72 second / it thus 15 train images 150 epoch 2 (reg images concept) : 4500 steps = 4500 3.72 / 3600 = 4.6 hours
RTX 3090 TI — slow preset : 1.58 second / it thus : 4500 * 1.58 / 3600 = 2 hours
RTX 3090 TI — fast preset : 1.45 second / it thus : 4500 * 1.45 / 3600 = 1.8 hours
A quick tutorial for how to use concepts in OneTrainer : https://youtu.be/yPOadldf6bI
Comments
Furkan Gözükara
for SD 1.5 we have different config here : https://www.patreon.com/posts/very-best-config-97381002 please also watch this tutorial : https://youtu.be/0t5l6CP9eBg
Javi dltr
does this work with 1,5?
Furkan Gözükara
you are welcome
Tom Bloomingdale
Awesome thank you. moving much faster now, looks like about three and a half hours. Thanks for the help
Furkan Gözükara
that means using shared vram. use lower speed. something else could be using your vram already
Tom Bloomingdale
Hello! I have this set up for SDXL using the "fast" option for fine tuning. I have a 4060ti with 16gb vram. With 150 epoch, Im looking at like 35 hours training time. Am I doing something wrong?
Furkan Gözükara
more images requires same vram it wont make difference. but more images would require lesser number of total epochs
Leonardo Chocron
Hi doc! Does more images require more vram? I don't get the consistency that I have with sd1.5 using the same photos, especially in the shape and physiognomy of the face.
Doc Snyder
https://github.com/Nerogar/OneTrainer/commit/07f8198e8762eed2b1f5755bc0445f2ae1cd988b
Furkan Gözükara
ok i asked the developer and he said it is already fixed
Furkan Gözükara
i get same error. the guy broken previous configs i have to remake
Doc Snyder
With the latest version of onetrainer I get "AttributeError: 'str' object has no attribute 'is_wuerstchen'" while changing to the added preset and it doesn't load.
Furkan Gözükara
SDXL is better with 12 GB
Furkan Gözükara
no on computer but i am gonna introduce something better hopefully
C. Jonas
Hi Furkan, would you rather do a full training on SD1.5 with your preset for 12GB cards or a full training on SDXL with your new config? Which training ist better for realistic faces whilst still enabling flexibility in the generated pictures?
Joel Maynard
are you tried on runpod?
Furkan Gözükara
ye kaggle is picky. i prefer runpod over paid google colab. cheaper and better. also there is a new cloud computing i am going to introduce. 31 cents per hour for A6000 gpu - 48 gb
Gen Zero
I'm not impressed with Kaggle Notebook because I got blocked. And they said I violated community rules. Even though I use the script to test.
Furkan Gözükara
ah i see what you mean. it can read safetensors or ckpt as well
Hey Ooo
I understand. Does onetrainer only take diffusers for this low vram method?
Furkan Gözükara
This is standalone app OneTrainer.
Hey Ooo
Does this only work with diffusers
Furkan Gözükara
i think both are really good. i would compare both to see which one is better for you
Furkan Gözükara
Since I don't have premium colab I can't test. but our kaggle notebook should work fairly well on pro colab have you tested?
Furkan Gözükara
you are welcome
Furkan Gözükara
thank you so much
Alex
Thanks, I'll give it a try.
Art
wonderful work, Furkan!
Gen Zero
I want Stable Diffusion - Automatic11119 The latest one is 2024 at Run on Colab. Please send me some tutorials. Thank you very much.
Ec Jep
Thx for this. How does it compare to latest kohya db TE training? I get excellent realism on kohya. From your earlier post these are very good but maybe facial detail not as good w/onetrainer. Thoughts?
