Software Engineering Courses (SECourses)•3y ago

when I tried to train on dreambooth originally with my dataset I had to be more specific in my class

when I tried to train on dreambooth originally with my dataset I had to be more specific in my class image generation because "photo of a woman" didn't give good results for me

PP1pSl1p when I tried to train on dreambooth originally with my dataset I had to be more ...

gatsby•3/8/23, 9:29 AM

Okay, so what did you have to use instead for better results?

P1pSl1pOP•3/8/23, 9:29 AM

since my wife is thai. I used "photo of a thai woman"

PP1pSl1p Click to see attachment

Trimac•3/8/23, 9:29 AM

Looks like lora copied perfectly your data set but not doing creativity. Well if that what you want then good for you

PP1pSl1p since my wife is thai. I used "photo of a thai woman"

gatsby•3/8/23, 9:30 AM

Ah okay. And then in your instance prompt did you use something like “ohwx photo of a Thai woman”?

TTrimac Looks like lora copied perfectly your data set but not doing creativity. Well i...

P1pSl1pOP•3/8/23, 9:30 AM

it did a great job for a start. now I need to add more images to the dataset and try again. I'm looking for something very flexible.

P1pSl1pOP•3/8/23, 9:31 AM

P1pSl1pOP•3/8/23, 9:31 AM

still good tho

Ggatsby Ah okay. And then in your instance prompt did you use something like “ohwx photo...

P1pSl1pOP•3/8/23, 9:32 AM

just photo of ohwx woman

PP1pSl1p just photo of ohwx woman

gatsby•3/8/23, 9:32 AM

Thanks so much for your help. Will test it out now

PP1pSl1p Click to see attachment

Trimac•3/8/23, 9:35 AM

Thats good. Can you please try more like a futuristic look prompts? it feels like i wanna try to go back in khoya lora. Im working wd my dreamboot now, wont give me precise face

TTrimac Thats good. Can you please try more like a futuristic look prompts? it feels lik...

P1pSl1pOP•3/8/23, 9:36 AM

I'll keep at it

P1pSl1pOP•3/8/23, 9:36 AM

try thos settings I posted above

P1pSl1pOP•3/8/23, 9:36 AM

training should take aroun 1hr 45

Trimac•3/8/23, 9:37 AM

My god this is so challenging its been months wd training settings but only the old revession dreambooth works once in my life lol! and able to create one model of my face perfectly and thats it Sd broked after that since updates

P1pSl1pOP•3/8/23, 9:37 AM

the tech is moving so fast

PP1pSl1p try thos settings I posted above

Trimac•3/8/23, 9:38 AM

will do thanks for the share

Aurora 神名河•3/8/23, 9:43 AM

thank you so much for sharing

Aurora 神名河•3/8/23, 9:43 AM

Now LoRA is great again!

P1pSl1pOP•3/8/23, 9:45 AM

all thanks to @Steel

P1pSl1pOP•3/8/23, 9:45 AM

he was s great help in getting these settings

HolmesCage•3/8/23, 9:46 AM

dreambooth keeps makes my lora checkpoints above 4gb what am i doing wrong?

P1pSl1pOP•3/8/23, 9:47 AM

dreambooth LoRa? or just Dreambooth? cause theyre two separate things

P1pSl1pOP•3/8/23, 9:47 AM

dreambooth checkpoints are huge

HolmesCage•3/8/23, 9:48 AM

i mean im using automatic1111 and there is only one extension for dreambooth

TTrimac Click to see attachment

Colored Tonalities•3/8/23, 9:48 AM

bush•3/8/23, 9:48 AM

i have a question. Anyone using dreambooth must've come across JOE PENNA dreambooth training tutorials. In that he uses a set of regularisation images which labelled ''man_unsplash'', these are real life photos of man from the unsplash site which are cropped to 512px square. how does using this man_unsplash dataset differ from using the ''2400photos of man'' provided by @Dr. Furkan Gözükara ??

P1pSl1pOP•3/8/23, 9:48 AM

yeah, that's straight dreambooth

HolmesCage•3/8/23, 9:48 AM

HolmesCage•3/8/23, 9:48 AM

should i be using other dreambooth?

P1pSl1pOP•3/8/23, 9:49 AM

when I'm dreambooth training that is unchecked. never tried it when checked so I don't know

P1pSl1pOP•3/8/23, 9:50 AM

I used Kohya Dreambooth LoRA for my recent results. which is entirely different

HolmesCage•3/8/23, 9:50 AM

yeah i saw tha tho there is no extension for kohya in auto1111

HolmesCage•3/8/23, 9:50 AM

it looks more complicated

P1pSl1pOP•3/8/23, 9:50 AM

qwen-flux-wan-such

P1pSl1pOP•3/8/23, 9:51 AM

use that video for install

P1pSl1pOP•3/8/23, 9:51 AM

then use the settings I posted above

P1pSl1pOP•3/8/23, 9:51 AM

qwen-flux-wan-such

HolmesCage•3/8/23, 9:53 AM

thanks a lot

vjavad1443•3/8/23, 9:56 AM

Does anybody know why I'm stuck in the loop when run "python relauncher.py" command ?

Python 3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]
Commit hash: 0cc0ee1bcb4c24a8c9715f66cede06601bfc00c8
Installing requirements for Web UI
Launching Web UI with arguments: --port 3001 --listen --enable-insecure-extension-access --share
Killed
Relauncher: Process is ending. Relaunching in 2s...
Relauncher: Launching...
Relaunch count: 1

P1pSl1pOP•3/8/23, 9:58 AM

I'm off guys. good luck with everything. See ya tomorrow.

Vvjavad1443 Does anybody know why I'm stuck in the loop when run "python relauncher.py" comm...

justalurker•3/8/23, 10:03 AM

Check your startup-webui.bat and clear any command line flags you may have set and try again.

vjavad1443•3/8/23, 10:04 AM

I think something is wrong with Gradio.live cause I'm getting bad gateway error! Maybe they are under DDOS Attack. Are you able to open it ?

bush•3/8/23, 10:05 AM

restart pod

bush•3/8/23, 10:05 AM

kill port 3000 before launching relauncher.py

bush•3/8/23, 10:06 AM

then launch relauncher

justalurker•3/8/23, 10:06 AM

Jjustalurker Click to see attachment

vjavad1443•3/8/23, 10:07 AM

I think my guess was true!

vjavad1443•3/8/23, 10:13 AM

BTW, I'm using mac. Do you know how can I install runpodctl on it?

https://github.com/runpod/runpodctl

I didn't find any instruction

GitHub

GitHub - runpod/runpodctl: RunPod CLI for pod management

RunPod CLI for pod management. Contribute to runpod/runpodctl development by creating an account on GitHub.

justalurker•3/8/23, 10:15 AM

Just pip'n the url doesn't work for you?

when I tried to train on dreambooth originally with my dataset I had to be more specific in my class

Similar Threads