is your notebook killed?
is your notebook killed?
For only gradio
Fpixart-alpha (PIXART-α) looking amazing
prompt : a mighty lion running in new york city
styles
default, anime, digital art
hopefully full tutorial and auto…
prompt : a mighty lion running in new york city
styles
default, anime, digital art
hopefully full tutorial and auto…
CCan anyone help please, ive created about 10 'deep fake videos so far with no issues at all.
But the past few times my pc just crashes out and restarts about 80% sometimes 64% etc into processing.
But the past few times my pc just crashes out and restarts about 80% sometimes 64% etc into processing.
S@Dr. Furkan Gözükara I’m doing this as a hobby but there is ways to make money generating this images and continue the research? and cover the server cost? this is a nice discussion that I guess a lot of people will be interest
CI cant get a screenshot of my pc because I never know when its going to crash and with it taking a long time for each video I can't sit and watch it constantly 
ive screenshotted the YouTube tutorial.
ive screenshotted the YouTube tutorial.
CSo I select my face, choose my target video, check many faces, and everything runs smoothly then as I say it gets to 60/80 sometimes 90% then crash computer turns off? 
Fyour PC specs is the problem
Fcould be undervolted RAM
Fsadly i dont know. but some people making money
CI'm confused as it worked fine, till now
C12th Gen I5
32GB Ram
GeFroce GTX 1660ti
this is a screenshot of a previous video that worked perfectly. Im face swapping on the same video each time
32GB Ram
GeFroce GTX 1660ti
this is a screenshot of a previous video that worked perfectly. Im face swapping on the same video each time
Fwell try to increase ram voltage
Fa little bit
DIs close images datasets is good for dreambooth training or full body or half body images data set is good for woman
Fi prefer to add all
Fand after use adetailer during inference
FSthis is like a new stable difussion?
Fyes
Fdifferent model
Fcan follow prompts better
Dcan confirm when the estimated trime is beyond 30 min. I reduced the images to 13 , which made the caching latency time within 30min (23min to be exact) , it is working now
Depoch 1/2
steps: 20%|███ | 521/2600 [44:13<2:56:30, 5.09s/it, avr_loss=0.118]
saving checkpoint: /kaggle/temp/models/DB_Gowthu-step00000521.safetensors
steps: 40%|████▊ | 1042/2600 [1:30:07<2:14:45, 5.19s/it, avr_loss=0.117]
saving checkpoint: /kaggle/temp/models/DB_Gowthu-step00001042.safetensors
steps: 50%|██████ | 1300/2600 [1:53:08<1:53:08, 5.22s/it, avr_loss=0.113]
saving checkpoint: /kaggle/temp/models/DB_Gowthu-000001.safetensors
epoch 2/2
steps: 60%|███████▏ | 1563/2600 [2:16:08<1:30:19, 5.23s/it, avr_loss=0.115]
saving checkpoint: /kaggle/temp/models/DB_Gowthu-step00001563.safetensors
steps: 64%|███████▋ | 1677/2600 [2:27:02<1:20:55, 5.26s/it, avr_loss=0.114]
steps: 20%|███ | 521/2600 [44:13<2:56:30, 5.09s/it, avr_loss=0.118]
saving checkpoint: /kaggle/temp/models/DB_Gowthu-step00000521.safetensors
steps: 40%|████▊ | 1042/2600 [1:30:07<2:14:45, 5.19s/it, avr_loss=0.117]
saving checkpoint: /kaggle/temp/models/DB_Gowthu-step00001042.safetensors
steps: 50%|██████ | 1300/2600 [1:53:08<1:53:08, 5.22s/it, avr_loss=0.113]
saving checkpoint: /kaggle/temp/models/DB_Gowthu-000001.safetensors
epoch 2/2
steps: 60%|███████▏ | 1563/2600 [2:16:08<1:30:19, 5.23s/it, avr_loss=0.115]
saving checkpoint: /kaggle/temp/models/DB_Gowthu-step00001563.safetensors
steps: 64%|███████▋ | 1677/2600 [2:27:02<1:20:55, 5.26s/it, avr_loss=0.114]
DSo i think there should be a disclaimer for now in your video to limit the images to 13-15 i guess. someone should work on this and see how many images can be within 30min. I am sure 18 images crosses 30 min
Fye maybe developer will fix it
Dluckily the notebook was on, i went into kohya gui and entered new data set(13 images) directory link and made changes to 521 steps and ran training
Dis it possible to move the generated tensor files to dataset directly ?
Die from temp files to dataset ?
Dnumbering of safetensor file is weird i guess ? 521/1042/1?/1563
Uhow is the speed of pixart-alpha?
DVaried , all types are important , but make it absolutely clear , in none of the photos other than face, nothing else repeats. Last time i trained my lora for my wife , i had few photos with same dress and it made a great impact on the outwhen when generating images. this time 
. waiting for dreambooth ...
. waiting for dreambooth ... 
Freally good
Fbut you need 16gb vram . i dont know if would work on 12 8 bit may work
Fi will try to make it work on kaggle as well
UNice. I think I'll try on runpod
Fyep should work great
UI saw this part on github page
Fye i checked it but
Ffor it to work
Ffor every image you load deload models
Fwill be ultra slow
Flike you lad text encoder, deload it , reload it everytime all models deleted and loaded again
UOh I see
Uthanks for your effort and great work
Fyou are welcome
Fi am testing runpod right now
Fa5000
Fupdated attachment again for runpod
Fneed 1 more update
F