although it works without
although it works without
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=16)
Fyes i guess it is redundant
AHey, could anyone help me with properly configuring AudioCraft MusicGen for training with my own data sets? I'm wanting to train it on a a100 gpu server instance using lambda. I tried to configure it using chatgpt as a guide but getting errors I can't figure out. I'd really appreciate any help!
Fit is a big task
AYeah, I assumed as much. I just am looking for guidance because chatgpt is getting me nowhere but errors.
M
Flive portrait very obviously
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Flive portrait animal we have installer
WThe COGVLM app... I keep getting an error every time I try and load an image. The message saying
WHappens with every image I have tried to load.
WAnyone have any suggestion?
Fcan you tell me your zip file name and your gpu?
WCogVLM2_v5.zip
3090 ti
3090 ti
Fok make a fresh install and send me install logs and also send me full run logs so i can see error happens where. i will also make a fresh instlal now and test
Fjust made a fresh install and tested on 3090 ti at 4 bit
F
Fno issues
Fexample image
RI have a issues with de IDM-VTON project, I cant use the manual mask. It doesnt work. Thank you for your help.
Fwhich zip file you are using?
Fsorry for late reply
RIm using the virtual_try_on_v16. When I try it from gradio doesnt work, I think the error is due to the first element of the array layer from gradio is a empty mask.
Ror an incorrect format because when I send my own mask in black and white format it works
Fit was working last time i used
Fdid you test demo images?
Fi will try latest version now
Fit works fresh install
F
Fi tested another image as well
RI mean manual mask mode
RWhen desactivate the option "use auto-generated mask"
Fyou are right plese remind me tomorrow if i forget
Fsorry for late replyt
RI think the call to the first element of the array Layer is wrong, maybe it try with the second
Fpublished even better version
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Fperfectly now you can mask 
Ftook me whole day to code
ᴏJust saw message, thanks. using Dr. Fukans.
AI tried switching to prodigy optimizer setting learning rate to 1 and cosine. With 60 images using basic tag captions, 150 epoch, batch 4 the result was very amazing and fast.
AIt actually overtrained
AI have never used it before though so I will need to fine tune the settings and educate myself on the differences between it and adafactor or Adamw
Fnice give it a try
Fso far i see that optimizer makes minimal difference as long as you are using most optimal parameters. my new workflow will be only slightly better
SSWe have it enabled at mitte.ai already before other platforms and thought you might want to try it first before others
Fsure add my account some credits i can ttest
Sadding!
Sdone 
Fty