Doc how will you cope updating everything as more and more repos come out....
Doc how will you cope updating everything as more and more repos come out....
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=40)
Dyou will have to be Dr Octopuss lol
V
D45 degree angle nice
V
V@Dr. Furkan Gözükara
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=16)
Fye it is becoming hard :d
Ffinally back again to 64 gb
F
Fimproved score at cinebench too
V@Dr. Furkan Gözükara So I've been checking out the Batch size 7 config. And It seems that your Learning Rate is 0.00001 which is 2.5x higher than when batch size is 1. What made you choose that Learning rate?
NI used the "flux-dev-de-distill" model for Dreambooth training, and the resulting file is very large. Is this because I haven't extracted the LoRA from it yet?
AI assume most everyone here has watched the Behind the scene from Corridor Digital on their rock paper scissors Anime. If not here it is.. https://youtu.be/_9LX9HSQkWo?feature=shared&t=675
Does anyone know about custom models in SDXL? I am curious.. When training their model, does he mean he trained a model on him and his costume, then used that model as the base to train the style into that same model?
Does anyone know about custom models in SDXL? I am curious.. When training their model, does he mean he trained a model on him and his costume, then used that model as the base to train the style into that same model?
Di want 190gb
Ffully testing
Fyes full checkpoints
Fbut sizes are different
Fweird
Fyes i explained what they did here https://youtu.be/kmT-z2lqEPQ
YouTubeSECourses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Turn your real video into an animation with just 1 click by using Stable Diffusion for free. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
Playlist of Sta...
https://www.patreon.com/SECoursesPlaylist of Sta...
Acan I do multi GPU for FLUX dev dreambooth/finetune ?
A@Dr. Furkan Gözükara how long did it take to train that 10k images model you did ? and what hardware ?
Fyes 80 gb gpus
Fi have shared all info on patreon timings too
Fplease read
Ftime record fine tuning tutorial
Fdaily life stuff taking huge time :d
Fwow windows flux training speed amazing
Falmost alike linux
M
Mtorch 2.5 offically out
Fadded triton
Fnice
Fnow we gonna wait xformers
Fi am recording tutoriakl
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
DThis only impacts training on windows, correct?
DWill it also impact inference/ generations on windows?
Fit depends on scripts
DHow much data does a HF account allow to store?
DThink I'll be needing a lot of space tonight.
Fi think unlimited :d
Fthey are amazing
Fman this fine tuning video being long as usual :d
DI thought the loras video covered almost all of the settings?
Fyes true did
Fbut i add some extra new stuff like auto crop
Fshowing some swarmui settings
DOhh cool.
DCan I have SwarmUI find models in my comfy unet folder? lol
DI'm running sooo low on space
DI did wanna get rid of duplicates of the same model