being distilled model
being distilled model
A
Fi am waitin them to become more mature
Fnext will research them
Asounds like a plan
Asorry for all the questions but do you have an estimate for how long you think that will be
Fsadly i dont know but i hope be fast
Fmy next is recording fine tuning video
Fcurrently testing FP8 conversiton of models
Ftesting
Fwow almost no quality loss
F
Awow
Awhat FP is the original
F
F
Foriginal is fp16
DWhat got broken exactly?
DI mean, two of my trainings are still ongoing probably on this version lol.
Fnewest version
Fnew trainings
Fnot starting
Flast update is 3 hours ago
Pnice!
Fthanks
Fabout to publish an article
DDoes this command on MC does not pull the latest version? "chmod +x Massed_Compute_Kohya_FLUX.sh
./Massed_Compute_Kohya_FLUX.sh"
./Massed_Compute_Kohya_FLUX.sh"
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Fit pulls latest
DI started a lora training, like an hour back.
Fweird
Fi wonder if only runpod broken
Fdue to accleerate
Fwill check now
Fbut it was working previously on runpod too
FGitHub
Urgent fix needed for SD3 branch @kohya-ss this error is after latest @bmaltais update this config worked yesterday INFO prepare accelerator flux_train.py:177 accelerator device: cuda Saving traini...
DIn the logs, like an hour back. Seems to say it is already up to date?
Fweird how yours works 
Fupdate was like 5 hours ago
DThen, not one, but two of mine are going right now lol
Fkohya fixing the error
Fman this guy awesome
Fhe replied my from twitter
Fye he fixed
Fnow we have to wait bmaltais
Fkohya fixed
DFux-De-Distilled I'm training right now great speed T5 and T5 att mask
Dwas training slower this morning.. same dataset, same settings
Didk
