which folder of stableswarm does it go in? unet?
which folder of stableswarm does it go in? unet?
Fdiffusion_models
Dthank you.
DThis is the best one I got so far. Pretty good. One on right is AI obviously.
Dmost photos though are blurry.
DGoing through the checkpoints now to find the best one. above was at 150 I believe.
Fif results not good then your dataset not good :d
Dgot it.
Dmaybe cause this dog has a really hard to see face?
DIs massed compute the best way to train models? I have a 16GB memory M2 macbook. Last model took 33 hours to train so I must not have optimized. And I rented two A6000 GPUs.
DAlso, why might this photo be blurry? I just used normal flux model, no fine tuning or LoRAs.
CChange your CFG scale to 1 for flux
Dawesome. tahnk you.
Fhappens sometimes
Fmake more steps
Fand cfg scale 1
MHi there!
Attempting to fully train FLUX with dreambooth on runpod.
Does anybody encounter same trouble?
[rank1]: ValueError: DistributedDataParallel device_ids and output_device arguments only work with single-device/multiple-device GPU modules or CPU modules, but got device_ids [1], output_device 1, and module parameters {device(type='cpu')}.
While using multiple GPU getting this error. Using 2 A100 PCle. If turning off checkbox multi GPU and switching Number of processes to 1 working great.
Using Quality_1_21820MB_16_12_Second_IT.json from Best_Configs_v3
Attempting to fully train FLUX with dreambooth on runpod.
Does anybody encounter same trouble?
[rank1]: ValueError: DistributedDataParallel device_ids and output_device arguments only work with single-device/multiple-device GPU modules or CPU modules, but got device_ids [1], output_device 1, and module parameters {device(type='cpu')}.
While using multiple GPU getting this error. Using 2 A100 PCle. If turning off checkbox multi GPU and switching Number of processes to 1 working great.
Using Quality_1_21820MB_16_12_Second_IT.json from Best_Configs_v3
message.txt5.28KB
Dit's quite difficult to find the right LR for Flux. Because they all work 
DYes, I also got to know recently (and after planning to start one training), that multiple GPUs won't work on dreambooth training x flux yet. I shoulda read the post better lol.
MGosh, am I arrogant? I just skimmed through it.
Fi trained lora on multi gpu
Ffine tuning had failed on 48 gb gpu
Fbut didnt try on 80 yet
Fbut i didnt get thgis error on massed compute
Fit was OOM
Fare you using my config @ministryofspaceandtime
MYes, was trying this configs. Every one of them works fine on single GPU and failed on multiple. (by the way I'm using RunPod, not Massed Compute)
Fi will try on runpod lets see
Finstalling right now on 2x a100
Fitm is working
F
FQuality_1_27500MB_6_26_Second_IT.json
Fbut it is ridiciliously slow slower than 1 gpu
Phey guys, how can i fix this, its been eating my head for a while now. Any help would be appreciated
Fwhat are you trying to do?
MHi there! @Furkan Gözükara SECourses , I read your latest greatest post about multiple-GPU Dreambooth finetuning for Flux. Please tell me if I got this right: if you want to use multiple GPUs, they must each have ≥80 GB RAM (so, top-of-the-line A100's or H100's). Still, you don't get linear decreases in processing time, at least with A100's (with 2x A100's you don't get 2x speed). Thus, for that money (at least on RunPod), you're better off with one L40S.
However, what about 4x A6000's? Those don't have 80 GB VRAM. Are they still cost-effective? EDIT: referring to Massed Compute's 4x A6000's at half-price with your special code, as well as those at full price.
However, what about 4x A6000's? Those don't have 80 GB VRAM. Are they still cost-effective? EDIT: referring to Massed Compute's 4x A6000's at half-price with your special code, as well as those at full price.
Fit doesnt fit into a6000
Fthat is the problem
Ffrom 27 gb to jumps 75 gb vram
Fwhen doing multi gpu
Fi reported this to kohya but he thinks it is accurate
MSo, using multiple GPUs gives marginal, non-cost-effective advantage only when using ≥80GB GPUs, right?
Fat least for 2x
Falso these are pciex
Fsxm maybe different
SWhat saas service did you use that was able to do it in only 30 minutes? I'd love to give that a shot
MIn case anyone was wondering, I started a finetune on Vast using an A100 SXM4 (80GB VRAM) and it's doing ~3.16 sec/iteration.
MIt should be noted that on Vast.ai you can get this machine with 250 GB semi-permanent hd space for $0.78/h, which is pretty cheap…
Fhow many gpus
