I'm getting 6s/it at home on a 4070, but 14 s/it on an A6000. Do you have any idea why this could be
I'm getting 6s/it at home on a 4070, but 14 s/it on an A6000. Do you have any idea why this could be? identical config
Dflux lora
Finteresting
WNo, base model fp8 which uses to train lora does affect the lora. For example 2 train 2 lora same dataset but one with fp16 based model one with fp8. The lora with fp16 have better prompt understand than fp8. My training is person lora. While the person quality is still good with both loras. The prompt understanding every subjects outside of the person is reduce with fp8 lora. For example: my prompt have something like little angels playing in the background. The fp16 lora show some angel with body of human and wing but the fp8 showing some birds.
Dwas a mistake, images were cached at a different resolution on the 4070
Fthis is actually one of my fears
Fdifferent folders should be used for different resolutions
Fkohya may fail to properly cache
JI am training currently a Lora with Flux using 20 photos and 200 Epoch, is it normal it will take 4 tot 5 hours using an RTX 4090 locally? Or did I miss any optimization setting or script?
Fsounds accurate
Fwhat is your step speed?
Fwhich rank config?
JStep speed is 4.71s/it , how can I see my rank config?
JI used a Saas solution where I trained on the same 20 photos using Flux Lora, it took me only 30 minutes, any idea what can cause the difference in speed?
Ffrom zip file which one you loaded?_
Fthey are lower quality simple as that
Funless expensive h100 one 
JRank_3_18950MB_9_05_Second_IT 
JWhen training instead of an person, an object or a style, would you recommend a minimal amount of images or are 20 images enough?
�20 should be enough
JThanks Nitin
Fye rank 3 slower
Fyour speed good
Ffor style i suggest more
�I have seen people train on style using 7 images
DI'm really happy with how good Flux can be trained, the rank 3 is perfect for the 4090, thanks Doctor
funny how despite all its capabilities, Flux if it EVER needs to show a nipple, even accidentally its so LOST that it just puts flesh colored gummy candies in their place
funny how despite all its capabilities, Flux if it EVER needs to show a nipple, even accidentally its so LOST that it just puts flesh colored gummy candies in their place
JDr. Furkan, could you make a video how to train multiple people, objects or styles in one training? Is it possible to train a person, a style and an object in the same time?
Fmultiple people really hard they bleed
Fyou need to have them in same picture
Fi plan that
Dwe can get good people loras in around 2k steps, but what about concepts? does that require more learning? like unique physical characteristics and such
Fit is hard to tell that is why you should save checkpoints and compare
Fmy 256 images was best at 80 epoch
JMaybe I overlooked the video, do you also have a good tutorial on training with Dreambooth? When using 20 images, can I use 200 epoch like the Lora training? Is there a general rule of thumb regarding amount of pictures vs epochs?
Fyes all same
Fjust use my configs
JBased on your experience what is the recommended amount of pictures and epochs for getting the best results without overfitting? Lora/Dreambooth?
JIn my last Lora training I used 20 pictures, 200 epochs and Rank_3_18950MB_9_05_Second_IT, it took almost 5 hours to complete. when I use 40, 60, 80 or 100 pictures, how many epochs would your recommend, is there a rule of thumb?
Fsadly no rule of thumb
Fbut for 15 images i get 150 epoch best
Ffor 256 i got best at 80 epoch - it was on 8 gpu batch size 8
Ffor 256 images 40 epoch was undertrained with batch size 1
JThanks for your fast answer, so it's more trial and error then
JI am now training an interior style 14 pictures with 200 epochs...I am curious what the quality will be
DI get error when using ultimate imageprocessor: too many open files. Why?
Dnow it says "cannot load backend tkagg which requires tk interactive framework. headless is currently running"
What deos this mean?
What deos this mean?
Dnevermind. fixed above issues. nnot sure how i fixed the second one but after restart it worked. and changing file description limit via terminal.
Finteresting
E@Furkan Gözükara SECourses Hello! I'm using RTX4090 (24Gb)
For full FLUX finetuning I used your config "Rank_1_15500MB_39_Second_IT.json" and It took me 16.5 hours to train 15 images dataset.
Then I tried the config "Quality_1_23100MB_14_12_Second_IT.json" and It took me 23.5 hours to train the same dataset
Why the training goes slower on the second config although it is more vram consuming?
For full FLUX finetuning I used your config "Rank_1_15500MB_39_Second_IT.json" and It took me 16.5 hours to train 15 images dataset.
Then I tried the config "Quality_1_23100MB_14_12_Second_IT.json" and It took me 23.5 hours to train the same dataset
Why the training goes slower on the second config although it is more vram consuming?
Fit means that your initial vram usage was a lot
Fthus you should do this
