I have just started with Flux, but using onetrainer and bf16 I am below 12 GB vram... 🤨
I have just started with Flux, but using onetrainer and bf16 I am below 12 GB vram... 
Dor do you mean the base model in fp16, not the Lora weights?
Dif so, I doubt that makes a difference. even during inference there is not much different between fp8 and NF4
Ffor fp16 you have to reduce resolution
Fno other way
Fhe means training
D? I also mean training
DI'm just saying that even during inference a low-precision base model doesn't make a difference, so how would it during training. The Lora weights are still bf16+
Dfascinating how Flux learns without any distortion. it just slowly adjusts
Fit makes some
Fnot very dramatic
DI'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
