you normally can't, this was an experiment that required code changes and is 3x slower than normal
you normally can't, this was an experiment that required code changes and is 3x slower than normal
Nwhoa
NI would be realliy curious to try, but FLUX is already painstackingly slow on my machine, so I can only speculate 
Mwait what!
M@Dr. Furkan Gözükara doc what do you think of this node, is it acuurate?
D?
Mthis is huge for flux
Dhave you seen that?
I'd much rather train it into a LoRA
I'd much rather train it into a LoRA
Fyou can convert them to fp8 but i dont know gguf lora
Ftheir demos are excellent
Fbut the app doesnt produce that quality atm
Fauthors said they will fix issues
Fi am following repo
Fyes waiting first day to buy hopefully
Fmy machine almost ready
F
Fcurrently running 9 hours Prime 95 so far good
Fi say worthless 
Fbut authors said they are working supir v2
Falthough not sure if will be public
Fyou can use de-disttiled model
Fit has negative prompt
FMedium
Thoroughly experimented with Fine-Tuning / DreamBooth training of Flux-dev-de-distill, PixelWave v03, Verus Vision and base FLUX Dev model…
Fi used them in past but with flux doesnt use anymore :d
Fno needed
Fhow far do you think we are from having veo 2 quality video models at home
WIt's because you dont know how to prompt with some tweak in ComfyUI, Flux is mile ahead of SD 1.5. Let me show you some images
W
W
�Has anyone used a Lora on a dreambooth?
Ais it the same as Q8? in terms of quality
JWhat you mean?
�I mean loading up a lora with a trained dreambooth instead of base flux dev
J@Furkan Gözükara SECourses Ive done dreambooth training on this Flux Checkpoint https://civitai.com/models/161068/stoiqo-newreality-flux-sd35-sdxl-sd15?modelVersionId=979329
But somehow i cant extract the lora from it, doesnt matter if i use the Full or the Pruned Model, do you know why that is?
But somehow i cant extract the lora from it, doesnt matter if i use the Full or the Pruned Model, do you know why that is?
�Is multi gpu dreambooth training possible?
�Has anyone tried training dreambooth on a 80gb card?
TPro tip: if you are getting low quality results when upscaling image with flux img2img always use at least 0.15-0.2
Took me a while to figure it out
Init Image Reset To Norm. Upscale artefacts you see are the result of SwarmUI upscale init image to target resolution BEFORE it is VAE encoded. This works WAY better than increasing image creativity.Took me a while to figure it out
Gin this video A1111 web ui is no longer supportednow stabilitymatrix is there how to go ahead then
THank you
THank you
A
P@Dr. Furkan Gözükara i asked ChatGPT 4o about blockswap and it linked your video 
Ptweaks like? my only trick is to prompt clip and t5xxl on their own format separately
NNah man, these are too artificial. But we might have different standards and it's ok)
NFLUX is great but way too inflexible at the moment.
Fsadly no idea atm.
Fno de-distilled is differently working. it uses cfg 3.5 so you can use negative prompts
Fmust be kohya not supporting yet
Fyou have to open issue thread
Fpreviously he wasnt supporting training even de-distilled model