Has anyone used a Lora on a dreambooth?
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
Fsince they are trained with different scripts
Fyes with 80 gb
Fit works
Fnice tips. do you have any exact config can you share screenshot?
Fyou can manually install
For use our installer
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Fgood job
Fwell it is because it has no idea of block swap and searches google very likely 
BThe 48g 4090 is currently available for private consumers in China (you can buy it exactly), with no restrictions (such as not being able to run on Windows). The only downside is that due to the fully modified turbo fan, the noise is similar to that of a helicopter...
WThere so many, I must say some examples: detailer daemon, different t5xxl & clip text encode, separate prompt and prompt style ... so many I dont even remember. Especially when combine Teacache with Sage Attention I nearly get 3x render speed without losing any quality of an image. Here my example:
W
W
WFlux tend to make image more polished which people claim it's artificial. It depends on people taste, I agree. But for understanding prompt, I never going back to SD 1.5 and even SDXL. Flux is way ahead of prompt understanding enough to forgive its weakness which is styling an image.
Tno single config fits all cases, you always have to play around with creativity and normalisation settings depending on composition, upscale factor and how close you need upscale to be to original
TThis is what I would start with
Nthere is a huge difference between a raw photo (digital or analog) and a stylized photo (with filters) of a person (a portrait). If you work with photography your eye is trained on raw images and you notice when something is even slightly artificial. FLUX at it's current stage struggles a lot with creating raw portraits. With elaborate prompt you can get better results, but currently it is a struggle, whereas accordingly-trained stable diffusion 1.5 or XL custom models do this with ease. It would be great if one day there will be a more flexible FLUX version. That said, if you are looking to create studio-like portraits with retouched skin and filter effect, FLUX is very good. Just not for natural portraits, same as Midjourney btw.
A@Furkan Gözükara SECourses @Timson I'm planning as a next project to train shoes, jewellery and other objects. Should I follow the same concept of diversity as I did with the logo ?
Tyou'll have to figure out the peculiarities of each class, but the starting point would be the same process. It all depends on how each of your base classes are trained into flux
TDo you see real non placebo benefit in this? Do you use SwarmUI comfyUI flow customisation for this?
I did not follow up this research avenue because BFL is not leveraging it for flux pro API, seems counter-intuitive that they would ignore it if it was a viable way to improve outputs with no additinal costs
I did not follow up this research avenue because BFL is not leveraging it for flux pro API, seems counter-intuitive that they would ignore it if it was a viable way to improve outputs with no additinal costs
Pcomfy, yeah benefit is pretty decent
SDr Furkan I try to use the copuon in massconpute but have a error,, dont accept it, surely i make a error
Fhi, I'm trying to use flux fill in SwarmUI to replace an orange wristband over a subject in a photo with some ISO noise. I'm using the basic generation flow and it looks perfect except it's too perfect and doesn't have any of the ISO noise in the original photo.
Is there a way I can get the generation to also add in similar noise to the inpainted mask that I'm shrink growing? I'm at max creativity since otherwise the orange wristband still shows. you can see in this image clip
Is there a way I can get the generation to also add in similar noise to the inpainted mask that I'm shrink growing? I'm at max creativity since otherwise the orange wristband still shows. you can see in this image clip
Ttry reducing Mask Blur
Tor just second pass it with Flux Dev
AIs it possible to inpaint an image straight forward?
AAs init perhaps ?
Twhat do you mean by "straight forward"?
Alet's say I have a white board
Aand I want to inpaint a statistics graph
Awith details and stuff
Acan I do that by providing swarm the image