flux-dev can train only one subject, but with flux-dev-de-distill I can learn many concepts
flux-dev can train only one subject, but with flux-dev-de-distill I can learn many concepts
WMost of us dont know chinese, oh well
V@wardensc2 I just use google translate to change the text.
Dyes but is too slow... now I'm training on my 3090ti, may be then I will try on mass compute
OI don't think I've ever tried to train a finetune with more than one subject
Wbut when you access to their server, their GUI also chinese, what will you do = )))
V@wardensc2 Click translate in the browser, lol.
V
Dyes but the quality is much worse... now I'm full on flux-dev-de-distill
WAlso @Dr. Furkan Gözükara already set up kohya_ss for quick install on Mass Compute, I just need 1 console code for it to run everything
Wno this is only the beginning
Wsimilar to masscompute, you have to upload your image training data and the checkpoint you want to train, vae, clip and install Kohya as well
Wit similar to our local PC but better hardware, it's not one click training.
WNo I guarantee when it come to people image, install ID is much better than lora if you know how to use it properly
WI'm not sure I can upload AI image of my instant ID for you to see on discord
WI make Mbappe Instant ID, not sure SDXL lora can beat it
DI know what you mean I try it, but the quality over all is much better on flux
DSDXL is good but not as good
Wof course I dont compare with Flux but SDXL lora can't beat Instant ID
V@wardensc2 I understand. Im just pointing at the price difference.
NVIDIA L20 / 48GB single precision 59.35 TFLOPS / semi precision 119.5 Tensor TFLOPS ￥ 4.19 / hour
USD is 0.60 an hour.
NVIDIA L20 / 48GB single precision 59.35 TFLOPS / semi precision 119.5 Tensor TFLOPS ￥ 4.19 / hour
USD is 0.60 an hour.
VNVIDIA L40 / 48GB single precision 90.5 TFLOPS / semi precision 181.05 Tensor TFLOPS ￥ 4.82 / hour
$0.69 USD
$0.69 USD
DIDK with a well trained lora you get perfect likeness and more flexibility
Wyes I know but when you using it, you can't translate everything if the operating system and other support software are also chinese
VI see, your saying the whole OS would be in chinese.
Dbut its ok if works for your purpose
VMaybe Dr. Can team up with them and have them make an option for flux training preconfigured.
Wnormally I just gen a image with style and pose I want then apply Instant ID on it. SDXL lora can't flexible than this
Wsomething like this
Dlooks very good
Wthis is SDXL not Flux
Ois instant id coming to flux?
Wmore fantasy ways
WI haven't heard it yet
Odoes swarmui support de-distilled?
VOS commands are still the same, just some text is Chinese.
V@OinkSauce If its .safetensor or .gguf it should work fine.
Othanks - just tried it and it inferenced, but gave me essentially a static image. does it have its own vae etc?
WWell I try to register but it does not have my country phone number, so bye bye
HHi, does anyone know the difference between de-distilled and the standard flux model? When I tried it, using an RTX 3090, I usually get output with flux in 30 seconds, but with de-distilled it took 120 seconds, and the image quality felt lower compared to the standard flux. I’m referring to the flux dev version
Wit's the model for training only
Wdont bother to generate
V@wardensc2 What country is missing for you?
Wvietnam
W= )))
Oahhhh
VJust get someone from the us to get the text code for you.
WI can use fake IP but MassCompute is enough for me
VDoes masscompute require a vpn for you?
WNo
WI can work straight
HOHH this is great. Is it for LoRA training or fine-tuning? I’ve been away from home for about a week, and I was finally excited to train a flux LoRA this night. Should I train my LoRA with the de-distilled version? By the way, I will be training a style LoRA
