I trained a flux lora on cicitai, and for testing i went with a real person. On generations, skin ge

I trained a flux lora on cicitai, and for testing i went with a real person. On generations, skin gets plastic and shiny...not like my dataset. Using heun beta 30 steps. Curious about what might cause this

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭I trained a flux lora on cicitai, and for testing i went with a real person. On ...

Furkan Gözükara SECourses•6/18/25, 10:34 AM

civitai training weak

Furkan Gözükara SECourses•6/18/25, 10:34 AM

see my latest tutorial i shown myself trained result

Furkan Gözükara SECourses•6/18/25, 10:35 AM

https://youtu.be/Xbn93GRQKsQ

YouTubeSECourses

WAN 2.1 FusionX is the New Best of Local Video Generation with Only...

FusionX: The BEST AI Video Model? + FLUX Hyper-Realistic Upscaling (One-Click Setup!). Struggling to create high-quality AI videos and hyper-realistic images? This tutorial is your ultimate solution! I'm introducing the incredible new Wan 2.1 FusionX model and a game-changing 2x latent upscaler for the FLUX model, all made incredibly simple with...

Furkan Gözükara SECourses•6/18/25, 10:35 AM

13:48 Generating a High-Quality Image with The Official FLUX Preset
14:50 Using Automatic Face Segmentation & Inpainting with FLUX
16:05 The Ultimate Upgrade: Applying The FLUX 2x Latent Upscaler Preset
16:32 Final Result: Comparing Standard vs. 2x Upscaled Image Quality
16:50 Outro & Sneak Peek of The New Ultimate Video Processing App

Original message was deleted

mlado•6/18/25, 4:14 PM

Scammer

TheRealDude•6/18/25, 10:12 PM

TheRealDude•6/18/25, 10:13 PM

Using a different model than Flux with my Lora looses the likeness. Is it possible to train a LoRA based on a Flux Model other than the Flux itself ?

TTheRealDude Using a different model than Flux with my Lora looses the likeness. Is it possib...

Furkan Gözükara SECourses•6/18/25, 10:41 PM

yes any flux variant

Furkan Gözükara SECourses•6/18/25, 10:41 PM

you can train

FFurkan Gözükara SECourses yes any flux variant

TheRealDude•6/19/25, 7:20 AM

should I check and verify the weigths ect as in the 1st place mixing my lora with that model is altering my model details or it'll be done automatically?

TTheRealDude should I check and verify the weigths ect as in the 1st place mixing my lora wit...

Furkan Gözükara SECourses•6/19/25, 3:12 PM

well it will be different

Furkan Gözükara SECourses•6/19/25, 3:12 PM

if you have trained on another base model

Furkan Gözükara SECourses•6/19/25, 3:12 PM

but probably with flux i assume it would work decent

Furkan Gözükara SECourses•6/19/25, 3:12 PM

since flux fine tunes are not so much different

Furkan Gözükara SECourses•6/19/25, 3:12 PM

usually

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭I trained a flux lora on cicitai, and for testing i went with a real person. On ...

LukeJoseph•6/20/25, 2:22 AM

Have any examples to share? If not that’s fine. Just curious how “plastic” it is. Plastic type skin is pretty inherent with Flux regardless. I have read there are some Loras that can help, I am testing way too many different things at the moment so can’t suggest.

And everything I have read training to Flux 1 Dev is by far the best.

What other models are you training when you say it looses its likeness?

pianogospel•6/20/25, 11:46 AM

Dr Furkan, I saw you released an update for SDXL finetunning today, 20/june. Are you planning any update for FLUX finetunning or your last release for FLUX are the best yet?

Ppianogospel Dr Furkan, I saw you released an update for SDXL finetunning today, 20/june. Are...

Furkan Gözükara SECourses•6/20/25, 11:53 AM

i recently tested flux fine tuning with more than 20 experiments

Furkan Gözükara SECourses•6/20/25, 11:53 AM

none yielded better

pianogospel•6/20/25, 1:38 PM

Dr using your tutorial and trainning a FLUX finetunning in Massed Compute, about choosing the GPU, is there a better GPU to choose? For better I'm only considering faster trainning and the relation cost x benefit, I know that the prices increase. I don't understand one thing, if I choose a H100 x8, or a 8 H100 boards, is it eight times faster than an 1 H100? or it doesn't work this way? Can you tell me what is the best board option in Massed Compute, ignoring price, for a 100 images finetunning of a person?

Ppianogospel Dr using your tutorial and trainning a FLUX finetunning in Massed Compute, about...

Furkan Gözükara SECourses•6/20/25, 1:51 PM

for lora it will be almost 8 x

Furkan Gözükara SECourses•6/20/25, 1:51 PM

but for dreambooth last time i tested it wasnt working properly

Furkan Gözükara SECourses•6/20/25, 1:51 PM

best price performance is RTX a6000 ADA i think

pianogospel•6/20/25, 2:33 PM

In your post, about Dreambooth finetunning, you said: "...single RTX 4090 is almost same speed as RTX A6000 for Fine Tuning." Does it mean that if I have a RTX 4090 can I train, locally, at the same speed as a RTX a6000 that has 48gb of vram, double vram than mine 4090?

Ppianogospel In your post, about Dreambooth finetunning, you said: "...single RTX 4090 is alm...

Furkan Gözükara SECourses•6/20/25, 2:42 PM

4090 is faster when fits into VRAM. current not fitting but with block swapping it matches almost

Furkan Gözükara SECourses•6/20/25, 2:42 PM

what is your second / it ?

Furkan Gözükara SECourses•6/20/25, 2:42 PM

5090 is almost twice faster than A6000 since fits into VRAM fully

pianogospel•6/20/25, 2:56 PM

So, if I choose the file 16GB_GPU_15150MB_11.6_second_it_Tier_1 to train a FLUX finetunning, my 4090 is better than a RTX A6000? Is it right? I imagine that I can't choose the 24GB_GPU_22900MB_7.3_second_it_Tier_1 because it's to close to use the full amount of memory, right?

Ppianogospel So, if I choose the file 16GB_GPU_15150MB_11.6_second_it_Tier_1 to train a FLUX ...

Furkan Gözükara SECourses•6/20/25, 5:09 PM

true

pianogospel•6/21/25, 3:20 PM

Dr, is 6.36s/it a good velocity to 16GB_GPU_15150MB_11.6_second_it_Tier_1 config in a 4090, locally?

Ppianogospel Dr, is 6.36s/it a good velocity to 16GB_GPU_15150MB_11.6_second_it_Tier_1 conf...

Furkan Gözükara SECourses•6/21/25, 6:09 PM

yes really good

PabloMoises•6/23/25, 11:48 PM

Hi! Does anyone know if it's possible to upload a fine-tuned model to Replicate to use it via API? And if someone knows, could you give me a mini step-by-step tutorial on how to do it?

Thanks a lot!

PPabloMoises Hi! Does anyone know if it's possible to upload a fine-tuned model to Replicate ...

Furkan Gözükara SECourses•6/24/25, 10:20 PM

yes possible

Furkan Gözükara SECourses•6/24/25, 10:20 PM

but you aint gonna find tutorial it is only useful for companies

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭OP•6/25/25, 8:59 AM

if i were to train a finetune on say norwegian women, to better capture their looks, say i have 5 models with maybe 10 photos each i use for this. would this be an example of where we use captions? @Furkan Gözükara SECourses

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭if i were to train a finetune on say norwegian women, to better capture their lo...

Furkan Gözükara SECourses•6/25/25, 10:57 AM

yes for general fine tuning you can use captions

Furkan Gözükara SECourses•6/25/25, 10:57 AM

but you need more photos

�

🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭OP•6/25/25, 11:03 AM

Ok. The other plan was to train 5 woman loras, then use all on low weight, without triggerword and prompt the womans looks.

�🍭🎀 𝒜𝓋𝒶 𝐹𝓇𝒾𝑔𝑔 🎀🍭Ok. The other plan was to train 5 woman loras, then use all on low weight, with...

Furkan Gözükara SECourses•6/25/25, 11:26 AM

each lora may overwrite each other but you can try

FFurkan Gözükara SECourses yes possible

PabloMoises•6/25/25, 4:23 PM

Thank you very much! I'm going to try anyway because I really need it, if anyone knows of something that could help me, I would truly appreciate it.

Flame火•6/27/25, 1:09 PM

Hey everyone, looking for a quick sanity check on my training parameters before I commit my resources. I've done my best to prep everything properly.

Model: Flux (via fluxgym)

Goal: A flexible character LoRA with two distinct styles (style_A and style_B).

Dataset: 98 high-quality, curated images.

Variant A (Core/Black Hair): ~55 images

Variant B (Secondary/Lighter Hair): ~43 images

Shot Distribution: ~14% full-body, ~38% medium, ~48% close-ups.

My Proposed Parameters: Repeats: 4, Epochs: 24, Batch Size: 2, Total Steps: ~5040 (approx. 51 steps per image), Unet LR: 1e-4, Text Encoder LR: 5e-5, Scheduler: cosine, Save every N epochs: 2

Does this recipe look solid for a high-quality Flux character LoRA? Any red flags or suggestions? Thanks!

FFlame火 Hey everyone, looking for a quick sanity check on my training parameters before ...

Furkan Gözükara SECourses•6/27/25, 1:47 PM

well i only can recommend our researched training config

Furkan Gözükara SECourses•6/27/25, 1:48 PM

but image distribution is sounding good

Furkan Gözükara SECourses•6/27/25, 1:48 PM

however different styles will get bleed into each other

FFurkan Gözükara SECourses well i only can recommend our researched training config

Flame火•6/27/25, 2:04 PM

Thanks, I really appreciate you taking the time.

Your point about style bleeding is exactly why I set up the style_A and style_B tags in my captions—I'm hoping that gives me the control to call them separately.

you mentioned your researched training config. Is that publicly available anywhere? I'd love to read up on it and compare it with my setup to make sure I'm on the right track.

FFlame火 Thanks, I really appreciate you taking the time. Your point about style bleedi...

Furkan Gözükara SECourses•6/27/25, 2:06 PM

with flux they bleed sadly

Furkan Gözükara SECourses•6/27/25, 2:06 PM

my configs are on patreon

Furkan Gözükara SECourses•6/27/25, 2:06 PM

https://youtu.be/FvpWy1x5etM

YouTubeSECourses

FLUX Full Fine-Tuning / DreamBooth Training Master Tutorial for Win...

If you want to train FLUX with maximum possible quality, this is the tutorial looking for. In this comprehensive tutorial, you will learn how to install Kohya GUI and use it to fully Fine-Tune / DreamBooth FLUX model. After that how to use SwarmUI to compare generated checkpoints / models and find the very best one to generate most amazing image...

FFurkan Gözükara SECourses with flux they bleed sadly

Flame火•6/27/25, 2:38 PM

Based on your warning, I'm now planning to train two separate loras as the safest path

Before I separate the dataset, I had one last quick question about the "style bleed." Was your experience with this happening on Flux even when the underlying facial identity was identical across both styles?

I ask because my dataset uses the exact same face model for both my "styles," with the only changes being things like hair color and subtle makeup. I'm trying to understand if flux is so powerful that it still blends even those subtle, correlated changes, or if the bleeding happens mostly when training on two more distinct concepts (like different characters or art styles).

FFlame火 Based on your warning, I'm now planning to train two separate loras as the safes...

Furkan Gözükara SECourses•6/27/25, 9:46 PM

yes with flux if what you train has same genre it will bleed

I trained a flux lora on cicitai, and for testing i went with a real person. On generations, skin ge

Similar Threads

Similar Threads

Similar Threads