π *** If you love it, like it! ***π
workflow: https://civarchive.com/models/1088678
π Cristin Milioti π¬
About my celebrities loras
90% of the dataset used to build my loras only use head images. That really help the blend with other lora or model as there is no hands, feet, that may or will interfere in the final image render. When you get distorted hands with a person lora, it's because there is info on hands in the dataset used to train the lora, but that will not happen with my loras.
I've trained on Flux.1 Dev so other merged or trained checkpoint may not work well with my loras.
The drawback side of that is that the body may not be reflecting the reality. It may not be a drawback tho.
This is a lora for Flux.1 Dev. Work with other model but you must drop some simple bloc (good start 19-32).
Trained with ai-toolkit, so merging it is not easy.
To get the best result
Guidance: 2.2-3
Steps (dev): 30-40
daemon detailer (laying Sigma Sampler): factor: -0.02, start 0.06, end 0.7
Resolution: Upscale the latent by 1.25 or 1.5 you'll get awsome result. (take longer time but worth it)
Trigger word is (may work better in certain context): ohwx
Enjoy!
Description
V1, initial release
FAQ
Comments (5)
Hi, thank you again for making such high quality loras. I am trying to understand how best to use your loras alongside other loras in a workflow.
You wrote " Work with other model but you must drop some simple bloc (good start 19-32)." so i tried weighting all blocks 1.0 and weighting single blocks 19-32 as 0 with kijai's block lora select, but it unfortunately took away all likeness from your lora.
Was that the correct way of doing it? I have not really played with blocks like this before so this part is new to me.
Thank you!
When i say it work, yes it do work but my loras was trained on Flux.1 Dev, so the best result you'll get it with flux DEV. I saw somewhere that training directly on other model may resulting on a working lora for that model BUT, I do not get those awsome result with kohya that I get with ai-toolkit, despite i'm using the same methode/settings. So when i use my lora, i use Flux.1 Dev and when i want to generate image only, i do use other model, like Jib, that is very good.
@bissonfrederic69429Β Hi, thanks for the response. I am using base flux dev. I just meant I was trying to use your loras alongside another lora at the same time. For instance using your Cristin lora here with a style/concept lora when generating.
@EnragedAntelopeΒ Oh, there should be no problem. My person lora also blend very good with other loras.
@bissonfrederic69429Β Awesome, thanks!