👍 *** If you love it, like it! ***👍
workflow: https://civarchive.com/models/1088678
👑 Naomi Watts (2000s) 🎬
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 (lying sigma sampler): factor: -0.02, start 0.06, end 0.75
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
v2, improved likeness and added some picture of her from King Kong movie.
FAQ
Comments (3)
"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.
...
The drawback side of that is that the body may not be reflecting the reality."
This is interesting, but I have a suggestion, if you don't mind (I was wondering why nobody had done a Naomi Watts LoRA yet btw, my own coming soon): to avoid the issue you describe, you can use mostly headshots, however, also include a couple of full-body shots, and a couple of upper-body shots. As long as the majority of the images are face/head and shoulders, it's okay to include some body images, it's not going to ruin the Lora unless they're standing in an awkward way. Not a criticism or anything, it took me lots of trial and error to realize this.
that's exactly what I do, 10% is full body so flux know how to handle proportion. But the body itself, i only capture it for character or when the person have a very unusual shape, too tall, skinny, fat...
@bissonfrederic69429 Oh, okay. Your description made it sound otherwise. Regardless, looks good, I'll be trying this later.