π *** If you love it, like it! ***π
workflow: https://civarchive.com/models/1088678
πDaisy Ridley & Rey Skywalkerπ¬
About my celebrities // character loras
The dataset used to build this lora is a mix of celebritie face and character in context images.
To get the celebritie only, you can use the trigger word, and not the other one: ohwx woman
To get the character, you can use all, or a mix of ohwx woman along with other trigger words mentionned in the description.
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 (I start with 2.2 as it give me best result, but if the image is deformed or color are washed, I rise up that number until full satisfaction)
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)(I usualy use 1.4, that give me outstanding result but sometime it add a strange color frame around the picture)
Enjoy!
Description
V1, initial release
FAQ
Comments (10)
Thank you!
welcome, I hope you'll enjoy it. Read the description as changed it.
which checkpoint did you use for the examples?
flux.1 DEV fp8
workflow should be in the png of the image, as there is more than just using the model to generate that quality
@bissonfrederic69429Β Thanks, Yes I am aware but always looking to learn from others. Am experimenting with the Daemon Detailer at the moment.
@MakeThemComeAliveAIArtΒ i'll share a simplified version of my workflow soon, maybe tonight. I need to test it first.
@MakeThemComeAliveAIArtΒ I've shared a simplified workflow to use with Flux.1 Dev and my loras.
best daisy lora by far. your focus on headshots appears to be the trick for achieving consistent likeness
yup ;). i found that even if I train only on face and some shoulder to head shot, flux still know how to do the rest; background, full body shot and such. so all the data in the lora keep info on face details.