Recommned using 0.6-0.8 lora weight.
We have 9 style, all in 1 lora, and you can trigger by: "type0 - type8"
It's good with anime, realistic or fantasy style. Add "bridal veil" if you want.
For the example:
(type0:1.2),1girl, dress, solo, official art, a character portrait, contrast, hair covering face,long hair, solo, cloud, sky, standing on the street, colorful background, masterpiece, high res, ray tracing, CG, 8K, 32K, best quality, lookbook, realistic, ultra realistic, realistic photography, bridal veil
<lora:Wed_Collect:0.65>
Description
FAQ
Comments (5)
Personally, type 4 & type 7 is the most successful since they're more discernible than the other.
"Omega gutto jobu" - as some weeb gonna say.
firsttime I try to create multiple style, thanks for ur comment
@LahIntheFutureland Then while we are at it, may I give you an advice?
Most of your project are clothing related, then why not making lora to exhibit clothing & tied up everything?
Like a background lora regarding red carpet hall, fashion show catwalk, or modelling photoshoot since as far as I know no one making those.
@Random_Seafarer That's a truly great idea, I will take note of it and work on it in the near future. After releasing the first checkpoint (which is currently taking up a lot of my time), I will prioritize implementing this idea. Thank you so much for bringing it to my attention. Once again, thank you very much!
@LahIntheFutureland Don't mind it, I don't have to train all the dataset myself is already good enough.
You got nice idea while I got already teained dataset, that's an equivalent exchange fullmetal alchemist style.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.