Patreon
Get early access to build and test build, be able to try all epochs and test them by yourself on Patreon or contact me for support on Discord
Recommended settings
Make sure you are aware on the usage instructions of LORA
Sampler: DPM++ SDE Karras (Recommended for best quality, you may try other samplers)
CFG Scale : 5 to 10
Lycoris weight for txt2img: reccomended 0.35
Those are a Lycoris, to use it you need to install the proper extension on Stable Diffusion.
Insutrctions
My advice is to start from the prompt of the posted images on civitai, or in any case use most of the keywords with 1.2-1.3 weight.
In general if you want a classic wonder woman suit you just need to use the keyword "wearing wonder_woman_cosplay_outfit" maybe with a weight if necessary.
in other cases you need to mix keywords with different weight depending on the model and colors you pick.
Enjoy!
If you'd like to support my efforts and have access to early and bleeding edge builds, please think about joining my Patreon: https://www.patreon.com/betterCuteAsians
Description
Not sure why but this model seem to generate watermarks in most of the images even if none of my training set images has a watermark.
I used absoluteReality by Lykon to generate the images i dont think thats the problem, but feel free to try other checkpoints.
I'm not very happy about the quality of the images i'm posting but today i didnt have much time to experiment with this model, i invite you all to experiment with it and post better images then mines for other people, generation data would be nice.
adviced weight: 0.35
for keywords weight look at example images, all have generation data.
FAQ
Comments (3)
More than 330mb for each outfit?
Have pity!
LyCORIS occupy much more space then normal LoRA, also realistic models occupy much more space then anime ones. thats what you have to expect for a realistic LyCORIS fusion.
Great model, but her tiara looks weird almost all the time. I hope to see the next version with a separate prompt for her tiara