This LoRA is trained on screenshots from the K/DA All Out's "More" music video. It features the members of K/DA, namely Ahri, Akali, Evelynn, Kai'Sa, and Seraphine from League of Legends. Thus, it can recreate both the style and characters from the music video. This model is trained on Pony Diffusion V6 XL, so it possesses Pony's ability.
Usage Tips:
Use with Pony Diffusion or a Pony-based model.
Trigger words:
ahri,akali,evelynn,kaisa,seraphineUse with a pony prompt.
Description
This LoRA is trained with screenshots from the K/DA All Out's "More" music video on Pony Diffusion V6 XL.
FAQ
Comments (10)
Looks like it was trained on the (relatively) low bitrate 1080p version of the video from youtube.
I think I have picked highest quality from Youtube but many times character needed to zoom in. (If you have any better source, you can suggest me)
@titansteng Would it not be better to AI upscale the zoomed in images then?
@onyaashou362
I have a plan to use LoRA to upscale the dataset. I don't like the results of the already provided AI upscaler, but maybe it's ready enough if I just need to try harder.
@titansteng "I don't like the results of the already provided AI upscaler". I use Topaz AI to upscale. Gives much better results than SD upscalers to upscale/enhance a dataset.
acording to automatic1111 the keyword for seraphine is seraphin
🤣miss spelling! but seraphine still work any way.
@titansteng yeah, i suppose it will call both, the lora and the info from the checkpoint in case has that tag too. i tried and is kinda the same.
This blends with my favorite styles very well. Thank you!
My favourite group! Aw yeah! 👍
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.