A LORA entirely based on Neneko’s GSHADE presets, the ones that give you Pop Art type style without it being disturbing.
What happens when dusk doesn’t have enough pictures of anyhting BUT their miqote and trains a LORA with no text encoder?
Yea this.
No tag word.
Reccomended strength: YOUR CHOICE, but it hardline produces ONE face above .6 – I should’ve had more content but i don’t have gshade installed.
If you got requests, or concerns, We’re still looking for beta testers: JOIN THE DISCORD AND DEMAND THINGS OF US: https://discord.gg/Da7s8d3KJ7
Listen to the music that we’ve made that goes with our art: https://open.spotify.com/playlist/00R8x00YktB4u541imdSSf?si=b60d209385a74b38
We stream a lot of our testing on twitch: https://www.twitch.tv/duskfallcrew
any chance you can spare a coffee or three? https://ko-fi.com/DUSKFALLcrew
Generation sites MAY use this as long as request/credit is given.
We are NOT RESPONSIBLE FOR YOUR use/downstream anything with this model.
DO NOT PRODUCE ILLEGAL CONTENT WITH THIS MODEL – we’re still not responsible, we just said don’t do it.
DO USE THIS.
Do feel free to ask for the safe tensors in another repo!