Lofi Style版本V1.0 (ID: 10133)

This is my new Model! If you want your own style/person trained, just DM me with a dataset of ~20 imgs on discord Flonix#4022 and ill train it for you!

Lora made on Spaceginners Lofi Dataset, set the weight lower than 1 to get it to follow your prompt more, no Tag needed. Also remember to set CLIP skip to 2.
Use with openjourney 2 for maximum MJ style
Keep in mind this is LoRA, so you need to use it as such. It's not a standalone model and it's not a TI.
may do accidental nsfw
How to use LoRA's in auto1111:

• Update webui (use git pull like here or redownload it)

• Copy the file to stable-diffusion-webui/models/lora

• Select your LoRA like in this video

• Make sure to change the weight (by default it's :1 which is usually too high)

usage by @Lykon

描述:

For image gen, run it in txt 2 img with lora enabled at around 0.8 then through a sd upscale with 0.3 denoise

Example settings:

landscape image of a japanese city, Lofi Style
Negative prompt: text
Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 3483891498, Size: 648x896, Model hash: fc52756a74, Clip skip: 2, ENSD: 31337, AddNet Enabled: True, AddNet Module 1: LoRA, AddNet Model 1: Lofi Style(64d4ee6b2777), AddNet Weight A 1: 0.65, AddNet Weight B 1: 0.65

训练词语: lofi style