My first attempt at creating a lora containing both a style and characters feedback is appreciated, I used 200 total images from the show, 75 of them being random characters, scenery, etc and 25 for each character, overall I think it turned out alright but I will train it again because some of the characters aren't consistent and sometimes the style isn't as visible. trained here on civitai using Pony Diffusion V6 XL as a training model at 1024

Style info:

• trigger word: kan_style

• weight: 1 is perfect

Characters info:

• Trigger word - looks tag

  1. Kim: kimaps - long hair, orange hair, green eyes

  2. Monique: moniiqkue, black eyes, black hair, dark-skinned female, dark skin

  3. Bonnie: bomnkinie, short hair, brown hair, green eyes

  4. Ann: ankkiin, brown hair, short hair, blue eyes, doctor, lab coat

  5. Shego: shmeikgo, black hair, long hair, green eyes, gloves, bodysuit, lipstick

Additional information:

• Webui I use

• VAE I use

• 4x-Ultrasharp as an Upscaler

• Imagine dimensions vary depending on what I'm trying to do

• Sampling steps I go 20-30

• hires steps I go 8-15 (I don't always use hires fix)

• Denoising strength I go 0.4

• I use 7 CFG Scale and CFG Scale Fix set at 9

• uddetailer for faces, I use mediapipe_face_mesh set Dilation to 50 and Y offset to 30 to get the full face

I do all of my lora training here, if you can spare any buzz I would appreciate it