A model of Ashley Graham, trained over 62 images for 1024 using AAA as a training model

Normal:

• Trigger word: ashgrahamley

• Looks tags: blonde hair, short hair, green eyes, red scarf, orange jacket, orange sweater, green skirt, plaid skirt, black pantyhose, brown footwear, knee boots

• Weight: 1 to 0.5 (0.7 is recommended)

Casual:

• Trigger word: ashcasualley

• Looks tags: multicolored hair, blonde hair, short hair, pink hair, green eyes, eyeliner, hair over one eye, black collar, necklace, black shirt, striped sleeves, mismatched sleeves, blue sleeve, pink sleeve, fingerless gloves, fingerless gloves, striped gloves, bracelet, ring, black belt, multiple belts, white shorts, purple pantyhose, pantyhose under shorts

• Weight: 1 to 0.5 (0.7 is recommended)

Romantic:

• Trigger word: AshRomanticley

• Looks tags: short hair, white hair, green eyes, white ascot, white shirt, red chest jewel, black pants

• Weight: 1 to 0.5 (0.7 is recommended)

Additional information:

• Webui I use

• AAA Anime VAE SDXL v1_4 as VAE

• Sampling method: Euler a

• Schedule type I set it to automatic

• Sampling steps I go 20-30

• 4x-Ultrasharp as an Upscaler

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

• Denoising strength I go 0.4

• Upscale by 1.2 to 1.5 depending on the starting image dimensions

• Detail Daemon at default settings

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

• I use 5 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