A model of Sasha Calle with her role as supergirl in the flash 2023, trained over 88 images at 1024 using Pony Diffusion V6 XL as a training model

Normal:

• Trigger word: sascalleha

• Looks tags: brown eyes, short hair, black hair

• Weight: 1 to 0.5 (0.7 is recommended)

Supergirl:

• Trigger word: ssascalleha

• Looks tags: brown eyes, short hair, black hair, blue bodysuit, bodysuit, red cape, long sleeves, red bodysuit, two-tone bodysuit, multicolored bodysuit

• Weight: 1 to 0.5 (0.7 is recommended)

Additional information:

• Webui I use

• VAE I use

• 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

• Negative embedding I used

• Detail Daemon for additional detail, I set the Detail Amount 0.2, Start 0.1, End 0.9 and I leave the Bias at default at 0.5

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

• 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

描述:

训练词语: sascalleha,brown eyes, short hair, black hair,ssascalleha,brown eyes, short hair, black hair, blue bodysuit, bodysuit, red cape, long sleeves, red bodysuit, two-tone bodysuit, multicolored bodysuit