Zamasu [3 Versions • Dragon Ball]

Details

Download Files

Model description

A model of Zamasu, trained over 101 images for 1024 using AAA as a training model

Zamasu:

  • Trigger word: Zambaseasu

  • Looks tags: colored skin, green skin, mohawk, white hair, grey eyes, pointy ears, potara earrings, single earring, green earring

  • Clothes tags: purple shirt, long sleeves, shirt under tunic, black tunic, shoulder pads, yellow trim, gold button, blue sash, baggy pants, blue pants, boots, white footwear

  • Weight: 1 to 0.5 (0.7 is recommended)

Fusion Zamasu:

  • Trigger word: Zafmionasu

  • Looks tags: colored skin, green skin, spiked hair, white hair, super saiyan, grey eyes, pointy ears, potara earrings, green earrings

  • Clothes tags: black shirt, long sleeves, shirt under tunic, grey tunic, shoulder pads, red trim, gold button, red sash, baggy pants, black pants, boots, white footwear

  • Weight: 1 to 0.5 (0.7 is recommended)

Fusion Zamasu Half Corrupted:

  • Trigger word: Zamhalfasu

  • Looks tags: multicolored skin, two-tone skin, colored skin, green skin, purple skin, heterochromia, grey eyes, red eyes, mismatched sclera, colored sclera, ring, spiked hair, short hair, white hair, parted bangs, pointy ears, potara earrings, green earrings

  • Clothes tags: black shirt, long sleeves, shirt under tunic, grey tunic, shoulder pads, red trim, gold button, red sash, baggy pants, black pants, boots, white footwear

  • Weight: 1 to 0.5 (0.8 is recommended)

If you wanna support me ko-fi

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

Images made by this model

No Images Found.