Displays some images generated by stable diffusion, they are all about Japanese anime character Kikyo. The related Lora model was trained by the webmaster personally.
Demo images:
If you are a Chinese internet user, some images might not be viewable due to the Great Firewall of China.
stable diffusion txt2img prompt:
(masterpiece:1.331), best quality, finely detail, ultra-detailed, finely detail,Resolution Enhancement, Enhance Picture Quality, Elevate Image Resolution, HD Enhancement, Improve Image Definition, highres, 8k wallpaper, close-up, Kikyo, archery, white Japanese shrine maiden top, mature female, a woman in a red dress holding a bow and arrow in her hand while standing next to a tree, forest, sky, long black hair, no other man,
Negative prompt:
EasyNegative, multiple girls, multiple views, extra fingers,(bad feet:2.0),fewer fingers,low quality, worst quality, text, watermark,sketch, duplicate, ugly,(text:2.0), logo, monochrome, worst face, (bad and mutated hands:1.3), (worst quality:2.0), (low quality:2.0), (blurry:2.0), (bad hands), (missing fingers), (multiple limbs:1.2), bad anatomy, (interlocked fingers:1.2), Ugly Fingers, (extra digit and hands and fingers and legs and arms:1.4), (long fingers:1.2),(bad-artist-anime),
Steps: 25, Sampler: DPM++ 2S a Karras, CFG scale: 7, Seed: 2491140323, Size: 512×512, Model hash: 54ef3e3610, Model: meinamix_meinaV11, Denoising strength: 0.35, Clip skip: 2, Hires upscale: 1.6, Hires steps: 15, Hires upscaler: R-ESRGAN 4x+,
AddNet Enabled: True,
AddNet Module 1: LoRA, AddNet Model 1: Kikyo(d1b2915e7170), AddNet Weight A 1: 1, AddNet Weight B 1: 1
Note:
You can use checkpoint CounterfeitV25_25 instead of meinamix_meinaV11 to get more cute images.
The lora file Kikyo-000003.safetensors also have a goog effect.
Lora model can be downloaded at the page:
