模型介绍: ※A LoRa model trained by a friend with multires noise. This is a LoRa model that trained by 60+ img generated with NijiV5,and it's the multires noise version. This model can generate exquisite light and delicate-style backgrounds. weight 0.8-1.0 maybe generates better imgs. It's a experimental work,Hope you found it usefulミ(・・)ミ ~~~~~~~~~~~~~~~~~~~~~~~o(* ̄︶ ̄*)o~~~~~~~~~~~~~~~~~~~~~~~ 示例提示词和参数: Prompt: 1girl, plant, solo, jewelry, earrings, potted plant, black hair, dress, looking at viewer, short sleeves, bangs, blush, brown eyes, floral print, indoors, bracelet, standing, shelf, short hair, hair ornament, print dress, nail polish, blue dress, medium hair, braid, chinese clothes, closed mouth <lora:oldtime:1> Negative prompt: extra fingers,fewer fingers,(low quality, worst quality:1.65), (bad anatomy), (inaccurate limb:1.2),bad composition, inaccurate eyes, extra digit,fewer digits,(extra arms:1.2), Steps: 20, CFG scale: 7.5, Sampler: DPM++ 2M Karras, Seed: 892956226, ENSD: 31337, Size: 448x832, Model: 969-5, Model hash: b2e1bf1214, Hires steps: 20, Hires upscale: 1.8, Hires upscaler: Latent (nearest-exact), Denoising strength: 0.56, Clip skip: 2 |
2人表示很赞