模型简介: ※A LoRa model trained by a friend with multires noise. This is a LoRa model that trained by 70+ img generated with NijiV5,and it's the multires noise version. This model can generate exquisite Qinghua-style clothing, decorations, and new Chinese-style backgrounds. weight 0.8-1.0 maybe generates better imgs. teapot, blue dress, hair ornament, chinese clothes, vase and so on are suggersted tag. ~~~~~~~~~~~~~~~~~~~~~~~o(* ̄︶ ̄*)o~~~~~~~~~~~~~~~~~~~~~~~ 示例提示词和参数: Prompt: ((masterpiece, best quality)),(complex lighting),solo,1boy, full body, jiren,white gloves,bodysuit,muscular,bald <lora:Jiren_1:0.6>, light particles, dust particles, Negative prompt: (worst quality, low quality:1.4), (worst quality),low quality, low-res, bad hands,((bad anatomy)),watermark,signature,username, EasyNegative,(head out of frame:1.5),(cropped head:1.3), bad-hands-5, verybadimagenegative_v1.3,holding, missing fingers,extra fingers, bad-artist, negative_hand-neg, holding, Steps: 20, CFG scale: 7, Sampler: Euler a, Seed: 3745079135, ENSD: 31337, Size: 512x512, Model hash: 038ba203d8, Hires upscale: 2, Hires upscaler: Latent, Denoising strength: 0.7, Clip skip: 2 |