模型介绍: weight 0.7~0.75 is best. I created this LoRA in response to a request. 1girl, solo, black hair, belt, short hair, blue eyes, hair bun, green hairband, blind, chinese clothes, green dress, short sleeves, pelvic curtain This was a very difficult LoRA to create because the images in the dataset were all styled differently. I apologize if you feel it doesn't look like the original Toph. ~~~~~~~~~~~~~~~~~~~~~~~o(* ̄︶ ̄*)o~~~~~~~~~~~~~~~~~~~~~~~ 示例提示词和参数: Prompt: masterpiece, best quality, highres, <lora:toph_beifong_v1:0.75>, 1girl, solo, black hair, hairband, belt, short hair, dress, blue eyes, hair bun, green hairband, blind, chinese clothes, hair bun, green dress, short sleeves, pelvic curtain, barefoot, fighting stance, rock, outdoors, Negative prompt: EasyNegative, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, (worst quality:1.2), low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, lowres graffiti, (low quality lowres simple background:1.1), Steps: 20, CFG scale: 7, Sampler: DPM++ 2M Karras, Seed: 2731361566, ENSD: 31337, Size: 512x768, Model: yesmix_v15, Model hash: f713bab753, Hires steps: 13, Hires upscale: 2, Hires upscaler: 4x-UltraSharp, Denoising strength: 0.45, Clip skip: 2 |
1人表示很赞