模型介绍: Used Anythingv3-Full for training and image creation. Used Anythingv3 vae I recommend a weight between 0.6 and 0.8 with some descriptors, especially if you want her in other clothes. With a higher weight, she tends to have a bow incorporated into her clothing. Link to Dohnna Dohnna style ~~~~~~~~~~~~~~~~~~~~~~~o(* ̄︶ ̄*)o~~~~~~~~~~~~~~~~~~~~~~~ 示例提示词和参数: Prompt: (detailed hair), (masterpiece), (best quality), (ultra-detailed), sharp focus, detailed face, perfect anatomy, perfect lighting, (intricate details), (depth of field), 1girl, full body, SailorMercury, background: city, background: tall neon buildings, <lora:SailorMercury-000009:0.9>, blue eyes, SMUniform, <lora:dohnaDohnaGyokai100Style_v10:0.7> Negative prompt: blur, motion blur, blurry images, unfocused, plain, plain colors, dull, comic, bad anatomy, missing fingers, distorted body, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, bland, dark, dark colors, boring, black and white, (worst quality, low quality:1.4), ( jpeg artifacts:1.4), (blurry, film grain, chromatic aberration, lens flare:1.0), greyscale, monochrome, dusty sunbeams, trembling, motion lines, motion blur, emphasis lines, text, title, logo, signature, realistic, realism, photorealistic, loli Steps: 40, CFG scale: 6.5, Sampler: DPM++ 2M Karras, Seed: 685953895, Size: 512x768, Model: abyssorangemix2_Hard, Model hash: e714ee20aa, Clip skip: 2 |
1人表示很赞