模型简介: <<<V1.0版本>>> 记得返图!示例图片皆为4090本地出图(N),效果与在线生成有区别! 推荐大模型:GhostXL https://www.liblib.ai/modelinfo/1fd281cf6bcf01b95033c03b471d8fd8 推荐LoRa权重:0.5-0.8(推荐0.7) 触发词:Zen painting illustration 推荐提示词: Zen painting illustration(最好填写触发词),anime art style(用于触发GhostXL模型扁平效果),flowing patterns(流动效果),abstract landscape.等...欢迎自行添加元素或使用珍藏提示词~ 其特点是可以生成具有流动感的风景及人物插画,配合GhostXL直出1024×1536图片! 负面提示词: Realistic,EasyNegative, (worst quality, low quality:1.4), (depth of field, blur: 1.2), (greyscale, monochrome:1.1), 3D face, cropped, lowres, text, (nsfw:1.3), (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly:1.331), (duplicate:1.331), (morbid:1.21), (mutilated:1.21), (tranny:1.331), mutated hands, (poor draw hands:1.5), blur, (bad anatomy:1.21), (bad proportions:1.331), bs, extra disfigured (1.331), (missing arms:1.331), (extra legs:1.331), (fused fingers:1.61051), (too many fingers:1.61051), (unclear eyes:1.331), lowers, bad hands, missing fingers, extra digit,bad hands, missing fingers, (((extra arms and legs)))), freckles,(white border:2),nsfw 采样方法:Euler a(其他也行,感觉Euler a的效果好点) 迭代步数:20-30(看你心情) 推荐尺寸:1024×1536(其他尺寸欢迎尝试) 提示词引导系数(CFG):7.0 高清分辨率修复:4x-UltraSharp 若有符合需求的图则使用高清放大,重绘幅度0.3-0.4即可,或直接重绘幅度0.5以上进行抽卡~ <注意事项> 生成有几率出现手与身体、四肢问题,需要进行多次抽卡! - Lib暂时无法直出1024×1536尺寸,在线最大直出1024×1024;条件允许建议下载本地使用~ - 人物全身或比例较小时,脸部会出现崩坏、模糊情况,请开启ADetailer并勾选启用,选择face_yolov8n进行修复! - 部分提示词可能效果不明显,后续版本将会扩大其泛用性; - 由于LoRA模型是基于SDXL_base底模训练,使用不同的大模型出图效果也会不同,后续会基于GhostXL为底模进行训练(也许效果会更好?),敬请期待! —————————————————————————————————————— 模型用途声明: 1. 您不得将此模型及其衍生版本(如融合模型版本)托管于计划赚取收入或捐赠的网站/应用程序。如果您需要将此模型及其衍生版本用于商业目的(如生成式服务、售卖图片、将图片用于公开发表到短视频平台的文章或出版物等等),请通过站内联系本人; 2. 您不得直接售卖由此模型生成的图片,除非您对该图片进行了足够程度的人工修改,使其在法律意义上可以被完全判定为您的个人作品。如果您违反本条,所造成的一切法律后果由您个人承担,请恕本人概不负责; 3. 您不能使用该模型故意制作或共享非法或有害的内容传播和输出,请您遵守公序良德,将此模型用于积极正面的用途。 测试提示词和参数: prompt: Zen painting illustration,anime art style,{"c":"animation poster, big view, up view, white and golden sand and 1girl with black hair and gold and white cloth::1 , lively posture, facing the audience, wear golden and white hanfu cloth, in the style of golden and white, golden sand and dust effect, battle pose, dynamic movement, dynamic pose, ,laser, full of imagination, unmatched composition ultra-detailed super high quality, ((a white tiger::1 in back background)),,<lora:20240222-1708571578268:0.7>,,, Negative prompt: Realistic,EasyNegative,(worst quality, low quality:1.4),(depth of field, blur:1.2),(greyscale, monochrome:1.1),3D face,cropped,lowres,text,(nsfw:1.3),(worst quality:2),(low quality:2),(normal quality:2),lowres,normal quality,((grayscale)),skin spots,acnes,skin blemishes,age spot,(ugly:1.331),(duplicate:1.331),(morbid:1.21),(mutilated:1.21),(tranny:1.331),mutated hands,(poor draw hands:1.5),blur,(bad anatomy:1.21),(bad proportions:1.331),bs,extra disfigured (1.331),(missing arms:1.331),(extra legs:1.331),(fused fingers:1.61051),(too many fingers:1.61051),(unclear eyes:1.331),lowers,bad hands,missing fingers,extra digit,bad hands,missing fingers,(((extra arms and legs)))),freckles,(white border:2), Steps: 30, Size: 1024x1536, Seed: 1811003378, Model: sdxl_vae.safetensors sdxl_vae, GhostXL V1.0-Baked VAE, sdxl_vae.safetensors sdxl_vae, GhostXL V1.0-Baked VAE, Sampler: Euler a, CFG scale: 7 |