SDXL 可以生成几乎任何艺术风格的高质量图像,是照片写实主义的最佳开放模型。 可以提示不同的图像,而无需模型赋予任何特定的“感觉”,从而确保风格的绝对自由。 SDXL 1.0 特别针对鲜艳而准确的色彩进行了精心调校,与前身相比,具有更好的对比度、照明和阴影,所有这些均采用原始 1024x1024 分辨率。 此外,SDXL 可以生成图像模型难以渲染的概念,例如手和文本或空间排列的构图(例如,背景中的女人在前景中追逐狗)。
Titan Image Generator 是亚马逊自行开发的最新 Titan 家族模型,号称能够赶上 OpenAI、谷歌、微软等竞争者。
该模型具备“图片编辑”及“隐藏水印”等功能,允许用户以英语输入提示词句,以生成“专业等级”的图像。亚马逊表示,Titan Image Generator 以高品质且多样化的数据训练而成,因此可以生成精准、拟真、多元的图片。
首先点击“Image”导航标签,链接如下:
https://us-east-1.console.aws.amazon.com/bedrock/home?region=...
第二步选择配置画图模型
第三步输入提示词进行画图
提示词创作
a beautiful young girl,white dress
艺术家风格 作品创作
(by Anna Dittmann:1.2),digital painting,illustration,portrait,fantasy,
动物画图
Please paint a rabbit, wildlife photography, photograph, high quality, wildlife, f 1.8, soft focus, 8k, national geographic, award - winning photograph by nick nichols
动漫风格图像画图
Please draw me a cute turtle, anthro, very cute kid's film character, disney pixar zootopia character concept artwork, 3d concept, detailed fur, high detail iconic character for upcoming film, trending on artstation, character design, 3d artistic render, highly detailed, octane, blender, cartoon, shadows, lighting
Please help me draw a robot team, they have combat capabilities and wear professional clothes, character sheet, concept design, contrast, style by kim jung gi, zabrocki, karlkka, jayison devadas, trending on artstation, 8k, ultra wide angle, pincushion lens effect
cinematic photo portrait of a man, cyberpunk, in heavy raining futuristic tokyo, rooftop, cyberpunk night, sci-fi, fantasy, intricate, extremely beautiful, elegant, neon light, highly detailed