GPT-4比Chatgpt升级了不少，现在还无法使用OpenAI官网或百度文心一言的小伙伴可以尝试以下方法。
打开 nat.dev
登录（sign-in注册时不用填手机号码）
选择GPT-4模型
然后直接空白处用英语或者中文输入问题
想尝试AI作图的方法如下。
打开网页 https://discord.com/ 点击“Open Discord”
发现页搜索“midjourney”进入社区
复制黏贴以下文字到GPT-4并且ctrl+enter
You will now act as a prompt generator for a generative AI called “Midjourney”. Midjourney AI generates images based on given prompts.I will provide a concept in so wait till i give you instruction and you will provide the prompt for Midjourney AI.You will never alter the structure and formatting outlined below in any way and obey the following guidelines:You will not write the words “description” or use “:” in any form. You will write each prompt in one line without using return. Structure of prompt will be in: [1] = [KEYWORD] [2] = a detailed description of [1] that will include very specific imagery details. [3] = with a detailed description describing the environment of the scene. [4] = with a detailed description describing the mood/feelings and atmosphere of the scene. [5] = A style, for example: photography, painting, illustration, sculpture, Artwork, paperwork, 3d and more). [6] = A description of how [5] will be realized. (e.g. Photography (e.g. Macro, Fisheye Style, Portrait) with camera model and appropriate camera settings, Painting with detailed descriptions about the materials and working material used, rendering with engine settings, a digital Illustration, a woodburn art (and everything else that could be defined as an output type) [7] = Parameters detaills as given below Note don’t use , when using parameter options and use all important parameter options which is required to generate image. Parameters details start Aspect Ratios (–aspect or --ar): Changes the aspect ratio of a generation. --aspect 5:4: Common frame and print ratio. --aspect 4:3: Common in television and photography. --aspect 3:2: Common in print photography. --aspect 16:9: Common in widescreen television and video. --aspect 2:1: Common in panoramic photography. --aspect 7:4: Close to HD TV screens and smartphone screens. --aspect 9:16: Common in vertical videos and smartphone screens. --aspect 1:2: Common in portrait-oriented photography. Chaos (–chaos ): Changes how varied the results will be. Higher values produce more unusual and unexpected generations. chaos parameter accepts a number from 0 to 100, where 0 produces very similar and expected results and 100 produces highly varied and unexpected results Negative prompting (–no): Removes unwanted elements from the image. Quality (–quality or --q <.25, .5, 1, or 2>): Controls the rendering quality of the image. Default is 1. Seed (–seed <integer between 0-4294967295>): Specifies a seed number to generate the initial image grids. Using the same seed number and prompt will produce similar ending images. Stop (–stop <integer between 10-100>): Finishes a job partway through the process. Stopping a job at an earlier percentage can create blurrier, less detailed results. Model Version (–version or --v <1, 2, 3, 4, or 5>): Uses a different version of the Midjourney algorithm. The current algorithm (V4) is the default setting. Stylize (–stylize or --s ): Influences how strongly Midjourney’s default aesthetic style is applied to jobs. This parameter accepts a number from 0 to 1000, where 0 produces images that more closely resemble the input prompt and 1000 produces images with the strongest default Midjourney aesthetic style Upscalers (–uplight, --upbeta, --upanime): Adds additional details to the low-resolution image grid. Multiple upscale models are available. Image Weight (–iw): Sets the image prompt weight relative to text weight. Default value is 0.25. Parameters details End* Use aspect ratio which fits best for the image as per your understading. If [5] looks best in a Japanese art style use, “–niji”. Otherwise use, “–v 4” (Use exactly as written)Formatting:What you write will be exactly as formatted in the structure below including the “/” and “:” This is the prompt structure: “/imagine prompt: [1], [2], [3], [4], [5], [6] ,[7]”. Important point to note while writing prompts , Never use / or : between [1], [2], [3], [4], [5], [6] ,[7] Don’t use [] while generating prompt. The prompts you provide will be in English.Please pay attention:- Concepts that can’t be real would not be described as “Real” or “realistic” or “photo” or a “photograph”. for example, a concept that is made of paper or scenes which are fantasy related.- One of the prompts you generate for each concept must be in a realistic photographic style. you should also choose a lens type and size for it. Don’t choose an artist for the realistic photography prompts.- Separate the different prompts with two new lines. I will provide you keyword and you will generate 3 diffrent prompts in vbnet code cell so i can copy and paste. Are you ready ?
机器回复后输入“concept：你想要画的内容，可用中文"
把返回的 /imagine prompt: 全部绿色内容黏贴到midjourney输入框内既可完成相应作画
个人观点
人工智能目前的核心价值在于自动化。可应用于解题，搜索客观事实，日程表预定，出书，翻译，写作，图片加工等等。对使用者来说重要的是从行业专业角度去规划哪些任务交给人工智能更合适。我们不能让人工智能抑制人脑的独特思维。在一个信息爆炸和生产力说话的时代，能尽早把一部分编程和数据任务交给人工智能的组织，必定会抢占先机。其次，再是去思考怎么用人工智能开发人脑做不到的任务，比如大数据建立知识图谱等等。就像我在量化如何破局？中提到的，工作最后真正区别他人的是创新。人工智能虽然可以让很多人失业，但也会开创新的领域。比如网站设计师不再是写代码，而是有一套属于自己行业的自然语言去完成工作。
公众号：gnu_isnot_unix - 前Citadel现自营交易。活在当下，终身学习 - 给在职却对未来始终迷茫的人的公众号。借此想告诉不断努力，对生活充满热情的读者们：我们要拥有的是事业而不是职业。
往期内容整理： 【python量化】在私募做量化研究半年能学到什么？我们和国外对冲基金的差距在哪里？最近银行股暴雷，应该怎么交易？ 如果真正用量价因子做交易？ 最近CTA总体回撤的深度策略复盘 怎么建立属于自己的交易优势-掘金蟒蛇付费内容说明 如何构建夏普5的择时策略（一）：技术指标方法论 （付费） 二级市场怎么赚钱？ 在城堡基金Citadel工作是一种什么体验？ 为什么赛马可预测，股市不可预测？ 五行风水能否预测股市？ 一定要相信k线是时时刻刻正确的（包含干货） 股票交易的本质是什么？ 做多还是做空? 不赚认知以外的钱-大盘什么时候可以抄底 亘古不变的交易法则 什么是最愚蠢的交易行为？ ### 更早请从公众号内进入 ###
近期评论