<div id="readability-page-1" class="page">
                
                



<nav id="global-navigation">


</nav>
<main id="wrap" aria-hidden="false">

<div>



                
                    


	
<article>
<header id="global-header">



<div>
<h2>미드저니(Midjourney)를 써보았다.</h2>
<ul>
<li role="text" aria-label="2023년 02월 25일 18시 38분에 작성된 글."><time datetime="2023-02-25T18:38">2023.02.25 18:38</time></li>
<li><a href="/category/Devlog" aria-label="Devlog">Devlog</a></li>
</ul>
</div>


</header>
<div id="article"><figure data-ke-mobilestyle="widthOrigin" data-filename="Geon_1_is_a_middle-aged_man_sitting_by_a_large_window_on_a_rain_1e5252e6-1017-4d7e-85d7-804ac07593d3.png" data-origin-width="1568" data-origin-height="896"><span data-url="https://blog.kakaocdn.net/dn/92Afs/btr0IvyZYJg/EDLfUVzktzNZ6CIOlq1qpk/img.png" data-lightbox="lightbox"><img src="https://blog.kakaocdn.net/dn/92Afs/btr0IvyZYJg/EDLfUVzktzNZ6CIOlq1qpk/img.png" onerror="this.onerror=null; this.src='//t1.daumcdn.net/tistory_admin/static/images/no-image-v1.png'; this.srcset='//t1.daumcdn.net/tistory_admin/static/images/no-image-v1.png';" data-filename="Geon_1_is_a_middle-aged_man_sitting_by_a_large_window_on_a_rain_1e5252e6-1017-4d7e-85d7-804ac07593d3.png" data-origin-width="1568" data-origin-height="896"></span></figure>

<p data-ke-size="size16">AI 이미지 생성 서비스인 미드 저니를 써보았다. 해당 서비스가 기존에 존재했던 건 알고 있었지만 사용하지 않았는데, 요즘 ChatGPT를 사용하다가 알게된&nbsp;<a href="https://chrome.google.com/webstore/detail/aiprm-for-chatgpt/ojnbohmppadfgpejeebfnmnknjdlckgj?hl=en-US" target="_blank" rel="noopener">AIPRM for ChatGPT</a> 이라는 확장 프로그램에서 키워드를 넣으면 미드저니용 프롬프트를 짜주는 프롬프트(Midjourney&nbsp;Prompt&nbsp;Generator)를 제공해서 궁금증에 한 번 써보았다.</p>

<figure data-ke-mobilestyle="widthOrigin" data-origin-width="2846" data-origin-height="1934"><span data-url="https://blog.kakaocdn.net/dn/b68fff/btr0GaI7R64/wOFHNH68sDjsWduBBLIxdK/img.png" data-lightbox="lightbox"><img src="https://blog.kakaocdn.net/dn/b68fff/btr0GaI7R64/wOFHNH68sDjsWduBBLIxdK/img.png" onerror="this.onerror=null; this.src='//t1.daumcdn.net/tistory_admin/static/images/no-image-v1.png'; this.srcset='//t1.daumcdn.net/tistory_admin/static/images/no-image-v1.png';" data-origin-width="2846" data-origin-height="1934"></span></figure>

<p data-ke-size="size16">아래 키워드를 입력하기만 하면 끝</p>
<p data-ke-size="size16"><span>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 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. Never place a comma between [ar] and [v]. You will write each prompt in one line without using return. Structure: [1] = 창밖을 보며 미래에 대해 고민하는 남성 [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). [1] [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) [ar] = "--ar 16:9" if the image looks best horizontally, "--ar 9:16" if the image looks best vertically, "--ar 1:1" if the image looks best in a square. (Use exactly as written) [v] = 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], [ar] [v]". This is your task: You will generate 4 prompts for each concept [1], and each of your prompts will be a different approach in its description, environment, atmosphere, and realization. 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</span></p>
<p data-ke-size="size16">그러면 키워드에 맞춰 위와 같은 프롬프트를 요청하게된다.</p>
<p data-ke-size="size16">해당 질의에 대한 결과 값은 다음과 같다.</p>
<p data-ke-size="size16"><span>/imagine prompt: [1] is a middle-aged man sitting by a large window on a rainy day, staring outside with a pensive expression. He is wearing a tweed jacket with leather elbow patches and holding a cup of steaming tea in his hands. The light coming through the window illuminates his face, casting a shadow on the left side. He appears lost in thought and deep contemplation. [3] The room is decorated with antique furniture, including a mahogany desk with brass handles, an oriental rug, and a bookshelf filled with leather-bound books. The walls are painted in a soft gray color, and there are several potted plants scattered throughout the room. [4] The atmosphere is introspective and melancholic, with a hint of nostalgia. The sound of raindrops hitting the windowpane creates a soothing background noise. The man's posture and facial expression convey a sense of loneliness and longing. [5] Photography [6] A close-up portrait shot with a 50mm prime lens, using natural light. The aperture will be set to f/2.8 to create a shallow depth of field and draw attention to the man's face. The camera will be a Canon EOS 5D Mark IV. --ar 16:9 --v 4</span></p>
<p data-ke-size="size16">해당 프롬프트를 미드저니에 질의하면, 미드저니는 해당 질의에 대해 4개의 결과물을 주고 그 중에 하나를 골라서 또 다른 4개의 결과물을 얻거나 화질을 높여서 결과 이미지를 받는 방식으로 되어있다. 맨 처음에 올린 사진이 바로 미드저니를 통해 얻은 결과물이다. 다음 사진은 또 다른 결과물인 "호텔 주방장이 된 스티브 잡스"이다.</p>
<figure data-ke-mobilestyle="widthOrigin" data-filename="Geon_Steve_Jobs_Becomes_Famous_Hotel_Chef_a7ac0dc9-a724-432f-99ff-226699e9356a.png" data-origin-width="1024" data-origin-height="1024"><span data-url="https://blog.kakaocdn.net/dn/b8K1K9/btr0KRhfvHM/i0JFyKRwsXuVAXUe7rpMWK/img.png" data-lightbox="lightbox"><img src="https://blog.kakaocdn.net/dn/b8K1K9/btr0KRhfvHM/i0JFyKRwsXuVAXUe7rpMWK/img.png" onerror="this.onerror=null; this.src='//t1.daumcdn.net/tistory_admin/static/images/no-image-v1.png'; this.srcset='//t1.daumcdn.net/tistory_admin/static/images/no-image-v1.png';" data-filename="Geon_Steve_Jobs_Becomes_Famous_Hotel_Chef_a7ac0dc9-a724-432f-99ff-226699e9356a.png" data-origin-width="1024" data-origin-height="1024"></span></figure>

<p data-ke-size="size16">그 이후로도 여러 시행을 해보았는데, 생각한 것과 다른 결과물을 보여주기도했다. 질의에 따라 결과물이 천차만별인 느낌이였다. 결국 무료 사용량을 초과해서 미드저니는 이제 과금하지 않은 이상 사용할 수 없는데, 굉장히 인상깊은 서비스였다.</p>
</div>


<nav>
<ul>
<li></li>
<li></li>
<li></li>
</ul>
</nav>





















</article>


                    
                
</div>
</main>









	




                        
        

        






                
                









                
</div>

빠리의 택시 운전사

AI 이미지 생성 서비스인 미드 저니를 써보았다. 해당 서비스가 기존에 존재했던 건 알고 있었지만 사용하지 않았는데, 요즘 ChatGPT를 사용하다가 알게된 AIPRM for ChatGPT 이라는 확장 프로그램에서 키워드를 넣으면 미드저니용 프롬프트를 짜주는 프롬프트(Midjourney Prompt Generator)를 제공해서 궁금증에 한 번 써보았다.
 
아래 키워드를 입력하기만 하면 끝
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 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. Never place a comma between [ar] and [v]. You will write each prompt in one line without using return. Structure: [1] = 창밖을 보며 미래에 대해 고민하는 남성 [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). [1] [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) [ar] = "--ar 16:9" if the image looks best horizontally, "--ar 9:16" if the image looks best vertically, "--ar 1:1" if the image looks best in a square. (Use exactly as written) [v] = 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], [ar] [v]". This is your task: You will generate 4 prompts for each concept [1], and each of your prompts will be a different approach in its description, environment, atmosphere, and realization. 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
그러면 키워드에 맞춰 위와 같은 프롬프트를 요청하게된다.
해당 질의에 대한 결과 값은 다음과 같다.
/imagine prompt: [1] is a middle-aged man sitting by a large window on a rainy day, staring outside with a pensive expression. He is wearing a tweed jacket with leather elbow patches and holding a cup of steaming tea in his hands. The light coming through the window illuminates his face, casting a shadow on the left side. He appears lost in thought and deep contemplation. [3] The room is decorated with antique furniture, including a mahogany desk with brass handles, an oriental rug, and a bookshelf filled with leather-bound books. The walls are painted in a soft gray color, and there are several potted plants scattered throughout the room. [4] The atmosphere is introspective and melancholic, with a hint of nostalgia. The sound of raindrops hitting the windowpane creates a soothing background noise. The man's posture and facial expression convey a sense of loneliness and longing. [5] Photography [6] A close-up portrait shot with a 50mm prime lens, using natural light. The aperture will be set to f/2.8 to create a shallow depth of field and draw attention to the man's face. The camera will be a Canon EOS 5D Mark IV. --ar 16:9 --v 4
해당 프롬프트를 미드저니에 질의하면, 미드저니는 해당 질의에 대해 4개의 결과물을 주고 그 중에 하나를 골라서 또 다른 4개의 결과물을 얻거나 화질을 높여서 결과 이미지를 받는 방식으로 되어있다. 맨 처음에 올린 사진이 바로 미드저니를 통해 얻은 결과물이다. 다음 사진은 또 다른 결과물인 "호텔 주방장이 된 스티브 잡스"이다.
그 이후로도 여러 시행을 해보았는데, 생각한 것과 다른 결과물을 보여주기도했다. 질의에 따라 결과물이 천차만별인 느낌이였다. 결국 무료 사용량을 초과해서 미드저니는 이제 과금하지 않은 이상 사용할 수 없는데, 굉장히 인상깊은 서비스였다.

미드저니(Midjourney)를 써보았다.

댓글