【AIツール】Midjourney - ミッドジャーニーで写真を元に画像生成する方法。

HIROCODE.ヒロコード
7 Mar 202308:39

TLDRThe video introduces the AI tool Midjourney, which generates images based on specific keywords and reference photos. It explains the process of using Midjourney, including creating a Discord account, joining the server, and executing commands to generate images. The video emphasizes the importance of using reference images and 'spells' (keywords) to create images closer to one's vision. It also discusses the free and paid plans, commercial use of generated images, and various parameters that can be used to improve image quality. The creator shares their experience of generating images with Midjourney and encourages viewers to explore AI tools for creative purposes.

Takeaways

  • 🌟 Introduction to AI tool Midjourney, which generates images based on specific keywords and can also incorporate reference photos for more accurate results.
  • 📸 Importance of using reference images in addition to text descriptions to generate images closer to one's envisioned concept.
  • 🛠️ Explanation of the process to use Midjourney, including creating a Discord account, joining the Midjourney server, and executing commands.
  • 💰 Discussion on the pricing plans of Midjourney, with a free plan allowing up to 25 image generations and paid plans offering more generations and commercial use rights.
  • 🎨 Mention of the impact of background color in reference images on the generated results and the possibility of adjusting this through 'spells' or commands.
  • 🔗 Instructions on how to upload reference images to Discord and use them in conjunction with text prompts for image generation.
  • 📝 Details on the use of 'spells' or commands in Midjourney and how they can significantly alter the output image.
  • 🔄 Description of the ability to refine generated images using various options like high-quality enhancement, re-generation based on the same prompt, and recycling marks.
  • 🔍 Encouragement to review other users' posts for successful 'spells' and to experiment with different keywords to achieve desired results.
  • 📌 Tips on using parameters like aspect ratio adjustment and exclusion of specific keywords to control the output more precisely.
  • 🌿 Example of generating an image using multiple reference photos and the inclusion of keywords related to the images to create a composite result.

Q & A

  • What is the AI tool introduced in the script?

    -The AI tool introduced in the script is called Midjourney, which generates images based on specific keywords or text descriptions.

  • What is the limitation of generating images with text descriptions alone?

    -The limitation of generating images with text descriptions alone is that it can be quite challenging to express detailed or complex images just through text, often resulting in generated images that differ from the intended vision.

  • How can the Midjourney tool improve the accuracy of generated images?

    -The accuracy of generated images can be improved by providing reference images along with the text descriptions. This allows the AI to create images that are closer to the user's intended vision.

  • What do users call the commands used for image generation in Midjourney?

    -Users refer to the commands used for image generation as 'incantations' or 'spells' in Midjourney.

  • What is the basic process of using Midjourney?

    -The basic process of using Midjourney involves creating a Discord account, joining the Midjourney server, entering the appropriate room, executing the commands, and then generating the image.

  • What are the pricing plans for Midjourney?

    -Midjourney offers a free plan that allows up to 25 image generations. For more than that, users need to subscribe to a paid plan. The cheapest paid plan is the Basic Plan at $10 per month, which allows up to 200 image generations.

  • What are the commercial use restrictions for images generated by Midjourney?

    -Images generated by Midjourney are not allowed for commercial use by default. However, if users subscribe to a paid plan, they gain the rights to use the generated images commercially.

  • How can the background color of a reference image affect the generation process?

    -The background color of a reference image can significantly influence the final result of the generated image. It's important to consider this aspect when selecting reference images.

  • What are some tips for creating an effective 'incantation' in Midjourney?

    -Effective 'incantations' often include specific details about the desired image, such as the style (e.g., anime style), and can also reference other successful 'incantations' seen in the community. Users should experiment with different keywords and phrases to achieve the desired result.

  • How can users refine the generated images?

    -Users can refine the generated images by using buttons provided on the result page. These buttons allow for high-quality enhancement (U1-U10), regenerating based on the same 'incantation' (V1-V4), or recycling the image with the same 'incantation' (recycling mark).

  • What are some additional parameters that can be used during image generation?

    -Additional parameters include '-AR' for aspect ratio adjustment, '-' for excluding specific keywords, and the inclusion of certain keywords like 'High Quality' or 'Beautiful' to potentially increase the level of the generated image.

  • How does using multiple reference images affect the generation process?

    -Using multiple reference images can result in a more complex and detailed generated image, as the AI takes into account the elements from all provided images to create a composite that reflects the combined vision.

Outlines

00:00

🖼️ Introduction to AI Image Generation with Midjourney

This paragraph introduces the concept of using AI tools, specifically Midjourney, to generate images based on specific keywords and reference photos. It explains that while Midjourney typically generates images from text keywords alone, there are limitations to expressing detailed personal visions through text. By incorporating reference photos, the AI can generate images closer to the user's imagination. The speaker also mentions the importance of choosing the right 'spell' or command to generate images that closely match the desired outcome. The paragraph outlines the basic process of using Midjourney, including creating a Discord account, joining Midjourney, executing commands, and generating images. It also discusses the pricing plans, with the free plan allowing up to 25 image generations and the paid plans offering more generations and commercial use rights.

05:01

🔍 Enhancing Image Generation with References and Parameters

This paragraph delves into the process of enhancing image generation by using reference images and specific parameters. It highlights the importance of providing clear information about the reference image to improve the quality of the generated images. The speaker suggests looking at other people's posts for inspiration and using their keywords to generate similar images. The paragraph also introduces various parameters that can be used to modify the output, such as changing the aspect ratio with '-AR' or excluding specific keywords with '-exclude'. It encourages users to experiment with different keywords to achieve the desired result. Finally, it discusses the possibility of using multiple reference images to create more complex and detailed images, showcasing the potential of AI in image generation.

Mindmap

Keywords

💡AI工具ミッドジャーニー (AI tool Midjourney)

AI tool Midjourney is the main focus of the video, which is an AI service that generates images based on specific keywords or text prompts. It allows users to create images that align with their imagination by not only providing text descriptions but also reference photos, leading to more accurate and personalized visual outputs. In the context of the video, the user explains how to utilize Midjourney for image generation, including the process of signing up, using commands, and the importance of selecting the right 'incantations' or parameters for desired results.

💡画像生成 (Image Generation)

Image Generation is the process of creating visual content using AI algorithms, as demonstrated in the video. It involves inputting text descriptions or providing reference images to the AI, which then produces images that match the given criteria. The video emphasizes the importance of using the correct 'incantations' or commands to achieve the desired image quality and similarity to the reference material.

💡テキスト (Text)

In the context of the video, text refers to the written descriptions or keywords that are used as input for the AI to generate images. The text serves as a guide for the AI to understand the user's vision and create an image that aligns with the described concept or theme. The video highlights the limitations of using text alone and the benefits of combining it with reference images for more accurate results.

💡参考写真 (Reference Photo)

A reference photo is an existing image that serves as a visual guide for the AI to generate a new image that closely resembles or captures the essence of the provided example. In the video, the user emphasizes the importance of using reference photos to achieve a higher quality and more accurate image generation, as it helps the AI understand the user's vision better.

💡コマンド (Command)

Commands are specific instructions or 'incantations' used in the AI tool Midjourney to generate images. These commands include text inputs, reference images, and parameters that guide the AI in creating the desired visual output. The video script explains the importance of choosing the right commands to achieve the best results in image generation.

💡Discord

Discord is a communication platform where the AI tool Midjourney is integrated. Users create accounts on Discord and join the Midjourney server to interact with the AI and generate images. The platform allows for easy sharing of commands, reference images, and communication with the AI tool.

💡無料プラン (Free Plan)

The Free Plan refers to the tier of service offered by Midjourney that allows users to generate a limited number of images without any cost. This plan is designed for users to try out the AI tool and understand its capabilities before deciding to upgrade to a paid plan for more extensive usage.

💡有料プラン (Paid Plan)

A Paid Plan is a subscription tier for the AI tool Midjourney that offers more extensive image generation capabilities than the free plan. Users who require generating more images or have specific usage needs can opt for a paid plan, which comes with additional features and a higher limit on the number of images that can be created.

💡商用利用 (Commercial Use)

Commercial Use refers to the permission for users to utilize the generated images for business or profit-making purposes. The video clarifies that while the free plan does not allow commercial use of the images, upgrading to a paid plan grants users this right.

💡パラメーター (Parameter)

Parameters are specific settings or options that users can adjust within the AI tool Midjourney to influence the characteristics of the generated images. These can include aspects like image aspect ratio, exclusion of certain keywords, and other factors that help refine the output to better match the user's vision.

💡画像URL (Image URL)

An Image URL is the web address of a specific image that can be used as a reference for the AI to generate new images. In the context of the video, users upload their reference photos and obtain the image URL, which is then used as input in the commands to guide the AI in creating similar or inspired images.

Highlights

Introduction to AI tool Midjourney for generating images based on specific keywords.

Midjourney generates images from text, but sometimes there are limitations to expressing complex ideas in text alone.

Combining text with reference photos can lead to generating images closer to one's imagination.

Exploring the use of 'incantations' or commands to significantly alter the resulting images.

A brief overview of how to use Midjourney, including creating a Discord account and joining the Midjourney server.

Information on the free and paid plans available for Midjourney, including the number of images that can be generated.

Commercial use of images generated by Midjourney is only allowed with a paid plan.

Preparation of reference images, including the impact of background color on the resulting images.

Uploading reference images to Discord and using the image URL in conjunction with 'incantations'.

Entering the /imagine command and adding keywords to generate images based on the reference photo.

Waiting time for image generation depends on server congestion, but it's roughly around a minute.

Adjustments can be made to the generated images using various buttons provided after the image is produced.

Tips for considering 'incantations' when generating images, such as specifying the style or quality of the reference image.

Using other people's posts as references on Discord can lead to generating images closer to one's desired outcome.

Parameters that can be used during image generation, such as aspect ratio and exclusion of specific keywords.

Experimenting with multiple reference photos to generate an image that reflects a combination of the provided images.

Reflection on the ease of generating high-quality images with AI and the potential future of using AI in work.

Encouragement for those who have never used AI to try Midjourney and experience the capabilities of AI.