How to make AI art of yourself with Midjourney for free

Jon Bear
25 Jan 202305:53

TLDRThe video introduces 'Mid-Journey', an AI tool that generates unique images from text prompts. Users can create detailed prompts combining text and images, or blend two images together. The process is simple, requiring a Discord account and the use of specific commands in the platform's chat rooms. The video also offers tips for refining prompts, such as using a template for clarity, specifying photorealistic details, and adjusting the aspect ratio for different compositions. The creator's enthusiasm for 'Mid-Journey' is evident, encouraging viewers to experiment and explore the tool's capabilities.

Takeaways

  • 🚀 Mid-journey is an AI tool that generates new images based on user input.
  • 📝 Users can prompt Mid-journey with text descriptions, like 'Samurai painting in the style of Edward Monet'.
  • 🎨 It's possible to combine text and images or mash two images together for unique creations.
  • 🆓 Mid-journey is a free service that can be accessed by signing up on their website with a Discord account.
  • 📌 To create an image, users need to type '!imagine' followed by their prompt in the Discord channel.
  • 🔄 Each prompt generates four variations, and users can select and upscale their preferred outcome.
  • 🖼️ Images can be included in prompts by copying and pasting the image URL at the start of the prompt.
  • 🎥 Adding camera perspective to the prompt can influence the style and viewpoint of the generated image.
  • 🌟 Using specific terms like 'Ultra HD photography' can enhance the detail and quality of the image.
  • 📸 The 'candid photo' prompt can generate images with subjects engaged in activities, not directly facing the viewer.
  • 🎨 The 'niji' mode can be used to create anime-style images and better action poses.

Q & A

  • What is Mid-Journey and how does it function?

    -Mid-Journey is an AI platform that generates new images based on the input provided by users. Users can create prompts using text, images, or a combination of both, and the AI will produce images that correspond to those prompts.

  • How can users get started with Mid-Journey?

    -To start using Mid-Journey, users need to sign up on their website through a Discord account. Once in the Discord channel, users can begin creating prompts in the newbie rooms by typing 'Imagine' followed by their prompt.

  • What kind of prompts can be used with Mid-Journey?

    -Prompts for Mid-Journey can range from text descriptions, like 'Samurai painting in the style of Edward Monet', to more complex requests that combine text and images or mash up two different images.

  • How does the image generation process work within Mid-Journey?

    -After a user submits a prompt, Mid-Journey will generate four variations of the image. Users can then choose the one they like best and upscale it by clicking 'U1' for the first variation, 'U2' for the second, and so on.

  • Can users include an image in their Mid-Journey prompt?

    -Yes, users can include an image in their prompt by finding an image online, copying its address, and pasting it at the beginning of their prompt. They can also upload an image directly to the Mid-Journey Bots and copy the image address from there.

  • What is the purpose of the template mentioned in the script?

    -The template is a tool to help users control their prompts with more accuracy. By filling in the blanks of the template, users can provide Mid-Journey with specific instructions, leading to more precise image generation.

  • How can users create two separate characters in Mid-Journey without blending them together?

    -Creating two separate characters can be challenging as Mid-Journey often blends them together. To overcome this, users should 're-roll' the prompt multiple times using the button provided in the Discord channel.

  • What should users include in their prompts to achieve photorealistic images?

    -To create photorealistic images, users should include terms in their prompts that indicate a high level of detail, such as 'Ultra HD photography', 'cinematic lighting', and other phrases that suggest intricate detail.

  • How can users direct the perspective of the generated images?

    -Users can direct the perspective by including camera angle instructions in their prompts, such as 'perspective of a GoPro' or 'perspective of a drone'. This will guide the AI to generate images from the specified viewpoint.

  • What is the 'candid photo' technique mentioned in the script?

    -The 'candid photo' technique involves creating prompts where the subject is not looking directly back at the viewer, which is different from the default generation that often shows subjects facing the camera directly.

  • How can users generate anime-style images with Mid-Journey?

    -To generate anime-style images, users can add 'dash dash niji' at the end of their prompt. This will transform the image into an anime style, which is particularly effective for creating dynamic action poses.

  • What is the significance of changing the aspect ratio in Mid-Journey prompts?

    -Changing the aspect ratio can alter the composition of the generated image. For instance, a 3 by 2 aspect ratio may favor action poses, while a 2 by 3 ratio is more suited to portrait mode. Users are encouraged to experiment with different aspect ratios to achieve desired effects.

Outlines

00:00

🚀 Introduction to Mid-Journey AI

This paragraph introduces the concept of Mid-Journey, an AI that generates new images based on user input. It explains that users can prompt the AI with text or images, or even combine two images to create something new. The speaker invites viewers to subscribe and like the video, and then provides a step-by-step guide on how to use Mid-Journey through its Discord channel. Tips for refining prompts and achieving desired results are shared, such as adding more text, using image links, and incorporating style elements into the prompts.

05:02

🎨 Advanced Techniques and Tips for Mid-Journey

The second paragraph delves into advanced techniques for using Mid-Journey effectively. It discusses the use of a template for more precise control over the AI's output, the challenge of creating distinct characters, and the importance of including details like Ultra HD and cinematic lighting for photorealistic images. The paragraph also covers the use of camera perspectives, such as GoPro or drone views, and the ability to generate candid photos. Additionally, it highlights the use of 'niji' mode for creating anime-style images and adjusting the aspect ratio of images to influence the final composition, such as action poses or portraits.

Mindmap

Keywords

💡mid-journey

Mid-journey is an AI platform that generates new images based on user inputs. It can interpret text descriptions or combine elements from different images to create unique visual content. In the video, the platform is showcased as a tool for creativity, allowing users to visualize complex ideas and blend various elements together to produce innovative artwork.

💡AI

Artificial Intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think, learn, and problem-solve like humans. In the context of the video, AI is the driving force behind mid-journey, enabling the platform to understand and execute user prompts to generate images, demonstrating the advanced capabilities of AI in the realm of digital art creation.

💡prompts

Prompts are the inputs provided to the AI, which can be textual descriptions or a combination of text and images, guiding the AI to produce specific outputs. In the video, users are encouraged to experiment with various prompts to generate images, such as 'Samurai painting in the style of Edward Monet' or 'Spongebob realistic render dancing in a jazz club', showcasing the versatility and creativity enabled by the AI platform.

💡Discord

Discord is a communication platform originally designed for gamers but has since expanded to various communities. In the video, Discord is mentioned as the necessary platform through which users can access and use mid-journey, indicating the collaborative and community-driven nature of the AI art creation process.

💡image upscaling

Image upscaling refers to the process of increasing the resolution of an image while maintaining or improving its quality. In the video, it is mentioned that users can upscale the image variations they like (e.g., U1, U2, U3, U4) generated by mid-journey, allowing for higher quality and more detailed visual outputs.

💡image mashing

Image mashing is the process of combining elements from two or more images to create a new, unique visual. In the video, the concept is illustrated by the idea of merging a picture of a pet with a famous monument, demonstrating the AI's ability to blend different visual elements in innovative ways.

💡energy drink

An energy drink is a type of beverage that contains ingredients designed to provide mental and physical stimulation, often including caffeine and other herbal elements. In the video, a natural energy drink called 'pirate tea' is mentioned, which is promoted as a healthier alternative to traditional energy drinks, offering benefits like improved brain function, focus, mood enhancement, and increased testosterone levels.

💡template

A template is a pre-designed format or structure that serves as a guide for creating content with a consistent layout and style. In the video, a template is recommended for users to more accurately control their prompts in mid-journey, ensuring that the AI understands the specific requirements and produces images that closely match the user's vision.

💡photorealistic

Photorealistic refers to images or artwork that closely resemble real-life photographs in terms of detail and visual accuracy. In the video, the creator advises users on how to create photorealistic images with mid-journey by including prompts that indicate a high level of detail and specific lighting styles, such as 'Ultra HD photography' or 'cinematic lighting'.

💡perspective

Perspective in art refers to the representation of three-dimensional space on a two-dimensional surface, creating an illusion of depth. In the video, the importance of including camera perspective in prompts is highlighted, with examples like 'GoPro perspective' or 'drone perspective', to guide the AI in generating images with a desired viewpoint and depth effect.

💡anime

Anime is a style of animation that originated in Japan and is characterized by its vibrant colors, fantastical themes, and distinctive, often exaggerated, character designs. In the video, the creator shares a tip on how to generate anime-style images using mid-journey by adding 'dash dash niji' at the end of the prompt, demonstrating the platform's ability to adapt to and produce content in various artistic styles.

💡aspect ratio

The aspect ratio of an image refers to the proportional relationship between its width and height. In the video, the creator explains that users can change the aspect ratio of their images by specifying it in the prompt (e.g., 'dash dash AR space three by two'), which affects the composition and orientation of the generated images, such as favoring action poses in a 3:2 ratio or portrait-style images in a 2:3 ratio.

Highlights

Mid-journey is an AI that creates new images based on user input.

Users can prompt Mid-journey with text, such as 'Samurai painting in the style of Edward Monet'.

It's possible to combine text and images for more specific prompts.

Mashing two images together is a feature of Mid-journey, allowing for creative combinations.

The use of Mid-journey is free of charge.

To use Mid-journey, users need to sign in through their website with a Discord account.

New users can start by entering '!imagine' followed by their prompt in the Discord channel.

Each prompt will yield four variations of the image, which can be selected using 'U1', 'U2', etc.

Images can be included in the prompt by copying and pasting the image address.

For a more accurate prompt, a template is recommended to clearly define the desired output.

Creating two separate characters can be challenging, and re-rolling is suggested.

Photorealistic images can be generated by including high detail and style prompts.

Camera perspective can be specified in the prompt, such as 'GoPro perspective' or 'drone perspective'.

The 'candid photo' prompt can be used to generate images where the subject is not directly facing the camera.

Anime style can be applied to prompts by adding '--niji' at the end.

Changing the aspect ratio of images can lead to different outcomes, such as '3:2' for action poses or '2:3' for portraits.

The video provides tips on how to effectively use Mid-journey for creating desired images.