Midjourney V5 - How To Upload A Reference Image Or Art And Use As A Prompt - Detailed Tutorial

Curtis Pyke
16 Mar 202303:09

TLDRIn this tutorial, the creator demonstrates how to transform a photo into an art piece using Mid-Journey version 5. The process begins with uploading the image to Discord, then crafting a detailed prompt including the desired scene and visual effects. By incorporating the image link and setting the image weight to 2.0, the user can generate a highly accurate representation of the original photo in the desired artistic style. The result showcases the impressive capabilities of Mid-Journey version 5.

Takeaways

  • 🎨 The tutorial demonstrates how to transform an image into a piece of art using a specific AI tool.
  • 👩 The subject of the image is a lady found on Pixels, used as a reusable prompt for the generation process.
  • 🖼️ The process begins by uploading the image to a platform, such as Discord, and obtaining a shareable link.
  • 🔗 The next step involves standard prompt engineering, where the desired outcome is described.
  • 📚 In this example, the prompt is 'lady reading a book' with specific details like depth of field and natural lighting.
  • 🖌️ The prompt also includes instructions for photorealism, specifying 'photo realistic' in the command.
  • 🔗 The image link is then incorporated into the prompt by copying and pasting it after a space bar.
  • 🌟 The 'image weight' (IW) is an important parameter that determines how much influence the original image has on the generated art, with a range from 0.5 (lowest) to 2.0 (highest).
  • 🚀 The final prompt combines the description, image link, and image weight to generate the desired artwork.
  • 📸 The result showcases the AI's capability to create highly realistic and detailed images based on the given input.
  • 🎉 The video concludes by highlighting the impressive results of mid-journey version 5 of the AI tool.

Q & A

  • What is the main topic of this tutorial?

    -The main topic of this tutorial is how to transform an image into art using a reusable prompt in the generation process to create characters from pictures and art.

  • Where did the speaker find the original image of the lady?

    -The speaker found the original image of the lady on Pixabay.

  • How does the speaker upload the image to Discord?

    -The speaker drags and drops the image into Discord, then uploads it to the server.

  • What is the purpose of copying the image link?

    -The purpose of copying the image link is to use it later in the generation process to give the original image a certain weight in the final artwork.

  • What does the speaker use to describe the desired look of the generated image?

    -The speaker uses a standard prompt engineering process with the forward slash imagine command, describing the desired look with terms like 'lady reading a book', 'depth of field', '35 millimeter lens', 'natural lighting', 'photo realistic', and the image weight.

  • What does 'dof' stand for in the script?

    -In the script, 'dof' stands for 'depth of field', which refers to the range of distance in a photo that appears acceptably sharp.

  • What does the '---IW' command do in the generation process?

    -The '---IW' command stands for 'image weight', which determines how much influence the original image has on the generated artwork, with a range from 0.5 (lowest weight) to 2.0 (highest weight).

  • How does the speaker ensure the generated image closely resembles the original?

    -The speaker sets the image weight to 2.0, which is the highest weight, to ensure the generated image closely resembles the original.

  • What version of the tool is the speaker using?

    -The speaker is using version 5 of the tool, which is assumed to be the current version for the user.

  • How does the speaker upscale the chosen image?

    -The speaker selects the desired image (number three) and uses the 'Zoo upscale' command followed by the image number to upscale it.

  • What is the speaker's final verdict on the generated images?

    -The speaker is amazed by the quality of the generated images, especially number three, and finds the mid-journey version five of the tool to be incredible.

Outlines

00:00

🎨 Transforming an Image into Art with Mid-Journey Version 5

The paragraph introduces a tutorial on utilizing Mid-Journey Version 5, a tool for creating art from images. The speaker demonstrates how to use an image of a lady found on pixels as a reusable prompt in the generation process to produce characters from pictures and art. The process begins with uploading the image to Discord, copying the link, and then using a prompt engineering technique to describe the desired output. The speaker emphasizes the impressive results and provides a step-by-step guide on how to achieve them.

Mindmap

Keywords

💡mid-journey version 5

The term 'mid-journey version 5' refers to a specific iteration or version of a software or tool being used in the tutorial. This version is likely to have certain features and capabilities that are distinct from previous versions. In the context of the video, it is the platform through which the user is transforming images into art, suggesting that this version has advanced features for image processing and generation.

💡image prompt

An 'image prompt' is a visual input used to guide the generation process in creative software. It serves as a reference or inspiration for the output, helping to shape the final result. In the video, the user takes an existing image and uses it as a prompt to create a new piece of art, demonstrating how the software can interpret and transform visual information.

💡Discord

In the context of this video, 'Discord' is a communication platform where users can upload and share images. It is used as a tool to store and access the image that will be transformed into art. The user uploads the image to a Discord server, then copies the link to the image, which will be used later in the process.

💡prompt engineering

Prompt engineering is the process of crafting text inputs, or 'prompts', to guide the output of a generative AI system. This involves carefully selecting words and phrases that will influence the AI to produce a desired result. In the video, the user describes how to use prompt engineering to create a specific image, demonstrating the importance of clear and descriptive language in achieving the desired outcome.

💡image weight

The term 'image weight' refers to the influence or importance given to an input image in the generative process. A higher weight means the generated output will more closely resemble the input image. In the video, the user adjusts the image weight to ensure that the generated art closely matches the original image they uploaded, indicating a desire for a high degree of similarity.

💡photo realistic

The term 'photo realistic' describes a quality of an image or artwork that closely resembles a photograph in terms of detail and accuracy. In the context of the video, the user aims to create art that looks very real, as if it could be a photograph, by using the image of a lady as a reference. This term highlights the goal of achieving a high level of visual fidelity in the generated art.

💡upscale

To 'upscale' an image refers to the process of increasing its resolution or detail while maintaining or improving its quality. In the video, the user selects certain generated images for upscaling, which suggests that they are satisfied with the initial results and want to enhance them further to achieve a more detailed and high-resolution final product.

💡character creation

Character creation is the process of designing and developing characters, which can be used in various forms of media such as literature, film, or video games. In the video, the user demonstrates how to use an AI tool to create characters from images, showing that the technology can be used for creative purposes like storytelling and character design.

💡natural features

Natural features refer to characteristics or elements that are found in nature and can be applied to the description of an image or scene. In the context of the video, the user includes 'natural features' in their prompt to guide the AI in generating an image with elements that appear organic and true to nature, such as natural lighting conditions.

💡depth of field

Depth of field (DOF) is a photographic term that describes the range of distance within a scene that appears acceptably sharp and in focus. It is a creative technique used in both photography and art to emphasize certain parts of an image while blurring others, creating a sense of depth and dimension. In the video, the user includes 'depth of field' in their prompt to guide the AI in generating an image with a specific focus and depth effect.

Highlights

The tutorial introduces a method to transform an image into art using a reusable prompt in the generation process.

The image used is a picture of a lady found on pixels.

The process allows creating characters from both pictures and art.

An example is provided showing the transformation from the original image to an artistic version.

The first step is to upload the image to a Discord server.

After uploading, the image link is copied for later use.

Standard prompt engineering is used to describe the desired look of the generated image.

The prompt includes details such as depth of field, lens type, lighting, and desired photorealism.

The image link is pasted into the prompt using command V or control V.

The image weight (IW) is set to determine the influence of the original image on the generated result.

The image weight can range from 0.5 (lowest) to 2.0 (highest).

The tutorial uses mid-Journey version 5 for the image generation.

The generated images are showcased, with a focus on the third image for its close resemblance to the original.

The process is described as simple yet effective, yielding impressive results.

The tutorial concludes by emphasizing the capabilities of mid-Journey version 5.