Midjourney Image Prompt & Blend Feature Tips (Full Tutorial)

PromoAmbitions
15 May 202307:29

TLDRThis tutorial delves into using image prompts and the blend feature in Midjourney, demonstrating how to upload and manipulate images to influence AI-generated content. It covers the importance of aspect ratio, the image weight parameter to adjust the influence of the image, and blending multiple images for unique outputs. The creator experiments with various prompts, including transforming a photo into a Greek goddess and a superhero, showcasing the versatility and creativity of Midjourney's AI capabilities.

Takeaways

  • 📸 **Image Prompts in Midjourney**: You can use an image as part of a prompt to influence the composition, style, and colors of the generated image.
  • 🖼️ **Uploading an Image**: Start by clicking the plus icon, uploading your desired image, and then copying the link to use in the Midjourney bot.
  • 📝 **Structure of the Prompt**: The prompt should include the image prompt first, followed by a text description and parameters.
  • 🎨 **Influencing the Output**: Midjourney uses the uploaded image to produce an output based on the given text prompt and parameters.
  • 👩‍🦰 **Personalization Example**: The video uses the creator's girlfriend's headshot as an example to demonstrate how the image prompt works.
  • 🌟 **Creative Exploration**: Experiment with different concepts like transforming the person in the image into a Greek goddess or a superhero.
  • 📐 **Aspect Ratio Parameter**: Ensure the aspect ratio of the output matches the uploaded image for the best results.
  • ⚖️ **Image Weight (IW) Parameter**: Adjusts the influence of the image versus the text in the prompt, with a range from 0.5 to 2 and a default of 1.
  • 🔄 **Blend Feature**: Allows blending up to five images to merge their concepts and aesthetics into a new image, best used with identical aspect ratios.
  • 🤔 **Comparison of Options**: The creator prefers using multiple image prompts with forward slash imagine for more control over descriptions.
  • 🧪 **Testing Blend Feature**: The video demonstrates blending two images, one of Rosie the Riveter and another of the creator's girlfriend, resulting in a unique output.
  • 🌐 **AI Platform Competition**: Midjourney is currently leading in certain aspects, but the creator is also exploring other platforms like Google and Adobe for future comparisons.

Q & A

  • What is the primary purpose of using image prompts in mid-journey?

    -The primary purpose of using image prompts in mid-journey is to influence the composition, style, and colors of the generated image based on the uploaded image and the text prompt provided by the user.

  • How does one upload an image to use as an image prompt in mid-journey?

    -To upload an image, you click the plus icon, select 'upload a file', choose the image you want to use, and then hit enter. After opening the image in the browser, you copy the link of the actual photo, which is used to interact with the mid-journey bot.

  • What is the structure of a prompt in mid-journey when using an image prompt?

    -The structure of a prompt in mid-journey when using an image prompt is 'image prompt' followed by 'text prompt', which includes a description of what to imagine from the journey, and then the parameters.

  • What is the significance of matching the aspect ratio of the uploaded image to the parameter in mid-journey?

    -Matching the aspect ratio of the uploaded image to the parameter ensures that the output image maintains the same proportions, which is crucial for achieving the desired composition and style.

  • What does the image weight parameter (-IW) control in mid-journey?

    -The image weight parameter (-IW) controls the importance of the image versus the text portion of a prompt. A higher -IW value means the image prompt will have more impact on the finished job, while a lower value will allow the text prompt to have more influence.

  • What is the default value for the image weight parameter in mid-journey?

    -The default value for the image weight parameter in mid-journey is typically one, which is suitable for most uses according to the script.

  • What happens when the image weight parameter is set to a high value in mid-journey?

    -When the image weight parameter is set to a high value, mid-journey tends to produce outputs that are more influenced by the initial image and less by the text prompt, which can result in less creative or less relevant outcomes for certain tasks like logo creation.

  • What is the blend feature in mid-journey and how does it differ from using multiple image prompts?

    -The blend feature in mid-journey allows users to blend up to five images by uploading them quickly and merging their concepts and aesthetics into a new image. It differs from using multiple image prompts as it does not allow for exact descriptions with each image, instead, it focuses on blending the overall aesthetic and concept of the uploaded images.

  • Why is it important to have identical aspect ratios for the images being blended in mid-journey?

    -Having identical aspect ratios for the images being blended ensures the best outputs by maintaining the compositional integrity and avoiding distortions or unwanted cropping of the images.

  • What is the creator's opinion on mid-journey compared to other AI platforms like Google and Adobe?

    -The creator believes that, at the time of the script, mid-journey seems to be at the top for certain tasks, although they acknowledge that Google and Adobe are investing heavily in their AI platforms and expect them to have phenomenal capabilities in the future.

  • What future content does the creator plan to produce regarding mid-journey and other AI platforms?

    -The creator plans to produce more tutorials, including comparisons between mid-journey and stable diffusion, highlighting the pros and cons of each when it comes to creating logos, realistic, and hyper photo-realistic imagery.

Outlines

00:00

🎨 Image Prompts in Mid-Journey: A Creative Tutorial

The first paragraph of the video script introduces the topic of using image prompts in the Mid-Journey AI tool. The speaker uses professional headshots of his girlfriend, Angie, as an example to demonstrate how to upload and manipulate images within the tool. The process involves uploading an image, copying its link, and then using that link in conjunction with a text prompt to guide the AI's output. The speaker explains the structure of the prompt as 'image prompt + text prompt + parameters' and emphasizes the importance of matching the aspect ratio of the uploaded image to the parameter settings. The video also showcases the results of using image prompts to create various themed images, such as a Greek goddess or a superhero, and discusses the 'image weight' parameter, which adjusts the influence of the uploaded image on the final output. The default value for this parameter is one, which the speaker found suitable for his purposes. The paragraph concludes with a teaser for future tutorials comparing Mid-Journey with other AI platforms.

05:02

🔄 Exploring the Blend Feature in Mid-Journey

The second paragraph delves into the blend feature of Mid-Journey, which allows users to combine up to five images to create a new, merged image. The speaker highlights the importance of having identical aspect ratios for the images being blended to achieve the best results. Using the cultural icon Rosie the Riveter and a photo of his girlfriend as examples, the speaker demonstrates how to upload and blend two images. The resulting image is described as meeting the speaker's expectations, showcasing the capabilities of Mid-Journey. The paragraph also mentions the speaker's plans to explore and compare Mid-Journey with other AI platforms like Stable Diffusion in future videos, and he encourages viewers to support his content through likes, comments, and subscriptions.

Mindmap

Keywords

💡Image Prompt

An image prompt is a visual input used to guide the AI in generating content based on specific visual elements. In the context of the video, the user uploads a photo to influence the composition, style, and colors of the AI's output. For instance, the video creator uses a headshot of his girlfriend to prompt the AI to imagine a Greek goddess, which results in a series of images influenced by the uploaded photo.

💡Mid-Journey

Mid-Journey refers to the AI platform being discussed in the video, which specializes in generating images based on prompts provided by users. It is an AI system that can take an image and a text prompt to produce unique visual content. The video demonstrates how to use Mid-Journey effectively, including adjusting parameters and blending images to achieve desired results.

💡Composition

Composition in art refers to the arrangement of elements in a work of art, including the way they are laid out and how they interact with each other. In the video, the AI's ability to influence composition is highlighted when the user uploads an image prompt and instructs Mid-Journey to create a specific scene, such as a Greek goddess, which the AI then incorporates into its generated images.

💡Aspect Ratio

The aspect ratio is the relationship between the width and the height of an image or a display. In the video, maintaining the same aspect ratio for the AI-generated images as the uploaded prompt is emphasized as crucial for achieving the desired output. The user instructs Mid-Journey to output images with a 4:5 aspect ratio, matching the uploaded photo, to ensure consistency in the visual results.

💡Image Weight

Image weight is a parameter in the AI platform that adjusts the influence of the image prompt relative to the text prompt. A higher image weight value means the AI will focus more on the visual aspects of the image prompt, trying to make the generated image closely resemble the input photo. In the video, the creator experiments with different image weight values to demonstrate how it affects the creativity and accuracy of the AI's output.

💡Blend Feature

The blend feature allows users to combine multiple images into one new image by uploading two to five images and letting the AI merge their concepts and aesthetics. This feature is particularly useful for mobile users and is demonstrated in the video by blending an image of the cultural icon Rosie the Riveter with a photo of the creator's girlfriend, resulting in a unique and visually appealing image.

💡Greek Goddess

In the video, 'Greek goddess' is used as a text prompt to guide the AI in creating an image that embodies the characteristics and aesthetics associated with ancient Greek deities. The AI then generates images that incorporate elements from the uploaded photo and the concept of a Greek goddess, resulting in a creative fusion of the two.

💡Superhero

The term 'superhero' is used in the video as a creative prompt for the AI to imagine the user's girlfriend as a character with superhuman abilities or powers. This demonstrates the versatility of the AI in interpreting and visualizing different concepts, and how it can adapt the uploaded image to fit various thematic roles or scenarios.

💡Corporate Logo

A corporate logo is a graphic mark or emblem that represents a company or organization. In the video, the creator uses the blend feature to ask the AI to create a corporate logo, demonstrating how the AI can be used for design purposes. However, the AI's output is influenced too heavily by the image prompt, resulting in a less effective logo design.

💡Super Villain

The concept of a 'super villain' is used in the video as another creative prompt for the AI. The user asks the AI to imagine the uploaded image as a super villain, which leads to the AI generating an image of a character resembling Harley Quinn, a well-known comic book villain. This showcases the AI's ability to interpret and visualize complex concepts and character archetypes.

💡Stable Diffusion

Stable diffusion is another AI platform mentioned in the video that is expected to have impressive capabilities. The video creator plans to compare Mid-Journey with Stable Diffusion in future tutorials to discuss their pros and cons, particularly in generating certain types of content like logos and hyper-realistic images.

Highlights

The tutorial covers how to use image prompts in Midjourney to influence job composition, style, and colors.

Image prompts can be combined with text prompts to guide the AI's output.

Uploading an image to Midjourney allows the AI to generate content based on that image.

The process involves copying the link of the uploaded photo for use with the Midjourney bot.

The tutorial demonstrates creating a Greek goddess image using a professional headshot.

Aspect ratio parameters should match the uploaded image for best results.

The Image Weight parameter adjusts the influence of the image in the final output.

A higher Image Weight value makes the AI more focused on the image, potentially reducing creativity.

The default Image Weight value is typically one, which is suitable for most uses.

Experimenting with an Image Weight of two can lead to different AI interpretations.

The Blend feature allows merging up to five images into a new concept.

Blend is particularly useful for mobile users and requires identical aspect ratios for best results.

The tutorial shows blending images of Rosie the Riveter and the presenter's girlfriend.

Midjourney's AI is capable of impressive image manipulation and creativity.

Comparisons between Midjourney and other AI platforms like Google and Adobe are planned for future tutorials.

The presenter encourages viewers to like, comment, subscribe, and share the tutorial for motivation.