Midjourney’s new AI tool challenges Photoshop’s Generative Fill

Midjourney, the popular AI art generator, has released a new feature that is set to rival the Generative Fill tool found in Adobe Photoshop. Dubbed ‘Vary (Region)’, the new tool lets artists and designers select an area within an image, then fill that region using the text-to-image generator. The new artwork can then be manipulated like any other element on the canvas.

What is Midjourney?

Midjourney is an online platform that allows users to create stunning artworks using artificial intelligence. Users can type in a text prompt, such as “a dragon in a forest”, and the platform will generate an image based on that description. Users can also modify the generated image by using various tools, such as ‘Vary (Strong)’ and ‘Vary (Subtle)’, which change the style and content of the image.

Midjourney’s new AI tool challenges Photoshop’s Generative Fill
Midjourney’s new AI tool challenges Photoshop’s Generative Fill

Midjourney has been praised by artists and designers for its ease of use and creative potential. The platform has also been used for educational purposes, such as teaching students about art history and visual literacy.

How does Vary (Region) work?

The latest feature from Midjourney, Vary (Region), is similar to the Generative Fill tool from Adobe Photoshop, which was released in May 2023. Generative Fill allows users to select an area of an image and fill it with content that matches the surrounding pixels. For example, users can remove unwanted objects or add new elements to an image.

Vary (Region) takes this concept a step further by using the text-to-image generator to fill the selected area. Users can type in a text prompt that describes what they want to fill the region with, such as “a hat on top of a character” or “a dolphin in a forest”. The platform will then generate an image that matches the prompt and blend it with the original image.

Users can also adjust the settings of the tool, such as the size and position of the region, the blending mode, and the remix mode. The remix mode allows users to change the prompt for the region without affecting the rest of the image.

What are the benefits of Vary (Region)?

Vary (Region) offers several benefits for artists and designers who want to create unique and original artworks using artificial intelligence. Some of these benefits are:

  • It allows users to experiment with different ideas and concepts without having to start from scratch.
  • It gives users more control over the generated image and enables them to fine-tune the details and composition.
  • It expands the creative possibilities of the platform and allows users to combine different styles and genres.
  • It saves time and effort by automating the process of filling regions with realistic and coherent content.

What are the limitations of Vary (Region)?

While Vary (Region) is a powerful and innovative tool, it also has some limitations that users should be aware of. Some of these limitations are:

  • It works best on large regions of the image (20% to 50% of the image). It is not a magic fix and often it may be best to do a Vary (Subtle) instead.
  • It may not always produce satisfactory results, especially if the prompt is too vague or too out of place. Users may have to try different prompts or settings to achieve their desired outcome.
  • It does not allow users to upload their own content. Users can only use the images generated by the platform or available on Unsplash.
  • It may not be compatible with some browsers or devices. Users may experience glitches or errors when using the tool.

Leave a Reply

Your email address will not be published. Required fields are marked *