Article
ArticleNewsWebsite navigation

AI painting Midjourney can generate images with consistent style, and will soon launch a feature to keep characters consistent

todayMidjourneyUpdated with a new feature called style references that generates images with a consistent style.

It's also very easy to use, just add the cue word after the---srefKeywords, and then just separate links to one or more reference images by spaces, e.g:

--sref url1 url2 url3

And the weight of each reference image can be adjusted to be enhanced by :: and numbers such as:

--sref url1::2 url2::3 url3::5

The intensity of the stylization can also be adjusted, via --sw, with a default of 100, 0 being off, and 1000 being the maximum, for example:

--sref url1 --sw 200

The --sref feature only affects the screen style, so the previous regular image cue (referencing the screen content) needs to be placed before the ---sref, and it is still recommended that it be placed at the very beginning of the cue word (as shown below).
AI painting Midjourney can generate images with consistent style, and will soon launch a feature to keep characters consistent
Precautions
  • The style reference applies to V6 models and Niji V6 models, older models are not supported;
  • Because it is still being tested, the feature may change significantly in the near future, so you need to be careful when using it;
  • If the tendency of the prompt is towards a realistic style, such as modern architecture, and you want to change it to another style referenced, such as illustration, this needs to be added in the prompt as well;
  • Style references have no effect on image cues and must contain at least one text cue word.
Soon, a feature to keep roles consistent will also be introduced, used in a similar way and invoked via the --cref parameter.
Demonstration
Made several examples using the same cue words, comparing image cues and new style references.
Example 1
Original image:
cover illustration, Penguin with watercolor, isolated white background, cartoon style, thick line,low detail,no shading
AI painting Midjourney can generate images with consistent style, and will soon launch a feature to keep characters consistent
Image Tip:
https://s.mj.run/21BQ-LiGbb4 cover illustration, cat with watercolor, isolated white background, cartoon style, thick line,low detail,no shading --ar 9:11 --v 6.0
AI painting Midjourney can generate images with consistent style, and will soon launch a feature to keep characters consistent

Style reference:

cover illustration, cat with watercolor, isolated white background, cartoon style, thick line,low detail,no shading ---sref https://s.mj.run/21BQ- LiGbb4 --ar 9:11 --v 6.0
AI painting Midjourney can generate images with consistent style, and will soon launch a feature to keep characters consistent
You can see that the difference between the two ways of referencing the images is still relatively large, the cat in the image cue is morphologically close to the original penguin, wearing a hat and scarf, round and chubby;
While the stylistic references only use similar styles, watercolors, and lines, the two are very different in terms of image content.
That is, the image cue will incorporate screen elements into the newly generated image, while the style reference is more about brushstrokes and texture.
To use a possibly inappropriate analogy.
Using image hints generates results that will make people say:
"Wow, it's a Monet painting."
And using a style reference generates results that will make people say:
"Wow, it's an impressionist painting."
Let's look at another example, this one where the image is more different from the cue word.
Example 2
Original image:
AI painting Midjourney can generate images with consistent style, and will soon launch a feature to keep characters consistent
Image Tip:
https://s.mj.run/IGEPdvEpo2M a girl --ar 2:3 --v 6.0
AI painting Midjourney can generate images with consistent style, and will soon launch a feature to keep characters consistent
Style reference:
a girl ---sref https://s.mj.run/IGEPdvEpo2M --ar 2:3 --v 6.0

AI painting Midjourney can generate images with consistent style, and will soon launch a feature to keep characters consistent

Because the image cues and text cues are relatively different, the result is that the former screen logic is not very good, while the latter style reference captures the essence.
Example 3
Example three is awesome, I used the two original images above as parameters, the penguin as an image cue, and the carriage as a style reference, and the effect is as follows:
https://s.mj.run/21BQ-LiGbb4 a cat --sref https://s.mj.run/IGEPdvEpo2M --ar 9:11 --v 6.0
AI painting Midjourney can generate images with consistent style, and will soon launch a feature to keep characters consistent

It references both the graphic elements of the penguin figure and the style of the carriage, blending to create kinda interesting graphics.

Stylistic fusion
Because the style reference can support multiple drawings and can also realize the characteristics of style fusion, an example from the Internet:
photograph of a mountain landscape --ar 16:9 --style raw --sref https://s.mj.run/EDG2Sh3Tktw https://s.mj.run/sLXYn-hJjOw --v 6

AI painting Midjourney can generate images with consistent style, and will soon launch a feature to keep characters consistent

This is all today, interested partners can actually go to experience.

Related content:

  1. Free for commercial use! Midjourney advanced skills, keyword list, experience summary
  2. Midjourney is slow to produce pictures? Are the pictures the same? Try these 3 parameter keywords!
  3. Midjourney drawing tutorial, use Midjourney to control character composition/screen ratio/photographic scene
  4. Tips Master teaches 5 elements of writing tips to help you easily conquer Midjourney V6
statement:The content is collected from various media platforms such as public websites. If the included content infringes on your rights, please contact us by email and we will deal with it as soon as possible.
MidjourneyKeywords
TutorialEncyclopedia

Byte version of GPTs "Coze Button" released, no-code AI chatbot usage application guide tutorial demonstration

2024-2-3 9:29:52

TutorialEncyclopedia

AI painting: Elegant temperament, cute and sweet smile [Stable Diffusion prompt words]

2024-2-5 9:40:18

You may also like
❯
Search

  • Scan to open current page

Top