Exploring Midjourney’s New Layer Feature: What Works and What Doesn’t Yet

midjourney blog post image

What’s New in the Midjourney Editor?

The latest Midjourney update redesigned the editor. Before, there were two separate editors – a “Full Editor” and a standard one. Now, these are combined. This means you can edit images created by Midjourney or your own photos in the same place. This unified approach is a positive step. The editor is now open to all subscribers, not just those who met specific criteria before.

Besides the combined editor, V7 also includes:

  • The new layer system (our main topic).
  • Improved smart selection (a feature available previously).
  • Better content moderation.
  • The return of the ‘weird’ parameter for unconventional images (using `–w` with values from 0 to 3000).

Layers and Retexturing: A Powerful Combination

The layer system lets you add images on top of each other. What works well is using layers together with the ‘retexture’ feature. Retexture keeps the overall layout of your composition but changes the style. This helps blend layered elements better.

Here’s one way layers and retexture can work:

  • Once your layers are arranged, use the retexture option. Provide a prompt describing the scene (e.g., “astronaut view from behind on Mars, title text at top”) and maybe a style reference (`–sref`). Midjourney will then recreate the entire composition in a new style, integrating the layered elements more smoothly.[/LI>

This retexture technique can help create complex scenes that would be harder to achieve with just a single prompt. It significantly improves how different image elements look together.

Where Midjourney Layers Need Improvement (No Retexture)

While retexture helps, the layer system on its own, without restyling the entire image, has limitations. Adding an element to an existing image without changing the style often results in poor integration. The new element can look very out of place, like it was simply pasted on.

Problemes include:

  • Difficulty blending images: Added layers may not match the original image’s lighting or shadows.
  • Selection tool challenges: While improved, using the smart selection tool isn’t always precise.
  • Lack of basic layer controls: You can’t easily rotate or flip layers, which makes precise placement difficult, especially when trying to match angles (like placing an object in a hand).

Users point out that other tools have features to automatically harmonize added elements with the background, adjusting colors and lighting. Midjourney currently lacks this “harmonize” function, which makes combining images without retexturing less useful for realistic compositions.

Creating images with multiple recurring characters is another area where layers are used due to the current absence of a character reference feature in V7. You can add two character images as layers and try to blend them. This can work, especially with the retexture feature. The trick is getting the source images of your characters to look similar in style and pose so they combine well.

Other Annoyances in the Current Editor

Beyond the integration issues, there are other points of frustration:

  • Suggest Prompt: This feature doesn’t read the whole composition. It only describes the currently selected layer, failing to recognize that multiple elements are present.
  • User Interface quarks: Simple actions like excluding a selected area or taking an image URL might not work predictably at times.
  • Mode Switching: Some options are unavailable depending on what mode you’re in (like conversational versus editing), and switching modes isn’t always intuitive.

These interface points add friction, making the creative process less smooth than it could be.

Conclusion

Midjourney’s new layer system in V7 is a promising feature with potential. It works quite well when used with the retexture function to create new compositions from existing images, helping to blend elements together stylistically.

However, the system currently falls short when trying to add elements to an image without changing the overall style. The lack of automatic harmonization and basic layer manipulation tools like rotation makes simple placement and blending difficult.

The editor itself also has some interface issues that can be frustrating. While not perfect yet, the layer system is a step towards more complex image creation within Midjourney. Hopefully, future updates will refine it, improve integration, and add more intuitive controls.

🖥

Do This Locally with Logen

Skip the subscription. Generate images like these on your own GPU — private, unlimited, no cloud dependency.

Try Logen Free →

Midjourney vs Logen

FeatureMidjourneyLogen
Cost$10-60/moFree & Pro plans
PrivacyCloud (images stored)100% local
GenerationsLimited by planUnlimited
Internet RequiredAlwaysNo
Custom ModelsNoYes (any ComfyUI model)
GPU RequiredNo (cloud)Yes (local)
Ease of UseDiscord botDesktop app
Try Logen Free →
FREE 11-PAGE PDF HANDBOOK + LOCAL AI FIELD NOTES

Get the Free 11-Page Local AI Image Generation Handbook

See what GPU VRAM you need for FLUX.1-schnell and SD 1.5, how checkpoints and LoRAs work, and five repeatable workflows on Windows and Linux x64. Enter your email to open the 11-page PDF right away and get our six-part weekly local AI field notes.

6–24 GB VRAM Tables Cloud vs. Local Math 5 Studio Workflows
How signup uses your email

We register your email with the TitanXT newsletter on beehiiv to send the 11-page PDF link, our six-part weekly local AI sequence, and occasional Logen updates. You can unsubscribe in one click from any email or by writing to support@titanxt.io. Read beehiiv's privacy policy (new tab).

Scroll to Top