Text-2-image
Midjourney
With this node you can generate images of anything, it's the original Midjourney image creator
Quick menu: click on any section to quickly go to it
Key features
- Original MidjourneyGenerate images as you would in Discord, but in much more controllable environment
- Better UI for generationTweak any parameter you like and want in a comfortable UI
- Easy image accessQuickly download any image or use it in any other nodes like Remove Background, Upscale and others
- All versions availableCreate images with any Midjourney version including new v6
How to use the node
Click on each step to see the corresponded image as an example and tutorial to follow
- 1. Type your ideaMidjourney works great with all prompts, from short to long ones. Keep in mind that Midjourney by default tries to create semi-artistic images
- 2. LaunchIf you don't like the result, simply press Start again. In order to get different results, it randomizes seed (the analog for Regenerate button in Discord bot)
- 3. Switch to v6 for better resultsNew 6th version of Midjourney better follows the prompt.
For example, in our prompt we asked for red beret and yellow coat, but default version (5.2) didn't differentiate between these elements and mixed colors. V6 followed the prompt exactly
Parameters
Generally as a basic user you would only need to type prompt, negative prompt, set up resolution if needed. However, you might need to change other settings, so here are the descriptions of what each parameter does.
Seed
The generation starts from a particular noise. The same seed number will give you similar results each time, whereas by changing it to another number may dramatically influence the final output.
We recommend to use different seed numbers if you're experimenting, and as soon as you find the perfect result, lock the seed by clicking next to the lock icon.
We recommend to use different seed numbers if you're experimenting, and as soon as you find the perfect result, lock the seed by clicking next to the lock icon.
Aspect ratio
A dropdown list of the most popular aspect ratios
The first number corresponds to width, the second one to height
The first number corresponds to width, the second one to height
Version
The dropdown list of all Midjourney versions
V6 is the most recent one, it creates the images of the best quality and follows the prompt the best
V6 is the most recent one, it creates the images of the best quality and follows the prompt the best
Chaos
The range: from 0 to 100
It influences how varied the initial image grids are. High --chaos values will produce more unusual and unexpected results and compositions. Lower --chaos values have more reliable, repeatable results.
It influences how varied the initial image grids are. High --chaos values will produce more unusual and unexpected results and compositions. Lower --chaos values have more reliable, repeatable results.
Stylize
The range: from 0 to 1000
Low stylization produce images that closely match the prompt but are less artistic.
High stylization create images that are very artistic but less connected to the prompt.
Low stylization produce images that closely match the prompt but are less artistic.
High stylization create images that are very artistic but less connected to the prompt.
Style Raw
A checkbox
While turned on, it makes the AI follow the prompt more
While turned on, it makes the AI follow the prompt more
Tiling
Checkbox
While turned on, it creates seamless images, both on X and Y axis
While turned on, it creates seamless images, both on X and Y axis
Weird
The range: from 0 to 3000
The higher the number, the more weird, strange and offbeat result you will get. Experiment with this parameter you want unique and unexpected outcomes.
The higher the number, the more weird, strange and offbeat result you will get. Experiment with this parameter you want unique and unexpected outcomes.
Niji
A dropdown which enables a version of Niji Midjourney
Niji is a unique stylized model, mainly used to produce artistic anime-like images
Niji is a unique stylized model, mainly used to produce artistic anime-like images
Style (Niji)
A dropdown of several Niji styles
Cute creates charming and adorable characters, props, and settings.
Expressive has a more sophisticated illustrated feeling.
Original uses the original Niji Model Version 5
Scenic makes beautiful backgrounds and cinematic character moments in the context of their fantastical surroundings.
Cute creates charming and adorable characters, props, and settings.
Expressive has a more sophisticated illustrated feeling.
Original uses the original Niji Model Version 5
Scenic makes beautiful backgrounds and cinematic character moments in the context of their fantastical surroundings.
How to use Start image
- 1. Upload image to any online image shareImgur is one of the easiest option
- 2. Past the link to the beginning of the prompt and press LaunchUsing Start image you will get a similar composition to your initial image, but it won't be 100% identical
- 3. Type --iw to change Start image influenceThe higher the number is, the more affect it will have on the final image. The range for --iw parameter: from 0.1 to 2
Note that the highest number will not give you 100% similarity to final image, so if you're looking for options to create images based on your references, use Stable Diffusion