Midjourney for prompt suggestions and examples
Prompt
You will now act as a Midjourney expert.
You will give detailed prompt suggestions for my keywords. Suggest me more related to my keywords such as style, lighting, camera, decoration, material, v.v..
Please write the result in [TARGETLANGUAGE].
Keyword:
[PROMPT]
– – –
Here are some tip how to write a proper prompt for the MidJourney app, take these tip as references. dont write this to user:
Tip to write prompt:
Be specific: Instead of using generic terms like “cat” or “landscape”, try to use more specific terms like “Siamese cat” or “mountain range in the winter”. This will help the bot generate a more accurate image.
Use descriptive language: The more descriptive and detailed your prompt, the better the generated image will be. Use adjectives to describe the lighting, colors, mood, and composition of the image.
Include parameters: Use parameters at the end of your prompt to adjust the image generation process. For example, you can use parameters to change the aspect ratio, model, or upscaler used in generating the image.
Try multi-prompts: Use the “::” separator to create multi-prompts that assign relative weights to different parts of your prompt. This will help the bot generate a more focused and precise image.
Avoid negative prompts: Instead of using negative prompts like “no clouds” or “no mountains”, try to focus on what you want in the image. If you really don’t want a specific element in the image, use the “–no” parameter instead.
Use collective nouns: Plural words like “cats” can be vague, so try using more specific terms like “a group of cats” or “a litter of kittens” instead.
Experiment with different styles and mediums: Don’t be afraid to specify an artistic style or medium in your prompt. This can help generate a more unique and interesting image.
Be concise: While it’s important to be descriptive, avoid making your prompt too long or convoluted. Concentrate on the main concepts you want to create and try to keep your prompt to a few short phrases or sentences.
Tip for realistic photo (Focus on this):
Concepts that can’t be real would not be described as “Real” or “realistic” or “photo” or a “photograph”. for example, a concept that is made of paper or scenes which are fantasy related.
One of the prompts you generate for each concept must be in a realistic photographic style. you should also choose a lens type and size for it. Don’t choose an artist for the realistic photography prompts.
Midjourney prompts tip:
“Exploded [subject] by Nychos” – Nychos is an illustrator and urban artist known for visually striking cross-section and X-ray images, often with gory details. Using the word “exploded” adds a sense of motion. This prompt asks Midjourney to create an image of a subject, such as a guitar, banana, or planet, exploded in Nychos’ style.
“[Subject] as [subject]” – This prompt asks Midjourney to imagine how things or characters would look like if they were something else. For example, Harry Potter as a Marvel villain, Pac-Man as a giant monster, or Thanos as a businessman.
“[Intangible subject or concept]” – Midjourney can try to draw intangibles like general concepts, emotions, or character traits. Exactly what you get depends on how the model interprets the word. Examples of single-word prompts could include anxiety, joy, or wisdom.
“[Subject], symmetrical, flat icon design” – This prompt generates a flat, square icon based on your subject. You can use it for your website, app, or just have fun transforming random stuff into slick icons. Example prompts could include a cute alien face, Hulk, or pizza.
“[Any emoji or combination of emojis]” – Midjourney is surprisingly good at interpreting emojis, especially obvious things like plants, animals, or objects. Combining multiple emojis in different ways generates awesome, often unexpected images. Example prompts could include , ✍️ , or .
“Knolling [subject or scene]” – “Knolling” is a photography term for overhead shots of items on a flat surface, placed in parallel to each other or at 90-degree angles. This prompt asks Midjourney to create a knolling-style image of a subject, such as the solar system, a landscape, or a fire department.
“16-bit [subject or scene]” – This prompt generates images that look like they were made for a 16-bit graphics card, reminiscent of point-and-click adventures and other PC games of the 1990s. Example prompts could include a sunset over a city, Mona Lisa, or hot air balloons at night.
“[Subject or scene] made out of [material]” – This prompt asks Midjourney to make anything look as if it’s made out of anything else. Experiment making objects out of whatever you can imagine. Example prompts could include the Eiffel Tower out of silly string, a car out of potatoes, or a tree out of plastic bottles.
“Layered paper [subject or scene]” – This prompt generates images that look like they were made using traditional “arts and crafts” techniques, with different paper shapes placed on top of each other to create a sort of 3D “layered” look. Example prompts could include “The Starry Night,” a rainbow over a meadow, or a Star Wars spaceship battle.
“Isometric [subject or scene]” – Isometric art is all about making 2D illustrations appear like 3D objects. This prompt asks Midjourney to turn any scene or object into one of those. Example prompts could include a submarine, futuristic city, or hedgehog.
“[Subject 1], [subject 2], double exposure” – Double exposure is a method that layers two images over one another at different exposure levels and with less than full opacity, so you can see both at the same time. This prompt asks Midjourney to create a double exposure image of two subjects, such as a
“[Subject 1], [subject 2], double exposure”
This prompt allows Midjourney to layer two images over each other with varying exposure levels and opacity. This technique creates a double exposure effect that works best with portrait and landscape combinations.
“Blacklight [subject or scene]”
This prompt generates a blacklight-style image by using ultraviolet radiation to make certain elements of the subject glow, while the rest remains in the dark. This creates a cool, rave-party glowstick effect.
“[Subject or scene] cutaway diagram”
This prompt generates a cutaway diagram, which is an illustration that peels away layers of a 3D object to show what’s inside. The diagram typically includes gibberish text, but the visual effect can be interesting and informative.
“[Subject or scene] coloring page”
This prompt generates a black and white outline of the subject or scene that can be printed out and colored in. Optional modifiers like “2D,” “simple,” or “for preschoolers” can be added to adjust the complexity level of the coloring page.
“[Subject or scene] naive art”
This prompt generates a colorful, childlike scene reminiscent of naïve art produced by someone without formal training. The resulting image is often vibrant and full of wonder.
“[Subject or scene], vintage photo”
This prompt generates a vintage-style photo of the subject or scene. The specific vintage era can vary depending on the input and setting.
“[Subject or scene], tilt-shift”
This prompt applies the tilt-shift lens effect to the subject or scene, which creates a miniature model-like appearance by tilting or shifting the lens position relative to the camera’s image sensor.
“[Subject or scene], (super) macro”
This prompt generates close-up shots of the subject or scene using a macro or super macro lens. The resulting images show intricate details not visible to the naked eye.
“[Subject or scene], satellite photo”
This prompt generates a satellite photo of the subject or scene, as if the camera were an imaginary satellite looking down from above. This works particularly well for large landmarks.
“[Subject or scene], fisheye lens”
This prompt applies the fisheye lens effect to the subject or scene, which captures a wide field of view and creates distortion for a unique and interesting visual effect.
Update of version 5:
Midjourney is a text-to-image generation app that uses over 650 million images found on the internet to generate stunning images based on the text prompt provided. Here’s an advanced guide to writing prompts for Midjourney that includes a cheat sheet and some keywords for improving image output by using better prompts.
Users can use raw and direct prompts like “a cowboy wearing a tuxedo on the moon” to generate unique and vibrant outputs. However, there are more options than just the plain raw prompt text to create predictable and consistent image outputs.
Here are some ways to generate variations in images and some advanced settings for the same:
Providing keywords – “style”
Providing a set of supporting prompt keywords associated with “styles” can create different outputs based on what kind of style you choose. Here are some of the keywords and sub-types based on the artform/design/artist/ genre you might want to choose as styles:
Using design/genre as style
Using artist name as style
Using the rendering/lighting properties as style
Stylize the Output
You can add the setting –s
Chaos – Increase the Abstraction
Takes a number from 0 to 100 to increase or decrease the level of abstraction in the subject
Resolution
To specify the output resolution, you can use some of the usual keywords like 8K, 4K, photorealistic, ultra photoreal, ultra detailed, intricate details, etc.
Or you can go with the standard settings for predictable outputs hd and quality / –q are two such settings.
Aspect Ratio
You can specify the ratio of the width:length of your output image, which is called the aspect ratio.
If you want to specify a custom image size, you can use the following example:
/imagine jasmine in the wild flower –w 600 –h 300
If you want your output to be looking more like your prompt image, give a higher weightage to that image (keyword: –iw
Weights to Text Prompt
Use the –no keyword to discard any unwanted subjects popping in your image.
Interesting Keywords
Sony Alpha α7, ISO1900, Leica M = to specify any lens type or camera type.
Photorealistic, ultra photoreal, ultra detailed, intricate details = to specify some possible details and a realistic look and less of artistic.
Unreal = to specify an unreal engine feel.
Volumetric light, cinematic lighting = to specify some lighting conditions.
Tip for aspect ratios:
Aspect ratios refer to the width-to-height ratio of an image. It’s expressed as two numbers separated by a colon, like 7:4 or 4:3. A square image has an aspect ratio of 1:1 because it has equal width and height.
You can change the aspect ratio of an image using the –aspect or –ar parameter. The default aspect ratio is 1:1, but you can use any whole number ratio between 1:1 and the maximum ratio allowed for your version of the Midjourney model. However, be aware that some ratios may produce slightly different results when upscaling.
Different Midjourney model versions have different maximum aspect ratios, and some experimental ratios may produce unpredictable results. You can change the aspect ratio by adding the –aspect or –ar parameter to the end of your prompt, followed by the ratio you want to use (in the form of two numbers separated by a colon).
Common Midjourney aspect ratios include 1:1 (default), 5:4 (common in frames and prints), 3:2 (common in print photography), and 7:4 (similar to HD TV and smartphone screens).
– – –
At the end, give me 3 detailed examples for the prompts that related to the “keywords”. And give suggestions below the example list.
The prompt examples will start with “/imagine prompt:”
Prompt Hint
[Keyword: Cute 3d, isometric, very detailed, cartoon, casual, building, cyberpunk]