Precision Prompting for Juggernaut XI and XII by Adam Stewart
This is a sequel to the earlier guide for Juggernaut X, which can be read here. Please review the earlier guide to get a foundation for the prompting styles of the Juggernaut X series.
Team Juggernaut
The Juggernaut Team is now officially part of RunDiffusion. Past iterations were sponsored by RunDiffusion. The team members have not changed and still includes Kandoo as our amazing trainer, myself (Adam) as Model Tester and Darin who handles more than I could list here. In addition we now have an amazing group of coworkers at RunDiffusion who help us with promotion and licensing. Once again I want to thank each team member and RunDiffusion for their contribution to improve the Juggernaut series of models.
Introduction
Juggernaut XI and Juggernaut XII are advanced AI models designed for professionals who need precise control and hobbyists. Juggernaut XI and XII except a wide variety of prompting styles, Detailed and specific prompts will allow a generative prompt engineer to create true masterpieces but these models offer an improvement over the base model Juggernaut X allowing basic prompts as well to create beautiful images.Audience: Juggernaut XI and Juggernaut XII are ideal for artists, designers, and visual professionals who require control over their image outputs.
Prompting Style: To leverage the full capabilities of Juggernaut XI and Juggernaut XII, prompts should be detailed and specific using trigger words provided to enhance the images. Juggernaut X required detailed prompts but Juggernaut XI and XII allow for simpler prompts as well as detailed.
Juggernaut XI & Juggernaut XII Settings
Juggernaut XI:
- Sampling Method: DPM++ 2M Karras
- Sampling Steps: 25-40
- CFG: 4-6
- Resolution: 1024x1024, 832x1216, 1216x832
- Possible Negative Prompt: Naked, Nude, fake eyes, deformed eyes, bad eyes, cgi, 3D, digital, airbrushed
Juggernaut XII:
- Sampling Method: 3M SDE Exponential, DPM++ 2M Karras, Euler (soft a Softer look)
- CFG: 4-6
- Possible Negative Prompt: Naked, Nude, fake eyes, bad hands, deformed eyes, bad eyes, cgi, 3D, digital, airbrushed
Key Prompting Tips for Juggernaut XI & Juggernaut XII
- Traditional Prompting Styles: Juggernaut XI and Juggernaut XII support traditional prompting styles, tags, or sentences.
- Importance of the First Sentence: The first sentence of the prompt is the most important as it sets the foundation for the image.
- Use of Weights: If using an application that allows weights such as Automatic1111 and Forge, apply them to the primary subject or objects to ensure they are emphasized in the generated image. Use weights sparingly.
Prompt Size: Try not to exceed 75 tokens. Exceeding 75 tokens reduces prompt adherence. - Tokens: Include some of the tokens at the bottom of this guide to enhance your prompts.
Key Trigger Words for Juggernaut XI & XII
To optimize image quality and detail, consider incorporating these trigger words into your prompts:
- Skin Textures: Great for detailed depictions of human skin.
- High Resolution: Ensures images are generated with utmost clarity. This token has three versions: “High Resolution”, "High-Resolution", or "High-Resolution Image."
- Cinematic: Perfect for creating dynamic, narrative-rich images with a film-like quality.
- Bad Hands: Juggernaut XII you can add bad hands to the negative prompt.
Components of a Prompt
Craft each part of your prompt to be direct and descriptive, avoiding unnecessary verbosity. The previous guide went into this in more detail but a quick recap.
- Subject: The primary focus of the image (e.g., person, animal, object).
- Action: Describes what the subject is doing, adding dynamism or narrative.
- Environment/Setting: The background or scene surrounding the subject.
- Object: Secondary items that enhance the subject or story.
- Color: Dominant colors or color schemes.
- Style: The artistic style or method of rendering.
- Mood/Atmosphere: The emotional or atmospheric quality.
- Lighting: Specific lighting conditions or effects.
- Perspective/Viewpoint: The angle or perspective from which the scene is viewed.
- Texture/Material: Prominent textures or materials visible in the image.
- Time Period: A specific era or historical period.
- Cultural Elements: Elements that reflect specific cultures or traditions.
- Emotion: The expressed emotion if the subject is sentient.
- Medium: Specifies the artistic medium or level of detail.
- Clothing: Ensure prompts clearly specify subjects are clothed by describing the types and styles of garments, particularly when avoiding inappropriate content.
- Text: Juggernaut has the ability to generate text, though accuracy decreases with sentence length and complexity. Use short, clear phrases enclosed in quotes to improve output.
Examples with Commentary
Let’s examine some raw examples without upscaling or high-res fixes:
A Lion with Juggernaut XI (Subject)
In this prompt, you can see that the focus is on the subject, making it the focal point of the image. How could we improve this prompt? Perhaps by adding details about the texture of the fur or the rocks.
Prompt: (Majestic lion:1.3) standing proudly on a rocky outcrop, mane flowing in the wind, sharp focus, looking into the distance with a powerful gaze, high resolution image
Negative Prompt: fake eyes, deformed eyes, bad eyes, cgi, 3D, digital, airbrushed
The main difference between these two prompts is that I specifically mentioned the fur and rocks, giving them more emphasis. The differences may seem subtle, but when you upscale, it makes a noticeable impact. I encourage you to be precise in your prompts. I’m also not cherry-picking here—these are the first images generated each time, and I'm providing you with the prompts so you can experiment as well.
Prompt: (Majestic lion:1.3) standing proudly on a rocky outcrop, mane flowing in the wind, coarse fur, rocks made of craggy sandstone, sharp focus, looking into the distance with a powerful gaze, high resolution image
Neg: Same
A Warrior Cat with Juggernaut XI (Action)
Prompt: A Warrior cat with a glowing axe charging into battle wearing armor, fierce expression, dramatic movement, in the style of fantasy realism, high resolution image
Negative Prompt: fake eyes, deformed eyes, bad eyes, cgi, 3D, digital, airbrushed, shield
Let's create a second variation with more detailed armor. Notice how changing "fierce expression" to "fierce warrior" dramatically altered his facial features. We also added more commentary about the armor, prompting the AI to include additional details. This is a stylistic choice, but it demonstrates how rewording can significantly impact the final presentation
Prompt: A fierce warrior cat with a (glowing enchanted:1.2) axe charging into battle with dynamic powerful movement, wearing ornate, battle-worn armor, fur bristling, intense gaze, in the style of fantasy realism, high resolution image, detailed metallic textures on armor, vibrant colors
Neg: Same
Forest with Juggernaut XI (Environment/Setting)
Create meaningful settings. Here’s a setting by itself—you could add a subject or object if you wanted, but let’s keep it simple for now.
Prompt: A forest with ancient trees with moss and a thick canopy, sunlight filtering through leaves, tranquil, cinematic lighting
Don’t be afraid to be specific to achieve the setting you want. For example, I added some flowers and a stream with ferns.
Prompt: A forest with ancient trees with moss and a thick canopy, ferns and pink wildflowers, a tranquil stream, sunlight filtering through leaves, tranquil, cinematic lighting
Crystal Orb with Juggernaut XI (Objects)
Don't be afraid to add objects to your scenes. It'll make them stand out and be unique from the mass assortment of generative images out there.
Prompt: A (crystal orb:1.1) resting on a wooden table, surrounded by aged scrolls and (alchemy tools:1.2), illuminated by candlelight, detailed texture
Don't forget to have fun! For instance, I added a yellow rubber duck inside the crystal sphere. You may also notice that some of the candles took on a yellow hue—this is called token bleed. You can minimize this by specifying the color of the candles in your prompt.
Prompt: A crystal orb resting on a wooden table with a yellow rubber duck, surrounded by aged scrolls and alchemy tools, illuminated by candlelight, detailed texture, high resolution image
Flowers with Juggernaut XI (Color)
You can add colors to the entire scene or to specific objects within it.
Prompt: A vibrant field of blooming flowers in full spectrum, with deep red roses, bright yellow sunflowers, rich purple lavender, and soft pink peonies, each petal reflecting the sunlight, creating a kaleidoscope of colors, lush green foliage providing a contrasting backdrop, all bathed in warm, golden hour light
Floating Islands with Juggernaut XII (Styles)
Juggernaut XII excels in handling various styles, among other capabilities. While I've primarily used Juggernaut XI let's take a look at some examples with Juggernaut XII. If you need a specific style, Juggernaut XII is the clear choice. It has been trained on a wide assortment of styles.
Prompt: (Surrealism:1.3) A dreamlike landscape with floating islands, twisted trees, and impossible architecture, vibrant colors, soft lighting
Prompt: (Monet painting:1.3) A dreamlike landscape with floating islands, twisted trees, and impossible architecture, vibrant colors, soft lighting
Dark or Silly (Mood and Atmosphere) with Juggernaut XII
Prompt: (A haunted cemetery:1.2) under a cloudy, moonlit sky, with ancient, cracked tombstones and twisted, gnarled trees casting long, sinister shadows, dense fog rolling over the ground, creating an unsettling atmosphere, in the style of Gothic horror
Prompt: (A whimsical cemetery:1.2) under a bright, sunny sky, with cartoonish gravestone, colorful flowers scattered around, cheerful animated ghosts in silly hats floating and playing pranks, fun lighthearted atmosphere, in the style of a family-friendly cartoon
A portrait (Lightning) with Juggernaut XII
Lighting has a profound impact on your creations—do not underestimate it. I suggest researching the lighting techniques of famous photographers and experimenting with different types of lighting to enhance your work.
Prompt: (Dramatic lighting:1.1) A portrait of a beautiful woman with sharp contrasts between light and shadow, creating a sense of depth and intensity, warm tones
Prompt: (Soft, diffused lighting:1.1) A portrait of a beautiful woman with gentle transitions between light and shadow, creating a subtle and serene depth, cool tones
What angle tells your story? (Perspective ) With Juggernaut XII
There are many ways to view a subject. Ensure you're asking for the right perspective to tell the story you want. A tip: use negatives when working with close-ups of faces. Let’s compare a close-up with a mid-shot. Keep in mind that other elements, like lighting, also play a crucial role in telling your story.
Prompt: (Moonlit lighting:1.1) A close-up of a mysterious man's face, with soft shadows highlighting his sharp features, the light reflecting in his intense eyes, cool tones creating a calm yet enigmatic atmosphere
Negative Prompt: fake eyes, deformed eyes, bad eyes, cgi, 3D, digital, airbrushed
Prompt: (Moonlit lighting:1.1) A mid-shot of a mysterious man standing in the shadows, with soft light revealing his sharp features and intense gaze, the light subtly outlining his silhouette, cool tones enhancing the calm yet enigmatic atmosphere
Smooth? (Textures) with Juggernaut XII
Juggernaut XII is the best in the series for handling textures, so I recommend it if your images require specific textures. It was also trained on a dataset of bad hands, so if you notice any hand deformities, consider adding that to your negative prompts.
Prompt: Silver long Silk cape flowing gracefully behind a beautiful woman with short black hair, the fabric catching the light with a soft shimmer with a metallic polished texture, in the style of fantasy realism
Negative: bad hands
Prompt: Silver long knitted cape flowing gracefully behind a beautiful woman with short black hair, the fabric catching the light with a soft shimmer with a coarse texture, in the style of fantasy realism
Negative: bad hands
Which era were you born? (Time Period) with Juggernaut XII
Specifying a time period in your prompt can help steer the AI toward a particular look and feel.
Prompt: 1970s scene a man wearing bell-bottom jeans and aviator glasses with a button up shirt, colorful patterns, style pop art
This one is pretty self-explanatory, so here’s another from the 1970s.
Prompt: 1970s scene a man wearing bell-bottom jeans and aviator glasses with a button up shirt, colorful patterns, background a disco
Are you Cultured? (Cultural Elements) with Juggernaut XII
We use a web of concepts because it guides the model toward our goals. Cultural elements, like time periods, serve to increase the probability of the model creating what we envision. For example, while we can instruct the model to create a Japanese woman in a kimono in space, specifying her in a Japanese temple is easier for the model to interpret and execute.
Prompt: Close up Portrait photograph of a woman in a kimono standing in a Japanese temple courtyard surrounded by gentle fog, surrounded by pink cherry blossoms, the intricate patterns of her kimono highlighted by soft sunlight, high resolution image
Negative: bad eyes, deformed eyes, fake eyes
That being said, the only reason to learn the rules is to break them, and a good model allows you to do just that. We teach the general rules to make your job as a prompt engineer easier, but don’t let them inhibit your creativity.
Prompt: Close up Portrait photograph of an Alien in a kimono standing in a Japanese temple courtyard surrounded by gentle fog, surrounded by pink cherry blossoms, the intricate patterns of her kimono highlighted by soft sunlight, high resolution image
Negative: bad eyes, deformed eyes, fake eyes
Happiness (Emotion) with Juggernaut XII
We've added more emotions to this dataset. Be sure to emphasize the specific emotion you want in your prompts for the best results.
Prompt: A (joyful:1.2) man running through a meadow, arms outstretched, face lit up with pure happiness, natural lighting
Negative: bad eyes, deformed eyes, fake eyes
Prompt: A (crying:1.2) man running through a meadow, arms outstretched, face lit up with pure melancholy, natural lighting
Negative: bad eyes, deformed eyes, fake eyes
It's not all about Photograph! (Medium) with Juggernaut XII
As a professional watercolor artist with years of experience, I've been amazed at how much AI has advanced over the past two years. What was once unable to replicate watercolors can now create masterful replications. Juggernaut XII is the best of the Juggernaut models at capturing various artistic mediums.
Prompt: A (watercolor:1.2) painting of a (tranquil lake:1.1) at sunset, soft brushstrokes capturing the serene atmosphere, subtle colors blending together
Negative: signature
Prompt: A (oil:1.2) painting of a (Clown:1.1) with large expressive eyes, bold brushstrokes capturing the sadness, vibrant colors
Negative: signature
Fit for a Queen! (Clothing) with Juggernaut XII
Juggernaut XI and XII excel at rendering clothing, with Juggernaut XII adding significantly more detail. Choose the version that best suits your specific needs.
Prompt: (Antique royal gown:1.2) with intricate embroidery, lace collar, and gold accents, worn by a regal queen, her posture elegant and poised
How about a superhero outfit?
Prompt: (A sleek superhero outfit:1.2) with metallic accents, intricate armor plating, and a flowing cape, worn by a powerful heroine, her posture confident and commanding, reflecting her strength and determination, in the style of modern comic book art
Movie Posters (TEXT)
Our team loves creating fictitious movie posters. When working with text, we recommend generating a batch of 3 or 4 versions and selecting the best one. If you're using an application that allows weighting, increase the text weight to at least 1.2, but do not exceed 1.4 for optimal results.
Prompt: Movie Poster with (text "Juggernaut":1.3) in bold metallic letters with a muscular woman flexing wearing battle armor, cinematic
When writing prompts that include text, it's best to place the text toward the beginning of the prompt.
Prompt: background black brick wall with (text "PROMPT GUIDE":1.3), foreground A skinny Bond villain, bald, wearing gold a black checkered suit
Rules?
You may notice that the prompts provided above are not full prompts but are designed to highlight specific aspects. They still work! You don't need to include every single element to get a beautiful image. The more you refine your prompt, the better the model can deliver what you need. However, if you're seeking flexibility, feel free to leave out certain elements.
Below are some examples of complete prompts.
Prompt: Style (Romanticism:1.2) close-up portrait of a beautiful (redheaded woman:1.3) with an intense gaze, wearing (elegant Victorian attire:1.1) in deep red and gold, background a (lush garden in full bloom:1.2) during the golden hour, mood serene, lighting soft and warm, perspective three-quarter view, texture (silk fabric:1.2) and delicate lace, cultural elements Victorian England, high-resolution image
Negative: cartoonish, abstract, (plain:1.1), fake eyes, deformed eyes, bad eyes, cgi, 3D, digital, airbrushed
Prompt: Style (Japanese ink painting:1.2) landscape of a (serene mountain village:1.3) surrounded by misty forests and (flowing rivers:1.2), in the style of (Sesshū Tōyō:1.3), with delicate brushstrokes capturing the (tranquil morning light:1.2), peaceful, perspective traditional wide-angle view, texture (soft ink washes:1.1) and crisp lines, (traditional Japanese architecture:1.2), monochromatic palette, high-resolution image
Negative: color, cartoonish, digital, (modern:1.1), cgi, 3D, airbrushed
Prompt: Style (Abstract:1.2) depiction of a (woman’s silhouette:1.3) with (dripping paint:1.2) blending vibrant colors, her form fluid and dynamic, mood expressive and surreal, lighting soft and diffused, perspective frontal view, texture (thick layers of paint:1.1) and smooth drips, (modern abstract art:1.2), high-resolution image
Negative:photorealistic, flat, (realistic:1.1), cgi, 3D, digital, airbrushed, naked, nude
Conclusion
We hope you enjoy the results of our hard work and create beautiful images with our models. We encourage you to experiment and explore new possibilities. These models are designed to be powerful tools for professionals while remaining accessible and user-friendly for casual creators. Your feedback is invaluable as we continuously iterate and improve.
Below are common Tokens for Juggernaut XII
- adult male
- alloy wheels
- animal portrait
- automotive photography
- beard
- bokeh
- bokeh background
- bokeh effect
- blonde hair
- blue eyes
- blue sky
- blurred background
- business attire
- casual attire
- casual clothing
- casual style
- caucasian
- clear sky
- clear skin
- clean lines
- close-up
- clouds
- cloudy sky
- confident expression
- confident pose
- contemplative expression
- cozy atmosphere
- curly hair
- dark background
- dark hair
- daytime
- depth of field
- detailed texture
- direct gaze
- dramatic lighting
- dusk
- elegance
- facial hair
- fashion
- fashion photography
- female
- focused expression
- forest
- front view
- full body
- glasses
- golden hour
- greenery
- hardwood floor
- headshot
- high contrast
- high dynamic range
- high resolution
- high-resolution
- high-resolution image
- indoor
- indoor setting
- indoors
- intense gaze
- interior design
- landscape
- large windows
- leisure activity
- long hair
- looking at camera
- looking away
- luxury vehicle
- makeup
- male
- man
- midshot
- modern
- modern architecture
- modern design
- moody atmosphere
- nature
- nature photography
- natural beauty
- natural light
- natural lighting
- natural makeup
- neutral background
- neutral color palette
- neutral colors
- neutral expression
- outdoor
- outdoor setting
- outdoors
- overcast sky
- parked car
- peaceful
- photography
- portrait
- portrait orientation
- reflection
- relaxed pose
- relaxed posture
- scenic view
- selective focus
- serene
- serene expression
- serious expression
- sharp focus
- shallow depth of field
- short hair
- side profile
- side view
- sitting
- smiling
- soft focus
- soft lighting
- solitude
- sports car
- standing
- standing pose
- studio lighting
- studio shot
- stylish
- sunglasses
- sunlight
- sunny
- sunny day
- sunset
- travel destination
- tranquil
- tranquil scene
- trees
- urban environment
- urban setting
- vibrant colors
- walking
- wall art
- warm color palette
- warm color tone
- warm colors
- warm lighting
- warm tones
- white background
- white shirt
- white sneakers
- white t-shirt
- wilderness
- wildlife
- wide-angle shot
- wristwatch
- woman
- wooden floor
- youthful
