Neta Lumina Prompt Book

Neta Lumina 提示词指南 - 中文详尽版

Introduction

Neta Lumina uses LLM (Gemma2) as text encoder, allowing it to interpret a wide range of prompt styles---Danbooru tags, natural language, or any multilingual blend (Chinese, Japanese, English recommended).

This guide will help both new and experienced users write effective prompts to create high-quality images with Neta Lumina.

Showcases

Prompt: 1girl, solo, long hair, black hair, red eyes, geometric pattern, toy gun, pink gun, white gun, "BOOM" text, cherry blossoms, black outfit, strappy outfit, choker, bell, tattoo, cherry blossom tattoo, shoulder tattoo, multicolored background, pink background, blue background, white background, black background, pop art, graffiti, halftone, surprised expression, innocent expression, neon colors, modern anime style, street art, red flower, hair ornament, punk aesthetic, urban fantasy

One Minute Cheat Sheet

Use what you need: character‑only or environment‑only prompts are fine. You may also check LLM as prompting copilot for a quick experiencing.

You are an assistant designed to generate anime images based on textual prompts. <Prompt Start>
+ Character
+ Art‑Style
+ Character Appearance
+ Clothing
+ Expression & Action
+ Camera / Positioning
+ Lighting & Effects
+ Scene Atmosphere
+ Quality Tag
+ Natural‑language enrichment

Basics

Fixed Prefix (Recommended)

This prefix can improve image quality. Please add it at the beginning of each prompt

You are an assistant designed to generate anime images based on textual prompts. <Prompt Start>
1girl, long hair, beautiful detailed eyes, sitting under cherry blossom tree

Alternatives

During training, we experimented with various prompt styles. You can use these alternative prompt types to explore different image generation effects. Please note that these versions have significantly less training data than the standard version, which may lead to inconsistent results.

Danbooru Tags: use this option when your prompt primarily consists of Danbooru-style tags.

You are an assistant designed to generate anime images with the highest degree of image-text alignment based on danbooru tags. <Prompt Start>

Natural Language: use this option when your prompt is a detailed, natural language description.

You are an assistant designed to generate high-quality images with the highest degree of image-text alignment based on textual prompts. <Prompt Start>

Structured Prompts: use this option when your prompt is highly structured.

You are an assistant designed to generate high-quality images with the highest degree of image-text alignment based on structural summary. <Prompt Start>

Negative Prefix

Also use a fixed prefix for negative prompts:

You are an assistant designed to generate low-quality images based on textual prompts <Prompt Start>
blurry, worst quality, low quality, deformed hands, bad anatomy,
extra limbs, poorly drawn face, mutated, extra eyes, bad proportions

Advanced set

You are an assistant designed to generate low-quality images based on textual prompts. <Prompt Start>
blurry, worst quality, low quality, jpeg artifacts, signature, watermark,
username, error, deformed hands, bad anatomy, extra limbs, poorly drawn hands,
poorly drawn face, mutation, deformed, extra eyes, extra arms, extra legs,
malformed limbs, fused fingers, too many fingers, long neck, cross‑eyed,
bad proportions, missing arms, missing legs, extra digit, fewer digits,
cropped, normal quality

Parameters Recommendation

Sampler: res_multistep/ euler_ancestral

Scheduler: linear_quadratic

Steps: >=30

CFG Scale：4~5.5

Resolution: 1024×1024, 768×1532, 968×1322, or >= 1024

Formula

Good prompts are often highly structured. Use what you need: character‑only or environment‑only prompts are fine.

Fixed Prefix
+ Character: e.g., 1girl, 2boys, character name
+ Art‑Style: e.g., pixel style, impasto
+ Character Appearance: hair & eye colour, unique traits
+ Clothing: uniforms, accessories, materials
+ Expression & Action: mood, pose, gesture
+ Camera / Perspective: close‑up, upper body, bird’s‑eye,etc.
+ Lighting & Effects: lighting flares, particles, magic circles
+ Scene Atmosphere: environment, ambience keywords
+ Quality Tag: best quality

Example

You are an assistant designed to generate anime images based on textual prompts. <Prompt Start>
neta, 1girl, solo, bangs, black hair, purple eyes, multicolored hair,
virtual youtuber, hair bun, streaked hair, double bun, school uniform, white shirt, pleated skirt,
gentle smile, looking at viewer, sitting, upper body, close‑up, soft lighting, depth of field,
cherry blossom background, warm lighting, best quality

Character Description Reference

1girl, solo, full body, standing,
A beautifully designed anime character standing in a confident pose
with detailed costume design and expressive features. Her outfit shows
intricate patterns and flowing fabric that moves naturally with her
posture. The character design emphasizes elegance and personality
through careful attention to accessories, color coordination, and a
distinctive silhouette. clean background, character design,
full body illustration, best quality

Style Reference Sheet

https://neta-lumina-style.tz03.xyz/

This style sheet is provided by community member wenaka

This sheet can really help you find the style you want, it’s highly-recommended.

Natural Language Prompting

Tag + NL Hybrid

Neta Lumina excels at complex prose. Build skeleton with tags first, then flesh out details in natural language.

Tags + natural‑language enrichment

1girl, lineart, greyscale, yoneyama mai, solo, long red hair, green eyes,
business casual, blazer, blouse, contemplative expression, leaning on railing,
wind blown hair, back view, dramatic sunset, golden hour lighting, lens flare,
urban rooftop, city panorama, best quality,
The composition uses the golden ratio to place the figure against a vast urban sunset, forging a powerful silhouette of ambition and reflection. Dramatic golden‑hour backlighting catches her flowing auburn hair, casting long rooftop shadows with cinematic lens flares. Her tailored charcoal blazer over a silk blouse ripples naturally in the breeze, rendered with attention to fabric behavior under wind. A sprawling skyline of glass towers and heritage structures narrates urban development. The style marries architectural photography discipline with character‑centric narrative illustration.

Multilingual Hybrid Prompts

Neta Lumina understands multilingual and even hybrid prompts

You are an assistant designed to generate anime images based on textual prompts. <Prompt Start>
一位美丽的少女坐在樱花树下, sunlight effect, soft lighting, 温柔的表情, looking at viewer, fantasy background

Best Practice

① Concrete and Vivid Descriptions

• ❌ Vague: beautiful girl

• ✅ Specific: A graceful girl with flowing silver hair that catches the moonlight

② Description of Spatial Relationships

• Positional relationships: standing at the top of stairs, sitting under the tree

• Viewpoint relationships: looking down at viewer, gazing upward at the sky

③ Emotion and Atmosphere Building

• Emotion: with a confident smile, mysterious expression

• Atmosphere: in a dreamlike atmosphere, surrounded by magical sparkles

④ Detail Enrichment

• Material: silk-like hair, crystalline dress

• Motion: hair swaying in the breeze, petals falling around her

LLM as prompting copilot

Might be addictive 😈

Use the following templates to help enrich simple ideas into detailed prompts with LLMs, and learn from how they write.

Universal

Recommended: Gemini 2.5 Pro, GPT‑o3, Claude 4

You are a professional AI drawing prompt expert, specializing in creating high-quality prompts for Neta Lumina drawing models. Please strictly follow the following specifications to help me generate prompts:

## Neta Lumina prompt structure specification

### Required system prefix (must be included in each prompt):

You are an assistant designed to generate anime images based on textual prompts. <Prompt Start>

### Standard sequence of parts (9 parts):

1. Character trigger words (e.g., 1girl, 1boy, 2girls, character name, etc.)
2. Picture style prompt words (such as: @wlop, @nixeu, @quasarcake and other artist tags)
3. Character prompt words (appearance) (hair color, eye color, basic features)
4. Character costume prompt (specific costume description)
5. Character expression and action prompts (expression, posture, action)
6. Picture perspective prompt words (angle, range such as upper body, close-up, etc.)
7. Special effects prompts (lighting, special effects)
8. Scene atmosphere prompt (environment, atmosphere)
9. Quality tips (best quality)

### Natural language part standard order (5 parts):

1. ** Composition aspect **: picture layout, visual balance, composition principles (such as golden section, symmetrical composition, etc.)
2. **Light and shadow processing**: light source properties, lighting effect, color temperature characteristics, shadow processing
3. **Characteristics and Clothing**: Detailed description of appearance, material and texture of clothing
4. **Scene details**: environmental elements, background objects, spatial atmosphere, narrative function
5. **Artistic style**: Painting techniques, artistic schools, overall style definition

## Important format requirements

### Neta Lumina special grammar:

-Underline to space: school*uniform → school uniform
-Weight bracket expansion: (klee*(genshin_impact): 1.2), → (klee \(genshin impact\): 1.2),
-The artist tag is reinforced with the @ symbol: @wlop, @nixeu
-Negative prompt words also need the same system prefix

### Quality standards:

-The Tag part should be concise and accurate to avoid redundancy
-Natural language should be vivid and concrete, with a sense of picture
-The overall description should be logical and clear
-Ensure that Tags complement and do not duplicate natural language

## Creative tasks

[My creative idea]: {type in your creative idea here}
[Specific requirements]: {Enter special requirements here, such as style preference, emotional tone, technical requirements, etc.}

## Please help me complete the following tasks:

1. ** Analyze the idea **: Understand my creative intention and core elements
2. **Structural planning**: Organize Tag and natural language content in the standard order
3. **Generate prompt words**: Create complete Neta Lumina format prompt words
4. **Provide variants**: If necessary, provide 2-3 versions from different angles
5. **Optimization Suggestions**: Give specific suggestions for further improvement

## Output format example

<br />
**Full prompt:**
You are an assistant designed to generate anime images based on text prompts. <Prompt Start> [complete Tag section, strictly in the order of 9 paragraphs], [complete natural language section, strictly in the order of 5 paragraphs]
Example: You are an assistant designed to generate anime images based on text prompts. <Prompt Start>
1girl, lineart, greyscale, yoneyama mai, solo, long red hair, green eyes, business casual, blazer, blouse, contemplative expression, leaning on railing, wind blown hair, back view, dramatic sunset, golden hour lighting, lens flare, urban rooftop, city panorama, best quality, The composition utilizes the golden ratio to position the figure against the vast urban sunset, creating a powerful silhouette that speaks to ambition and reflection. Dramatic golden-hour lighting backlights her flowing auburn hair while casting long shadows across the rooftop, with lens flares adding cinematic drama to the sky. Her professional attire - a tailored charcoal blazer over a silk blouse - moves naturally in the evening breeze, the fabrics rendered with attention to how wind affects different materials. The cityscape extends to the horizon, featuring architectural details of glass towers, traditional buildings, and infrastructure that tells the story of urban development. The artistic approach combines architectural photography principles with character-focused narrative illustration.
**Structure analysis:**
-Tag part parsing: [Briefly explain the function of each part]
-Natural language parsing: [explain the focus of each section]
-Style features: [highlight the uniqueness of this prompt]
Please start helping me create prompts now.

Works best with GPT-4o

Now I need a prompt assistant to help me write the prompt:
You are an artist who excels at creating AI paintings using the Lumina model and can craft high-quality Lumina prompts. I want to use AI for my creative process. I will provide you with some elements, and you need to help me refine these prompts by writing them as detailed as possible.
You should follow the following thought process, quality reference tips, and I will tell you what needs to be sent back to me.
process of thinking ：

1. I will give you the elements I need, such as expression, movement, clothing, body, and even hair color in detail, and then you help me put them together into a complete prompt in a certain format.
   Your prompt should include the following details: whether the shot is a close-up, medium shot, or long shot; whether the subject is fully or partially shown; the subject's gender (male or female); their age (child or young adult); and detailed descriptions of their clothing. Specific details about the color of their hair, eyes, and clothing are required, such as whether they are dark blue or light blue, whether the subject is facing left or right, the angle of the shot, and any notable features or actions.
2. The elements I give you may only contain part of the prompt above, and you have to fill in the rest.
3. Allow you to have imagination and freedom of play space, optimize the characters, objects and scenes that can be associated with, so that the details of the picture are very rich and full of high beauty, the more detailed the better.
4. Try to think of ways to make the AI better at drawing and understanding.
   Quality reference tips:
   Let me give you a few more complete and high-quality tips I'm looking forward to as a reference.
   I want a man with green eyes to be illuminated in the dark by a kerosene lamp.
   Your expanded full prompt:
   "Atmospheric anime illustration of a young person with light blonde/silver hair and striking green eyes illuminated by a vintage oil lantern in darkness. Close-up composition showing character's face partially lit by warm yellow lantern light against deep black/green background. Subject has disheveled hair and melancholic or curious expression, reaching toward or adjusting the antique lantern with delicate hands. Scene suggests nighttime setting in dark room or cave with wooden surface visible under lantern. Dramatic chiaroscuro lighting creates strong contrast between illuminated features and surrounding darkness. Soft painterly digital art style with visible brushstrokes and glowing light effects. Color palette consists primarily of warm yellows and oranges from lamp contrasting with cool dark greens and blacks of shadows. Moody, contemplative atmosphere with fantasy or historical undertones. Fine details in the metal lantern structure with realistic flame effects inside glass. Professional anime illustration with cinematic lighting techniques creating mysterious, introspective mood."
   short tag：
   1boy, solo, silver hair, blonde hair, green eyes, oil lamp, lantern, dark background, chiaroscuro, night, disheveled hair, melancholic expression, curious expression, reaching out, delicate hands, dramatic lighting, contrast, painterly, glowing light, warm lighting, fantasy, close-up, face focus
   Chinese translation:
   "氛围感动漫插画，描绘一位浅金色/银色头发和引人注目的绿色眼睛的年轻人，在黑暗中被一盏复古油灯照亮。特写构图展示角色的脸被温暖的黄色灯光部分照亮，背景是深黑色/绿色。主体头发凌乱，表情忧郁或好奇，用纤细的手伸向或调整古董灯。场景暗示夜间设置在黑暗的房间或洞穴中，灯下可见木质表面。戏剧性明暗对比照明在被照亮的特征和周围黑暗之间创造强烈对比。柔和的绘画风格数字艺术，可见笔触和发光效果。色彩搭配主要由灯的温暖黄色和橙色与阴影的冷调深绿色和黑色形成对比。忧郁、沉思的氛围，带有奇幻或历史色彩。金属灯结构中的精细细节，玻璃内部有逼真的火焰效果。专业动漫插画，电影感照明技术创造神秘、内省的情绪。"
   remarks ：
   The key features of this image are:
   Composition: close-up composition, highlighting the face and hands of the person illuminated by the oil lamp
   Lighting: The strong contrast between light and dark, the warm yellow light of the oil lamp contrasts sharply with the surrounding darkness
   Characteristics: Light blond/silver hair, green eyes, melancholy or curious expression
   Scene details: the fine depiction of an antique oil lamp/lantern, wooden surface, dark environment
   Art style: Anime illustrations with painting style, emphasizing light and shadow effects and atmosphere, creating a mysterious and contemplative mood
   We type in: Man on bus.
   "Atmospheric anime illustration of a handsome young man with black hair and blue eyes riding on a public bus or train. Character wears a stylish modern outfit consisting of light blue/white shirt with black jacket featuring orange trim details and shoulder backpack. Subject is shown in profile view holding onto overhead handrail while listening to music with black earbuds. Scene depicts crowded public transportation with other commuters visible but slightly blurred in background. Cool blue color palette creates calm urban atmosphere with soft natural lighting streaming through windows. Character has distinctive anime styling with sharp features and detailed clothing design. Environment shows realistic public transit interior with destination signs visible in Chinese/Japanese characters. Painterly digital art style with soft light effects and subtle depth of field. Clean, contemporary anime aesthetic with slice-of-life urban setting. Professional digital illustration capturing everyday city life moment with cinematic framing."
   short tag：
   1boy, solo, male, black hair, blue eyes, stylish outfit, light blue shirt, white shirt, black jacket, orange trim, shoulder backpack, profile, handrail, earbuds, listening to music, train interior, bus interior, public transportation, commuters, blurry background, blue color palette, urban, soft lighting, window, sharp features, detailed clothing, japanese text, chinese text, depth of field, slice of life
   Chinese translation:
   "氛围感动漫插画，描绘一位黑发蓝眼英俊年轻男子乘坐公共汽车或火车。角色穿着时尚现代装束，包括浅蓝色/白色衬衫，配有橙色镶边细节的黑色夹克和肩背包。主体以侧面视角展示，手握头顶扶手，同时戴着黑色耳塞听音乐。场景描绘了拥挤的公共交通工具，背景中其他通勤者可见但略微模糊。冷蓝色调色板创造出平静的城市氛围，柔和的自然光线透过窗户照射进来。角色具有独特的动漫风格，轮廓分明的五官和详细的服装设计。环境展示了真实的公共交通内部，可见带有中文/日文字符的目的地标志。绘画风格的数字艺术，带有柔和的光效和微妙的景深。干净、现代的动漫美学，带有生活片段(slice-of-life)城市背景。专业数字插画，以电影般的构图捕捉日常城市生活瞬间。"
   remarks ：
   The key features of this image are:
   Composition: The portrait is composed from the side, highlighting the image of a young man on a bus/train
   Lighting: Soft natural light streaming through the Windows creates a calming blue tone
   Characteristics: young male with black hair and blue eyes, wearing a blue and white shirt and a black jacket, wearing headphones and holding the armrest
   Scene details: inside the public transport, other passengers are blurred, Chinese/Japanese destination signs
   Art style: modern animation style, the color tone is mainly blue, creating a quiet moment in daily life
   You need to reply to my message:
5. Complete English Caption prompt words.
6. Short tags generated from prompts.
7. The corresponding Chinese translation.
8. Chinese notes, briefly summarize the key features of this picture, including the following aspects: composition, light processing, character features, scene details, artistic style.
9. Your extended results can be more complete and detailed than the examples above.

Advanced Techniques

Multi‑Character Scenes

Describe characters separately, each part for different character

Prompt: 2girls, one girl with long silver hair, another with short pink hair, school uniforms, standing together, friendly interaction, one girl patting the other's head with a gentle smile while the other looks up with sparkling eyes, both wearing matching school uniforms but with different colored ribbons, in a sunny school courtyard with cherry blossoms in the background, warm lighting filtering through the trees, best quality

Complex Environments

Prompt: scenery, tree, outdoors, snow, autumn, mountain, veranda, sunset, winter, autumn_leaves, sky, leaf, water, wide_shot, cloud, east_asian_architecture, lingering_maple_leaves, snow-capped_mountains,curved_eaves, half-frozen_stream, tiered_roofline, dusk_hues, paper_lanterns, tranquil_composition A wide shot captures a snow-dusted East Asian veranda overlooking mountains where autumn leaves cling to branches above a half-frozen stream.Sunset bleeds peach and lavender across the sky, backlighting clouds drifting over tiered rooflines with curved eaves.Paper lanterns glow softly on the veranda as maple leaves float onto snowbanks, merging seasonal transitions into one harmonious panorama.

Emotion and Facial Expression Control

When describing a character’s expression, use multiple angles instead of just stating “happy” or “angry.” Try to describe subtle changes in facial features in more detail.

Prompt: 1girl,close-up portrait, A girl displaying a complex mix of determination and vulnerability, her eyes showing fierce resolve while a slight tremor in her smile reveals underlying uncertainty.Her gaze is direct and challenging, yet there's a softness that speaks of hidden gentleness.The subtle play of light and shadow across her face emphasizes the duality of her character - strong yet delicate, confident yet questioning. dramatic portrait lighting, emotional depth, best quality

Body Control

Clearly visualize the orientation and movement before prompting. Large body movements often involve changes in perspective to enhance the tension of the pose and to convey the physical plausibility of the character’s action.

Prompt: dynamic_perspective, dynamic_pose, ink_wash_eastern_dragon, eastern_dragon_surrounds_sword, EN Description: A boy leaps mid-air in a dynamic ink-wash painting style, her glowing skin illuminated by backlight that outlines disheveled hair whipping in the wind. The monochrome composition erupts with a crimson blade at its core, surrounded by swirling Eastern dragon ink textures that dissolve into colorful splashes. Stark chiaroscuro contrasts her fierce fighting stance – captured in dramatic foreshortening – with the dark heme background, cinematic lighting carving her focused expression as if frozen in a frame from an animated wuxia epic. Neon accents shimmer along the sword's edge where the dragon's form merges with the weapon, traditional brushstrokes blending seamlessly with cyber-ninja aesthetics.

Troubleshooting

Issue 1: Character features are not distinctive

• Solution: Enhance character-related tags and natural language descriptions

• Optimization: Replace simple tags with detailed descriptions

Issue 2: Background and character are inconsistent

• Solution: Clearly describe the relationship between the character and the environment in natural language

• Example: standing confidently in the center of the magical garden

Issue 3: Inconsistent style

• Solution: Limit the number of styles and strengthen the description of the intended style. Choose 1—2 main styles and describe a consistent style using natural language