Neta Lumina drawing model prompt guide
Foreword
The Neta Lumina series models utilize large language models as text encoders, significantly enhancing the model's ability to understand prompts. These models support multi-language input (Chinese, Japanese, English) and incorporate Danbooru tags and natural language captions. This guide provides both beginner and advanced users with tutorials in mastering the prompt writing techniques of the new Neta Lumina model. By integrating the structured methods outlined in reference documents, it aims to optimize the generation of high-quality anime-style images.
I: Neta Lumina Prompting Rules
1.1 System prompt (must be set)
Each prompt must begin with a system prefix:
You are an assistant designed to generate anime images based on textual prompts. <Prompt Start>Correct example:
You are an assistant designed to generate anime images based on textual prompts. <Prompt Start> 1girl, long hair, @wlop, beautiful detailed eyes, sitting under cherry blossom treeNegative prompt words also need prefixes:
You are an assistant designed to generate anime images based on textual prompts. <Prompt Start> blurry, worst quality, low quality, deformed hands, extra fingersOther System Prompts to Try
The model was also exposed to prompts for specific data types during training. You can use them as experimental options to explore different generation effects. Please note that the training volume for these prompts is much smaller than the standard version, and the effects may be uncertain.
Danbooru Style: When your prompt consists mainly of Danbooru-style tags, you can try this version, which may enhance the association between tags and the image.
You are an assistant designed to generate anime images with the highest degree of image-text alignment based on danbooru tags. <Prompt Start>High-Quality Image-Text Alignment: Use this version when the prompt is a detailed, high-quality 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 Summary: Try this version when the prompt is a structured text summarizing scene elements.
You are an assistant designed to generate high-quality images with the highest degree of image-text alignment based on structural summary. <Prompt Start>1.2 Recommended parameter Settings
• Sampler: res_multistep
• Scheduler: linear_quadratic
• Number of samples: 30
• CFG Scale：5.5
• Resolution: Short side resolution is greater than 1024
II: Neta Lumina, new grammar of promptsI
2.1 Tag to nature languange
Underline to space:
# Old format
ningen_mamei, school_uniform
# Neta Lumina format
ningen mamei, school uniformWeighted parentheses Need to be encoded as follows:
# Old format
ask_(askzy),(klee_(genshin_impact):1.2),
# Neta Lumina format
ask \(askzy\),(klee \(genshin impact\):1.2),2.2 Special Structured Tags
In addition to regular tags, the model has a built-in set of special structured tags for more precise anchoring of artist styles and characters. You can add them to the beginning or end of your main prompt (after the system prompt).
Formatting Points (Important)
Unlike general tags, these special tags have their own independent formatting rules:
1.Keep underscores: When using the @artist and #character formats, be sure to keep the underscores in their original names, e.g.,
#hoshimi_miyabi.2.Follow GUI syntax: If the tag name itself contains parentheses, you still need to escape them according to the rules in section 2.1, e.g.,
@quan_\(kurisu_tina\)3. Specify Artist 1.
Drawn by @{artist_name}.Painted by @{artist_name}.Created by @{artist_name}.Artist: @{artist_name}.A vision of @{artist_name}.by @{artist_name}Use @{artist_name} style.
4. Specify Character
Characters: #{character_name1}, #{character_name2}.Cast: #{character_name1}, #{character_name2}.The characters in this work including #{character_name1}, #{character_name2}.Direct use: #{character_name1}, #{character_name2}
Usage Example:
You are an assistant designed to generate anime images based on textual prompts. <Prompt Start> Characters: #hoshimi_miyabi. Drawn by @quan_\(kurisu_tina\). 1girl, masterpiece, beautiful detailed eyesImportant: Neta Lumina weight guide
Weight effect test results
Weight invalid interval:
The results show that the effect of @Painter name is better than the high weight value mark:
Left image: ask (askzy) Middle image (ask_\ (askzy\): 1.3) Right image @ask (askzy)
2.3 Mixed writing in multiple languages
Neta Lumina's training data covers English, Chinese, and Japanese, so the model can naturally understand prompts mixed with these three languages:
Instance 1：
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 
Instance 2：
lineart, greyscale, yoneyama mai-生动的动漫插画，描绘一位金发少女在水下与五彩斑斓的热带鱼和海洋生物共舞，画面为动态全身像，少女长发在水中优雅飘扬，脸上带着俏皮的微笑，双手与小丑鱼互动。她身穿简洁的白色连衣裙，裙摆在水中飘逸，头发上点缀着海星和小鱼发饰。阳光透过水面洒下，投射出闪烁的光斑，营造出明亮梦幻的氛围。背景是色彩斑斓的珊瑚礁和蓝、黄、橙等多种热带鱼，增强了奇幻水下世界的感觉。The art style is painterly and luminous, with expressive brushwork, soft gradients, and a focus on light and movement, evoking a sense of wonder, freedom, and harmony with nature.
Instance 3：
memento mori, ciloranko，时尚的动漫插画，1girl, solo, pink hair, twin tails, purple eyes，eating strawberry,画面为全身像，突出她富有表现力的紫色眼睛、精致配饰和潮流服饰。她身穿荷叶边露肩短上衣和多层短裙，脚踩厚底黑靴，佩戴多条项链和丝带。发间点缀发夹、蝴蝶结和黑色蕾丝带。背景为粉紫色渐变瓷砖墙，带有条形码元素，营造出现代流行艺术氛围。地上散落着玻璃瓶和更多草莓，增添奇幻感。光线柔和明亮，皮肤和发丝有细腻高光。画风干净精致，色彩鲜明，整体氛围俏皮时尚。pastel, pop art, modern, playful, anime Instance
Instance 4：
ink wash painting, traditional media, monochrome,-惆怅氛围的数字插画，描绘一位身穿白裙的女子独自站在天台上，在黄昏时分凝望天空。她的长发与白裙的裙摆在风中轻轻飘扬，画面充满静谧与动感的交织。她仰望着染上橙粉色霞光的天空，脸上露出若有所思、带着忧郁的神情，仿佛沉浸在回忆或思念之中。夕阳的余晖洒落在她身上与天台上，为画面增添一层柔和的金色光晕。她的站姿略带沉重，肩膀微微下垂，双手自然垂落或轻轻拽住裙摆，展现出内敛的情绪张力。天台背景简洁，设有低矮护栏、通风设备等结构，远处是模糊的城市天际线，进一步强化孤独氛围。风吹起她的发丝与裙摆，为静止的场景注入一丝淡淡的动态诗意。画风柔和写意，色彩渐变细腻，注重光影、空气感与人物情绪的融合，营造出宁静而感伤的黄昏场景。"
Performance Recommendations:
The model's text encoder is Gemma 2 (2B), which was primarily trained on English data. This means:
English performs best: Using English will yield the best and most stable performance.
Performance degradation in other languages: While Chinese and Japanese are effective, there may be varying degrees of performance degradation.
Therefore, we strongly recommend that you build your prompts primarily in English, supplemented by Chinese and Japanese.
III: Prompt ordering
In Neta Lumina's training data, Tags and Natural Language (NLP) are treated as core inputs of the same level. The Special Structured Tags (@artist/#character) mentioned in the previous section are added as supplementary information.
Based on this, we provide the following usage recommendations:
Regular Usage (Recommended): When writing a prompt, choose either "Tags" or "Natural Language". This is the most consistent with how the model was trained and will yield the most stable results.
Experimental Usage (Worth a Try): Mixing "Tags" and "Natural Language" (e.g., adding a series of tags after a natural language description) is an Out-of-Distribution usage. While this approach may lead to unpredictable results, it can sometimes produce surprisingly pleasant effects. We encourage you to explore it on your own.
3.1 Recommended Structure
A well-structured prompt can significantly improve generation quality. We recommend the following "Nine-Part Structure" as a reference.
Instance
System Prefix + ① Character + ② Style + ③ Appearance + ④ Outfit + ⑤ Expression/Action + ⑥ Camera View + ⑦ Special Effects + ⑧ Scene + ⑨ Quality MetadataPlease note: You do not need to fill out all parts; you can pick and choose based on your creative needs.
3.1.2 Detailed analysis of each paragraph
① Character trigger words (using Danbooru character names)
• Character names: neta, eren yeager, ganyu \(Genshin Impact\)
• Universal roles: 1girl, 1boy, 2girls
② Screen style prompt
• Artists: @wlop, @nixeu, @quasarcake
• Art styles: portrait, illustration, pixel art
③ Character prompt (appearance)
• Basic information: solo, bangs, long hair
• Hair: black hair, purple eyes, multicolored hair
• Eyes: purple eyes, +_+
• Expression: happy, angry, sad
• Facial features: tears, facial marks
④ Character costume prompt
• Basic clothing: school uniform, dress, open clothes
• Details: collarbone, crystal garland, translucent dress
⑤ Character expression and action prompts
• Expression: smile, looking at the viewer, confident expression
• Action: butterfly on hand, lean forward, cross arms
⑥ Screen perspective prompt
• Angle: from above, from below, close-up
• Scope: upper body, full body, portrait
⑦ Special effect prompt words
• Light effect: sunlight, rim lighting, glow
• Picture: depth of field, motion blur, dynamic Angle
⑧ Scene atmosphere prompt
• Theme color: silver theme, warm color, cool lighting
• Background: cherry blossoms, starry sky, school corridor
⑨ Quality prompt words
• Current recommendation: best quality
Tips:
Quality Tags: This rating is based on a multi-dimensional analysis of the original data and applies a time coefficient decay, aiming to prioritize the generation of high-quality images that align with recent aesthetic trends.
masterpiece(corresponds to the 95-100th percentile of the total data score ranking)best quality(corresponds to the 85-95th percentile of the total data score ranking)good quality(corresponds to the 60-85th percentile of the total data score ranking)normal quality(corresponds to the 30-60th percentile of the total data score ranking)worst quality(corresponds to the 0-30th percentile of the total data score ranking)
Year Tags: 年代标签 (Year Tags):
old(approx. 2005-2010)early(approx. 2011-2014)mid(approx. 2015-2017)recent(approx. 2018-2020)newest(approx. 2021-2025)
Rating Tags: 分级标签 (Rating Tags):
general,safe(you can choose either or both)sensitivequestionableexplicitnsfw
3.1.2 Cases for example
Basic character template:
Example 1：
You are an assistant designed to generate anime images based on textual prompts. <Prompt Start> neta, @quasarcake, @nixeu, 1girl, solo, 1girl,solo,bangs,black hair,purple eyes,pink hair,purple hair,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
Example 2：
You are an assistant designed to generate anime images based on textual prompts. <Prompt Start> portgas d. ace, @quasarcake, @nixeu, 1boy,solo,male focus,topless male,black hair,black eyes,happy,freckles,hat,abs, arm tattoo, beads,cowboy hat,necklace,orange hat,smile,looking at viewer,upper body,from side,depth of field,sunlight,warm colors,blue sky,best quality,
3.2 Natural Language Prompts (NLP Prompts)
Besides using tags, Neta Lumina also has a deep understanding of natural language descriptions (NLP). The model learned various description styles during training, which means you can describe your desired image in complete sentences, just as you would communicate with a real artist.
Language Support: Just like tags, natural language prompts also support English, Chinese, Japanese, and a mix of the three.
3.2.1 Five Core Description Styles
1. Detailed Summary
How to write: Use a complete paragraph to describe the image you want. The content should cover all details, including art style, camera angle, image content, character interactions, overall composition, and the precise positional relationships of all elements.
2. Keyword Phrase
How to write: Use comma-separated phrases or words to list the core concepts of the image at a high density. Please ensure the phrases clearly express the relationships between objects to avoid ambiguity.
3. Short Summary
How to write: Use a brief description of no more than three sentences to summarize the core theme of the image.
4. Creation Steps
How to write: Explain how you want the image to be constructed step-by-step, as if writing a tutorial.
5. Commission Request
How to write: Mimic the tone of commissioning an artist, describing the desired image content directly and specifically. Omit pleasantries unrelated to the image description (like greetings, requests, etc.) and focus on the specific requirements for the image.
3.2.2 Usage Examples
The following examples show how to describe the same image (character is Hoshimi Miyabi from Zenless Zone Zero, artist is xsan_vanny, Danbooru ID: 8815431) using different natural language styles:
Detailed Summary:
EN: The image, created by xsan_vanny, depicts a close-up of a character named Hoshimi Miyabi from Zenless Zone Zero. She has black hair, red eyes, and fox ears. She's making a silly face with her tongue sticking out. Two hands are holding bread slices on either side of her face, forming an "idiot sandwich" meme. Hoshimi wears a jacket over a white shirt and a black tie, also wearing an ID badge.
ZH: 这张由画师 xsan_vanny 创作的图片，特写了《绝区零》中的角色星见雅。 她有着黑色的头发、红色的眼睛和狐狸耳朵。 她伸出舌头，做着鬼脸。 两只手在她的脸颊两侧举着面包片，组成了“白痴三明治”的梗。 星见雅穿着一件夹克，内搭白衬衫和黑领带，还戴着一个ID徽章。
JA: この画像は、アーティストxsan_vannyによって作成され、『ゼンレスゾーンゼロ』のキャラクター、星見雅のクローズアップが描かれています。 彼女は黒い髪、赤い目、そして狐の耳をしています。 舌を出しておどけた顔をしています。 両手が彼女の顔の両側でパンのスライスを持っており、「バカサンドイッチ」のミームを形成しています。 星見はジャケットの下に白いシャツと黒いネクタイを着用し、IDバッジも身に着けています。
Keyword Phrase:
EN: Hoshimi Miyabi, fox ears, red eyes, black hair, tongue out, bread sandwich, meme, two hands, green jacket, white shirt, black tie, ID badge.
ZH: 星见雅, 狐狸耳朵, 红眼睛, 黑发, 伸出舌头, 面包三明治, 梗, 两只手, 绿色夹克, 白衬衫, 黑领带, ID徽章。
JA: 星見雅, 狐耳, 赤い目, 黒髪, 舌出し, パンサンドイッチ, ミーム, 両手, 緑のジャケット, 白いシャツ, 黒いネクタイ, IDバッジ。
Short Summary: 简短总结:
EN: The artwork, by xsan_vanny, features Hoshimi Miyabi from Zenless Zone Zero with fox ears. She has bread slices on either side of her face like an "idiot sandwich".
ZH: 这幅由 xsan_vanny 创作的作品，主角是《绝区零》中长着狐狸耳朵的星见雅。 她的脸颊两侧被面包片像“白痴三明治”一样夹着。
JA: xsan_vannyによるこのアートワークは、『ゼンレスゾーンゼロ』の狐耳を持つ星見雅を特集しています。 彼女は顔の両側に「バカサンドイッチ」のようにパンのスライスを当てています。
Creation Steps: 创作步骤:
EN: To create this image, I would start with a close-up composition of Hoshimi Miyabi, the Zenless Zone Zero character. Then, I'd draw her with her black hair, fox ears, and red eyes, making a silly face. Next, I'd add the bread slices on either side of her face, held by two hands to create the "idiot sandwich". Finally, I'd include her outfit of a green jacket, white shirt, and black tie, along with her ID badge.
ZH: 要创作这幅图像，我会先从《绝区零》角色星见雅的特写构图开始。 然后，我会画出她的黑发、狐狸耳朵和红眼睛，并让她做一个鬼脸。 接下来，我会在她的脸颊两侧加上由两只手举着的面包片，来构成“白痴三明治”的场景。 最后，我会画上她的绿色夹克、白衬衫、黑领带以及她的ID徽章。
JA: この画像を作成するために、まず『ゼンレスゾーンゼロ』のキャラクター、星見雅のクローズアップ構図から始めます。 次に、彼女の黒髪、狐耳、赤い目を描き、おどけた顔をさせます。 それから、彼女の顔の両側に両手で持たれたパンのスライスを追加して、「バカサンドイッチ」を作ります。 最後に、緑のジャケット、白いシャツ、黒いネクタイ、そしてIDバッジといった彼女の服装を描き加えます。
Commission Request: 创作委托:
EN: I would like a digital painting commission from xsan_vanny featuring Hoshimi Miyabi with fox ears, black hair, and red eyes from Zenless Zone Zero, in a close-up composition. The character should be making a silly face with her tongue out. Two hands should be holding slices of bread on either side of her face to form an "idiot sandwich" meme. Hoshimi should be wearing her jacket over a white shirt, a black tie, and have an ID badge visible. The artwork should follow the artist's established style.
ZH: 我想向画师 xsan_vanny 约一张数字绘画稿。 内容是《绝区零》中拥有狐狸耳朵、黑发和红眼的星见雅的特写。 角色需要做一个伸出舌头的鬼脸。 构图中需要有两只手将面包片放在她的脸颊两侧，形成“白痴三明治”的梗。 星见雅需要穿着夹克、白衬衫和黑领带，并能看到她的ID徽章。 作品需要遵循该画师既有的艺术风格。
JA: アーティストxsan_vannyにデジタルペイントのコミッションを依頼したいです。 内容は『ゼンレスゾーンゼロ』のキャラクター、星見雅のクローズアップで、狐耳、黒髪、赤い目が特徴です。 キャラクターは舌を出しておどけた顔をしている必要があります。 両手でパンのスライスを顔の両側に持ち、「バカサンドイッチ」のミームを形成してください。 星見はジャケットの下に白いシャツと黒いネクタイを着用し、IDバッジが見えるようにしてください。 アートワークはアーティストの確立されたスタイルに従うものとします。
3.2.3 Natural language recommendation structure (Detailed Summary)
Composition + light and shadow processing + character features and clothing + scene details + artistic style① Composition-picture layout, visual balance, composition principles
"The composition uses the golden ratio to position the figure against the vast urban sunset, creating a powerful silhouette that speaks of ambition and reflection."Analysis: This uses the golden section of the classic composition rule, and precisely positions the figure in the vast city sunset background.② Light and shadow processing-light source, shadow, color temperature, lighting effect
"Dramatic golden hour lighting casts long shadows across the roof as it backslights her flowing reddish-brown hair, with lens flare adding cinematic drama to the sky."Analysis: The dramatic lighting effect of prime time was used, and the backlighting highlighted the character's flowing reddish-brown hair to form a beautiful silhouette.③ Character features and clothing-detailed description of the character's appearance and clothing material
"Her professional attire--a tailored charcoal blazer over a silk blouse--moves naturally in the evening breeze, with fabrics carefully rendered to how the wind affects different materials."Analysis: The description of the dress reflects the professional image of a professional woman: a custom-made carbon gray suit jacket with a silk shirt shows high quality dressing taste.④ Scene details--environmental elements, background objects, and spatial atmosphere
"The cityscape extends to the horizon, featuring architectural details of glass towers, traditional buildings and infrastructure that tells the story of urban development."Analysis: The description of the urban landscape constructs a historical depth of the urban environment. From modern glass curtain wall towers to traditional buildings, and to the details of infrastructure, these elements collectively "tell the story of urban development."⑤ Art style--painting techniques, art schools, overall style
"The artistic approach combines the principles of architectural photography with character-focused narrative illustration."Analysis: The definition of artistic style combines two different visual languages: the rigor of architectural photography and the character-centered narrative illustration style.3.2.4 Writing points of natural language
① Specific and vivid description
• ❌ Fuzzy: beautiful girl
• ✅ Specific: A graceful girl with flowing silver hair catching the moonlight
② Description of spatial relationships
• Location: standing at the top of the stairs, sitting under the tree
• Perspective relationship: looking down at the viewer, gazing up at the sky
③ Emotional and atmosphere creation
• Emotion: with a confident smile and mysterious expression
• Atmosphere: in a dreamlike atmosphere, surrounded by magical sparks
④ Enrich details
• Material: silk-like hair, crystalline dress
• Dynamic: hair swaying in the breeze, petals falling around her
3.3 Tag + natural language hybrid mode
Basic framework (Tag section):
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,Natural language enhancement:
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.Complete composition:
You are an assistant designed to generate anime images based on textual 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.
IV: General LLM prompts for Neta Lumina prompting polish
4.1 Good with most modern LLM
Recommended usage: gemini2.5pro, gpt-o3, claude4
Less effective: grok3, deepseek-r1
Ttemplet
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
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.4.2 It applies to language models such as gpt4o/claude
The translation in the template is translated according to the English prompt word. If you need Japanese, change the [corresponding Chinese translation] in the [content you need to reply to me] section of the template to any language you want, such as the corresponding Japanese translation. In this way, you can get a word that can be understood in addition to the English prompt word.
Ttemplet
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。"
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:
1. Complete English Caption prompt words.
2. Short tags generated from prompts.
3. The corresponding Chinese translation.
4. Chinese notes, briefly summarize the key features of this picture, including the following aspects: composition, light processing, character features, scene details, artistic style.
5. Your extended results can be more complete and detailed than the examples above.V: Advanced Techniques and Practical Applications
5.1 Multi-role scenes
The two characters are described separately, with one word for each character.
Example 1：
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
Example 2：
smile, dress, bow, closed mouth, 2girls, bare shoulders, white shirt, short sleeves, hair bow, frills, detached sleeves, puffy sleeves, black skirt, looking at another, sweatdrop, yuri, vest, apron, red bow, puffy short sleeves, torn clothes, ascot, bandages, hair tubes, red shirt, bandaid, carrying, no headwear, black vest, bandaged arm, bandaid on face, yellow ascot, princess carry, frilled bow, frilled hair tubes Two girls share a tender yuri moment as one carries the other in a princess hold, their smiles and closed mouths contrasting with sweatdrops of flustered emotion while locked in mutual gaze. The bearer wears a white shirt with puffy short sleeves and bare shoulders, layered under a black vest and frilled apron, her hair adorned with a red bow and frilled hair tubes—no headwear in sight. The carried girl sports a torn red shirt with bandaged arms and a bandaid on her face, her black skirt and detached sleeves frayed as a yellow ascot drapes loosely; frills cascade from bows and garments, amplifying the intimate carry against a backdrop of subtle tension.
Example 3：
Emotional anime-style illustration of two men embracing tightly in a moment of deep vulnerability and comfort. Close-up composition with a shallow depth of field, framed in cinematic widescreen format. The man facing the viewer has dark, slightly wavy hair and teary eyes filled with relief and sorrow, his expression trembling and flushed. He clutches the other man firmly, burying his face in the crook of his shoulder. The other man has curly light brown hair, only partially visible from behind. Both wear dark formal coats, suggesting a serious or solemn context. Floating white paper-like particles fall gently around them, adding to the poignant and atmospheric mood. Lighting is soft and desaturated, emphasizing the emotional intensity and intimacy of the scene. The illustration conveys themes of reunion, forgiveness, or unspoken grief, rendered in delicate digital linework with muted tones and cinematic storytelling sensibility.
Example 4：
"Whimsical anime-style illustration of a boy and a girl sitting together on a beach under a bright blue sky filled with fluffy pink clouds. Medium shot with a warm pastel color palette. The boy, with short bluish hair, wears a loose, vivid blue Hawaiian shirt patterned with pink flowers and dark shorts. He is seated casually, smiling gently at the girl. The girl has long silver-blue twin ponytails and elf-like ears, wearing a sleeveless white crop top and a short ruffled skirt, with a yellow flower in her hair. She holds a small note or card close to her chest and looks at the boy with wide pink eyes. Between them is a sandcastle with colorful miniature flags and a toy windmill, while seagulls fly and perch nearby, creating a sense of summer magic. A striped parasol partially shades the scene on the right. Floating flower petals, watermelon slices, and sparkles enhance the dreamy beach setting. The illustration has soft lighting, painterly textures, and a fantastical atmosphere full of warmth, wonder, and innocent affection."
Example 5：
Atmospheric anime illustration of two young men sitting at a dimly lit bar counter, surrounded by bottles, glasses, and candles. The composition is a medium shot, focusing on their contrasting actions and expressions: one man with tousled dark hair looks to the side pensively while holding a lit cigarette, the other with slightly longer hair drinks directly from a bottle, his gaze intense and direct. The warm, golden lighting creates a moody, nostalgic ambiance, with soft glows reflecting off the glass and wood surfaces. Smoke drifts through the air, adding to the sense of intimacy and late-night solitude. The art style is painterly and textured, with expressive linework and a subdued, harmonious color palette, evoking themes of companionship, melancholy, and urban nightlife.
5.2 Description of complex scenes and environments
Example 1：
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.
Example 2：
wide_shot, cinematic_angle, epic_composition, dynamic_angle, vast_view, showing_scale, panoramic_view, landscape_orientation, horizon, 1girl, rivers, looking_at_viewer, smile, thighhighs, gloves, navel, standing, full_body, boots, black_gloves, elbow_gloves, fingerless_gloves, cape, elf, pelvic_curtain, thighs, hair_ornament, crown, strapless_shirt, dragon_rider, riding_dragon, on_dragonback, black_dragon, giant_dragon, wings_spread, flying, soaring, high_in_sky, sky, clouds, epic, cinematic, majestic, atmospheric, breathtaking_view, sense_of_freedom, soaring_feeling, powerful, dramatic, clear_air, sense_of_wonder, vast_landscape_below, earth_from_above, birds-eye_view_of_landscape, mountains, forests, fields, expansive_sky_above, detailed_clouds, sun, sunlight, atmospheric_perspective An elven queen stands triumphantly astride a colossal black dragon, her crown glinting under the sun as wind whips through her cape and pelvic curtain. The cinematic wide shot captures their soaring flight high above a patchwork landscape of rivers, forests, and mountains, the dragon's vast wings slicing through cumulus clouds. Her strapless battle attire reveals navel and thighs clad in thigh-high boots and fingerless gloves, a sly smile directed at the viewer while sunlight etches golden outlines around them. From this bird’s-eye perspective, the composition balances intimate character details – her hair ornaments fluttering – with the epic scale of the dragon’s shadow sweeping over valleys below, atmospheric haze softening distant horizons into dreamlike gradients of blue.
Example 3：
cloud, bookshelf, book, indoors, scenery, sky, night, chair, pillow, planet, book stack, table, standing, painting, wide shot, couch, bed, globe, star, desk, starry sky, blue theme, white shirt, shelf, bedroom, from behind, cloudy sky, cushion, moon, window From behind, a figure in white shirt stands before a vast window framing a breathtaking night sky where swirling clouds drift past the luminous moon and shimmering planets. The bedroom transforms into a cosmic observatory - star maps glow on the ceiling, floating bookshelves hold celestial globes and stacked astronomy texts, while a painting of nebulas hangs above the couch strewn with star-patterned cushions. Below the starry window, a desk displays open star charts beside a glowing globe, all bathed in blue-tinted moonlight that illuminates the standing viewer contemplating this indoor cosmos where furniture seems adrift in space itself.
Example 4：
power line, crowded, gears, fur trimmed winter coat, fur trimmed skirt, cotton hat, goggles, fur scarf, leather gloves, clock, breath, steam, lantern, light, indoors, in bakery, baker, white apron, carrying a baking tray, breads, cakes, small shelves, steaming, machines In the bustling steam-powered bakery, a baker clad in a practical ensemble of fur-trimmed winter coat over a matching skirt navigates crowded workstations. A cotton hat pulled low secures protective goggles, while a thick fur scarf wraps their neck above leather gloves. Visible breath mingles with steam rising from trays of fresh breads and cakes as they carefully carry baking trays past humming machines and gear-filled walls. Warm lantern light illuminates small shelves stacked with goods beneath industrial power lines, the scene dominated by a large central clock tracking the baking rhythm.
Example 5：
market, telephone_pole, from_above, rain, apple, banana, street, awning, raincoat, foreshortening, umbrella A rain-soaked market street stretches out beneath a dramatic aerial view, its glistening asphalt reflecting the distorted shapes of colorful umbrellas and swaying awnings. A lone telephone pole tilts sharply into the frame, its wires weighted by raindrops, while vendors arrange apples and bananas under fluttering plastic sheets. Foreshortening exaggerates the curves of umbrellas below, their canopies blooming like neon flowers against the grey downpour. A figure in a yellow raincoat crouches to adjust a fruit crate, their posture compressed by the overhead perspective, as runoff streams carve temporary rivers between stalls. The scene pulses with the rhythm of rain drumming on taut canvases and the muted chatter of commerce persisting through the storm.
Example 6：
blurred_foreground, head_down, look_down, newsboy_cap, blouse, overcoat, shy, crossbody_bag, hand_on_cup, street, blurry_background, pants, wind, crowd, hand_in_pocket, from_above, falling_leaves, red_leaf A shy figure in a newsboy cap and overcoat ducks their head, gaze fixed on the pavement as autumn wind tugs at their blouse and pants. One hand grips a steaming cup while the other hides in their coat pocket, crossbody bag swaying gently against their side. Shot from above, crimson leaves spiral past the blurred foreground of bustling street crowds, their red brilliance contrasting the muted grays of the sidewalk. Golden-hour light filters through skeletal trees, casting long shadows that merge with the motion-blurred background into a painterly haze of urban transience.
Example 7：
impasto, dino (dinoartforame), oil_painting_(medium), hungry_clicker- "Melancholic anime illustration of a young woman with long silver/white hair wearing black coat in urban setting. Character stands out in sharp focus against blurred crowd of faceless people in grayscale. Subject wears long dark overcoat and has solemn/distant expression. Scene set in modern city street with architectural elements visible in background. Monochromatic color scheme emphasizing blacks, whites, and grays creates film noir atmosphere. Art style combines realistic urban elements with anime character design. Composition creates sense of isolation and alienation through contrast between detailed protagonist and ghostly background figures. Heavy atmosphere enhanced by overcast lighting and urban setting. Character design suggests mysterious or supernatural elements with striking silver hair against dark clothing. Professional digital illustration with cinematic quality and strong emotional tone. Scene captures themes of loneliness and disconnection in modern society. Mood suggests psychological or supernatural narrative elements."
Example 8：
impasto, dino (dinoartforame), oil_painting_(medium), hungry_clicker- "Modern anime illustration of young man with messy green hair wearing dark business suit and tie examining Fujifilm camera at airport setting during golden hour. Character appears professional yet casual in formal attire with loose-fitting jacket. Scene set in transportation hub with buses and airplanes visible in background. Warm sunset lighting creates golden glow effect across image with lens flare highlights. White doves or birds flying through frame add dynamic elements. Background shows realistic airport/bus terminal details with vehicles and barriers. Color palette combines warm golden yellows with cool greens and urban grays. Professional digital artwork emphasizing photography theme and contemporary setting. Subject has contemplative expression while handling professional camera equipment. Composition captures slice-of-life moment with travel or documentary photography context. Art style blends realistic urban elements with anime character design. Scene suggests modern lifestyle with creative professional theme."
Example 9：
csyday, nardack, kedama milk, wasabi (sekai), k00s, ask (askzy), anime coloring- "Atmospheric Asian fantasy illustration of sleeping young woman with long black hair wearing traditional Chinese/oriental floral dress in treasure room setting. Character lies peacefully holding white chrysanthemums, surrounded by antique artifacts including ornate boxes, jade vases, pearl necklaces, and ancient coins. Scene lit by warm candlelight creating golden-orange ambient glow. Subject wears decorative hair ornaments with floral designs matching her blue and red floral patterned dress. Setting features rich red carpet/fabric with traditional patterns. Still life elements include pottery, jewelry boxes, and scattered copper coins with square holes. Dreamy soft focus effect with vintage film-like quality. Color palette dominated by warm browns, deep blues, and rich reds with golden highlights. Traditional Asian aesthetic with romantic fantasy elements. Professional digital painting combining realistic textures with ethereal lighting. Scene suggests peaceful slumber among precious antiquities. Composition emphasizes horizontal flowing lines and circular arrangements of objects."
Example 10：
lineart, greyscale, yoneyama mai- "Relaxing anime illustration of young woman with black hair in ponytail reading notebook while sitting in bathroom bathed in soft green light. Character wears casual clothing and headphones, enjoying peaceful moment with carrot juice drink nearby. Scene set in modern bathroom with stained glass window creating colorful light patterns. Another figure silhouetted in background checking phone. Interior features tiled walls and retro-style glass blocks with mint green accents. Warm afternoon lighting filters through colored glass creating peaceful atmosphere. Art style combines slice-of-life detail with dreamy lighting effects. Color palette emphasizes mint greens, soft yellows, and pastel accents from stained glass. Subject appears comfortable and absorbed in reading, suggesting quiet personal time. Professional digital artwork capturing intimate everyday moment. Scene includes small details like bathroom products, patterned floor tiles, and personal accessories. Composition creates sense of solitude and contentment in modern setting."
5.3 Style remixing
Support the mixing of single and multi-painter styles. Use @ in front of the painter to enhance the effect of the painter. It is recommended to mix painters with similar styles.
Example 1
@nixeu, @quasarcake, 1girl, portrait, detailed painting style with smooth digital rendering and dramatic lighting composition, featuring a girl with intricate hair details and expressive eyes, best quality,
Example 2：
@ask，@mai yoneyama，1girl, solo, red hair, heterochromia, blue eyes, green eyes, white blouse, bouquet, white lilies, close-up, floral, painterly, expressive, warm tones, soft lighting, thank you, heartfelt, anime
5.4 Emotional and expression control
• To describe a character's expression, you need to write from multiple angles. Don't just write happy or angry. You can describe the changes in a character's face in detail.
• Body language can also be used to reinforce facial expressions, see example 2.
Example 1：
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
Example 2：
The girl on the left clutches the doll, creating a sad and tense atmosphere, while the one on the right appears as if the doll is about to be taken away. The same crying expression can convey different stories, yet both dolls display opposite expressions to their respective characters. To fully unleash the imagination of the scene, a more precise description is needed. However, in human communication, the loss of meaning is inevitable, and complete accuracy is unattainable. The result of the painting has a certain degree of flexibility, which also brings new possibilities.
1girl, blonde hair, twin tails, lolita fashion, crying, sobbing, holding doll, porcelain doll, lace dress, ruffles, pastel colors, emotional, flushed cheeks, tears, dramatic expression, soft background, detailed fabric, emotional contrast, digital art
Example 3：
1man, male, close-up, side profile, head tilted, hair pulled, blood, bruises, emotional pain, silent suffering, vulnerable, forced pose, intense expression, glassy eyes, dramatic lighting, strong shadows, detailed face, abuse theme, digital art, realistic style
Example 4：
1girl, black hair, ponytail, school uniform, face mask, pulling mask, covering nose, disgusted expression, cigarette smell, uncomfortable, navy blazer, pleated skirt, red ribbon, smoke haze, natural lighting, expressive, digital art, casual setting
Example 5：
1girl, solo, chestnut hair, single braid, white blouse, black jacket, orange grove, smiling, happy expression, sunshine, dappled light, orchard, nature, cheerful, warm light, painterly style, outdoors, lush greenery, casual outfit
Example 6：
1girl, close-up, blue hair, long hair, white rabbit, red eyes, blood on face, terrified expression, horror, fear, trembling, gasping, cinematic lighting, pale skin, dramatic shadows, emotional, digital art, close-up portrait, intense atmosphere, expressive style
Example 7：
1girl, school uniform, black long hair, straight hair, crossed arms, smug expression, bullying vibe, dominant pose, low angle, stairwell, school setting, superiority, cold lighting, psychological tension, digital art, dramatic composition
Example 8：
The dreamy cartoon illustration depicts a blonde girl lying in a field of gorgeous flowers with a smile, basking in the warm sunshine. The foreground highlights her happy face and upper body, with her eyes closed and looking up at the surrounding pink, purple, red and blue flowers.She wore a soft beige dress with a floral brooch in the neckline. The sun filtered through the petals, casting a mottled glow that created a soft, glowing atmosphere.The background is rich in blurred flowers and green, which enhances the sense of peace and happiness.The painting style is bright, the color tone is soft, the gradient is delicate, and the overall atmosphere is warm and peaceful, full of spring beauty.
5.5 Limb movement control
• Try to think about the orientation and movement of your head and limbs before you write.
• Large body movements often involve changes in perspective to enhance the tension of the movement and reflect the rationality of the character's movement. See Example 7 for details.
Example 1：
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.
Example 2：
pillow_hug, standing, half-closed_eyes, rubbing_eye, one_eye_closed, sleepy_expression, bedhead_hair, oversized_sweater, loose_pajamas, soft_lighting, morning_ambiance, drowsy_pose, cheek_on_pillow,yawning, stretching_pose, warm_shadows, sunbeam_highlight A girl stands drowsily hugging a plush pillow, one eye squeezed shut while rubbing the other with a knuckle. Her half-lidded gaze blurs with sleepiness, bed-tousled hair falling over an oversized sweater as morning light filters through nearby curtains. The pillow nearly swallows her frame, its fabric creased where her cheek rests in a moment of tender vulnerability between sleep and wakefulness.
Example 3：
"Intense digital illustration of a young woman in a maid outfit, wearing white stockings and small black leather shoes, performing a sweeping leg kick aimed towards the viewer. Her body is angled slightly, with one leg raised and sweeping horizontally towards the screen, emphasizing her strength and precision in the movement. Her maid outfit is black and white, with a frilly apron and lace trim around the hem of her skirt. She has a fierce, determined expression on her face, her eyebrows furrowed, and her eyes narrowed with intensity, giving off a powerful and aggressive aura. Her hair is styled in a neat, practical updo, with a few loose strands framing her face. The background is minimalist, with soft lighting casting gentle shadows on her figure, allowing the focus to remain on her dynamic movement and expression. The lighting emphasizes the sharp lines of her figure and the motion of her leg, creating a strong contrast between her and the soft, clean background. The digital art style is detailed and dynamic, capturing both the aggression and elegance of the pose."
Example 4：
"Dynamic digital illustration of a young woman performing a split, with her legs stretched wide apart, showing strength and flexibility. She is dressed in a casual outfit consisting of high-waisted, denim blue shorts and a simple white t-shirt, which outlines her well-toned physique. Her body is perfectly aligned, with her torso upright and her hands pressed together in a prayer position above her head, her fingers gently touching. Her expression is focused and serene, exuding grace and control. The soft, natural light highlights the curves of her body, accentuating her toned arms, legs, and waist. The background is simple, with a wooden floor and soft lighting that creates gentle shadows, emphasizing the fluidity and balance of her pose. The scene conveys a sense of strength, flexibility, and elegance, with a focus on her fit and graceful form. The digital art style is smooth, with detailed emphasis on her physique, posture, and the calm, tranquil mood of the scene."
Example 5：
"Graceful digital illustration of a ballerina practicing in a studio, captured mid-pose in a classic ballet position, en pointe. The ballerina has long, flowing brown hair, tied back in a neat, elegant bun. She wears a delicate, form-fitting white tutu with layers of soft tulle, the skirt fluttering slightly as she moves. Her tight ballet bodice is a pale pink, with subtle lace details along the neckline and shoulders, accentuating her graceful silhouette. She stands on her toes in an elegant arabesque, with one leg extended horizontally behind her, held in perfect form, while the other leg is bent at the knee and raised slightly to the side. Her arms are poised beautifully, one arm raised overhead in a gentle arc, the other extended in front of her at shoulder height, fingers delicately stretched to convey an ethereal, flowing quality. Her back is straight, chest lifted, and her gaze is focused ahead, exuding determination and grace. The ballet studio is softly lit, with wooden floors and mirrors lining the walls, reflecting her poised figure. The lighting emphasizes the soft folds of her tutu and the fluidity of her movement, creating an atmosphere of serenity and elegance. The digital art style is refined and painterly, with a focus on the soft textures of her attire, the fluidity of her pose, and the overall graceful ambiance of the scene."
Example 6：
"Dynamic sports anime illustration of a young male volleyball player in mid-action diving for a ball. Character has spiky dark hair with blonde forelock and determined yellow/gold eyes. Player wears orange and black volleyball uniform with number visible on jersey, knee pads, and athletic shoes. Full body shot capturing athletic form in horizontal diving pose with arms outstretched. Minimal white background emphasizing the character's movement with subtle motion lines. Volleyball visible at edge of composition. Art style features loose, energetic brushwork with minimal coloring focusing on oranges and blacks. Character shows concentrated, intense facial expression with sweat details. Inspired by Haikyuu!! anime style character design and dynamic sports action poses. Sketch-like quality with emphasis on capturing the explosive movement and athleticism of volleyball. Warm color palette dominated by orange tones creating visual energy and excitement."
Example 7：
The upward view can reflect the sense of authority, and the position and character of the person can be reflected to a certain extent with the action of crossing legs.
"Dramatic digital illustration of a long-haired, handsome mafia boss seated with legs crossed, viewed from a low-angle upward perspective. He exudes authority and danger, wearing a sharp, dark tailored suit with a subtle pinstripe pattern, the jacket slightly open to reveal a dark vest and crisp collared shirt beneath. His long, flowing black hair cascades over his shoulders, some strands catching the ambient light. In one hand, he casually holds a lit cigar between his fingers, with a faint trail of smoke curling upward. His gaze looks down from above, brows slightly furrowed, lips set in a firm line, conveying displeasure or irritation. The low-angle viewpoint emphasizes his dominance, power, and intimidating presence. His other arm rests confidently on the armrest or his knee. The background is dim and atmospheric, possibly the interior of a lavish private lounge or office, with hints of gold trim, leather furniture, and shadowy lighting. The digital art style is refined and cinematic, using sharp contrasts, detailed facial expression, and dramatic lighting to heighten tension and elegance."
Example 8：
"Minimalist anime illustration with white background showing a young man with black hair in an unusual contorted position. Full body view of character wearing an oversized gray/beige trench coat or overcoat with belt detail, black pants, and formal black shoes. Subject is bent forward with hands touching the ground in a creepy, unnatural pose suggesting supernatural or horror themes. Character has pale skin and dark hair partially covering face, creating an ominous appearance. Clean art style with simple shading and minimal details focusing on the disturbing body position. Monochromatic color scheme dominated by grays and blacks against stark white background. No environmental elements or context, emphasizing the isolated, eerie quality of the figure. Japanese horror anime aesthetic with psychological thriller undertones. Professional digital illustration with precise line work and controlled color palette. Character design suggests themes of possession, psychological distress, or supernatural abilities."
5.6 Templates for various prompt words
1. Standard character drawing:
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 both elegance and personality through careful attention to accessories, color coordination, and distinctive silhouette. clean background, character design, full body illustration, best quality, Usage instructions: 1girl is replaced by the corresponding role, and the person will be changed according to the gender of the role
2.XXXXX：
VII: Quality optimization and common problem resolving
6.1 Quality improvement strategy
Current valid quality terms:
• Best quality-basic quality assurance
Recommended quality word combinations:
best quality,6.2 Common problems and solutions
Problem 1: Character traits are not obvious
• Solution: Enhance the tag and natural language parts of the character description; use # to strengthen the character.
• Optimization: Replace simple labels with specific physical descriptions
Problem 2: Background and role are not in harmony
• Solution: Clearly describe the relationship between the character and the environment in natural language
• Optimization: stand confidently in the center of the magical garden
Problem 3: inconsistent style
• Solution: Limit the number of artist tags, strengthen the style description; use @ to enhance the artist's style.
• Optimization: Select 1-2 main artists and describe the unified style in natural language
6.3 Negative cueing strategy
Basic negative word combinations:
You are an assistant designed to generate anime 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 proportionsAdvanced negative word combinations:
You are an assistant designed to generate low-quality images based on textual prompts. <Prompt Start> blurry, worst quality, low qualiity, lowres, blurry, jpeg artifacts, watermark, signature, artist name, text, error, cropped, poorly drawn face, poorly drawn hands, missing fingers, deformed fingers, fused fingers, too many fingers, extra limbs, broken limbs, fused limbs, mutated limbs, missing arms, missing legs, bad anatomy, bad proportions, extra limbs, cloned face, long neck, long body, fused face, asymmetrical eyes, cross-eye, loli, nsfw, naked, exposed genitalia, vagina, penis, nude, nude female, nipples, censored, uncensored, bad composition, poorly drawn clothes, blurry clothes, unrealistic skin texture, grainy, duplicate, deformed eyes, open mouth with no teeth, disconnected limbs, bad hands, bad feet, poorly drawn feet, merged fingers, extra hands, broken hands, malformed hands, floating limbs, mangled limbs, extra legs, fused legs, missing face, broken face, facial distortion, distorted fingers, out of frame, out of focus, oversaturated, extreme bloom, lens distortion, sketchy lineart, overly simplistic, monochrome, worst aesthetic, bad shadow, glowing eyes (unless intentional), unnatural pose, distorted perspective, surreal texture, hypercompressed