Labnana
Nano Banana, GPT-Image-2 & Seedream 5.0 Pro AI Image Generator
4K
Nano Banana
GPT-Image-2
Seedream 5.0 Pro
Highly Detailed
Anime
UHD
Lossless
Portrait
Concept Art
Nano BananaNano Banana PromptsThe Nano Banana family on Labnana — Pro and 2 — documented with the prompts behind each result.Browse prompts
GPT-Image-2GPT-Image-2 PromptsOpenAI’s image model on Labnana, indexed with the prompts that produced each result.Browse prompts
Seedream 5.0 ProSeedream 5.0 Pro PromptsByteDance’s image model on Labnana — generation plus region-level editing that leaves the rest of the frame untouched.Browse prompts
Trending AI Image Prompts
Real prompts from Nano Banana, GPT-Image-2 and more
以图一为主角，参考图二画风，
竖版插画，干净利落的赛璐珞平涂风格，清晰硬边线稿，全彩，以冷白、浅蓝灰与淡米色为主的夏日清凉基调。这是一幅由同一只白发羊耳少女的三个瞬间拼合而成的状态卡片——安静看书、翻页继续看、躲在冰箱里被发现，三种平淡与一丝心虚在竖幅中上下铺展，如同翻开一本夏日避暑的安静漫画。
上中下的三联分割构图
整个竖版画幅被清晰地区分为三个大小不等的区块。左上方与右上方各自占据画面上半部的左右两半，形成对角线呼应的双联画。下方区块占据画面下半部全部宽度，面积最大，是整幅画的视觉重心。三个区块之间以极细的留白缝隙或浅灰色细线分隔，如同剪贴簿中并排贴在一起的三张拍立得。每个区块都有独立的纯色或极简背景，互不干扰，但又统一在相同的角色特征、画法与色调之下。
左上区块：小衬衣看书的平淡状态
白发羊耳少女位于左上方格内，呈半身或全身蜷躺的姿态。她躺在一个尚未明确交代的环境中，身下是简单的浅色平面。身穿一件略微宽大的白色或浅蓝条纹小衬衣，衬衣的下摆只扣了一两颗扣子，其余全部松开，露出腰腹的一截皮肤与肚脐。肚脐以一道极细的浅灰弧线轻轻勾勒。衣领自然地摊开在锁骨两侧，袖口卷到手肘，整体穿着显得随意而清凉。她的双手举着一本摊开的书，书页微微泛黄，封面是素色。她的目光落在书页上，眉毛平展，嘴唇自然闭合，没有任何上扬或下垂的弧度，整张脸呈现出一种专注而平淡的表情。一对柔软的羊耳从白色短发间垂落，耳尖轻轻搭在肩侧，一只耳朵内侧对着画面，耳廓的软骨起伏以极淡的灰线表现。头顶的羊角弯曲向后，角面有细微的横纹。背景是极淡的米白色。
右上区块：翻书的平淡延续
白发羊耳少女位于右上方格内，与左上格呈镜像或延续姿态。她依旧躺在同样的环境中，身穿同样松开扣子的小衬衣，双手依旧捧着同一本书。唯一的变化是她的手指正捏住一页书页的右下角，即将翻过——纸页被提起一半，与下方的书页之间形成一小片三角形的阴影。她的目光落在那页即将被翻过的文字上，表情依旧平淡如水，眉毛平展，嘴唇微合，看不出任何情节带来的情绪波动。羊耳与羊角的姿态与上一格基本一致，但其中一只耳朵微微转动了一个极小的角度——可能是对环境中某处细微声响的本能反应。身后的短发因躺姿而铺散在枕靠的表面，发丝的走向以几道流畅的弧线交代。背景是极淡的米白色，与左上格保持统一。
下方区块：冰箱里的心虚状态
镜头拉远，空间关系被完整揭示。白发羊耳少女正蜷缩在一个老式冰箱里，冰箱门大开，冷气从内部涌出，在冰箱外形成极细的白色冷雾，以半透明的锯齿状弧线表现。冰箱是典型的老式单门冰箱，外壳为奶油白或浅绿色，门内侧的搁架上放着几瓶饮料与半个西瓜。冰箱内部的灯发出淡黄色的光，照在她的脸上与身上。
她蜷腿坐在冰箱最下层的隔板上，膝盖几乎顶到胸口，小衬衣的下摆垂在腿侧，肚脐与腰腹在冷光下皮肤显得更白。脚上没有穿鞋，光脚踩在冰箱的金属隔板上，脚趾因冰凉而微微蜷缩。她的双手还捧着那本书，书页仍翻开在刚才那页，但她的注意力已经完全不在书上。她的脸明显泛红——不是炎热，而是“做坏事被发现了”的心虚与窘迫，红晕从颧骨蔓延至耳根与脖颈。眉毛微微上扬成一个无辜的弧度，眼睛瞥向一边——也就是冰箱门外的方向，瞳孔被冰箱灯光映出一个小小的暖色高光，眼白在暗部中显得格外分明，眼神中写满了“完了被发现了”的慌张。嘴唇微抿，嘴角僵硬地抽动，似乎正想编造一个借口但还没来得及开口。一对羊耳紧张地向后贴着头发，耳尖微微颤抖。身后的羊角几乎顶到了冰箱上层的隔板。她的周围是冰箱内部的瓶瓶罐罐，一瓶牛奶的瓶身挂满了冷凝水珠，一盒打开的布丁搁在她膝盖旁边。冰箱门外是正常的室内环境，可能有一道从房间窗户射入的自然光，与冰箱内部的冷黄灯光形成冷暖对比。背景为极淡的冷灰色，冰箱内部的冷白冷气与外部暖灰形成明确边界。
统一的羊耳少女特征
三个区块中，角色始终保持统一的外貌特征：白色短发，淡黄色或琥珀色眼瞳，头顶两侧弯曲的羊角，一对柔软垂落的羊耳。衬衣是同一件，书是同一本，发型保持一致。羊耳的姿态随情绪变化而微调——左上与右上是放松的垂落，下方是紧张的后贴。脸颊的红晕只在第三格出现，成为情绪转折的关键视觉信号。
赛璐珞风格的干净处理
全画采用硬边赛璐珞上色法。光影切割果断，亮部与暗部之间以清晰色块边界区分，不做渐变或晕染。头发的反光以白色硬边条直接铺在发丝暗部上方。皮肤的阴影用浅棕或浅橙色块直接叠压，阴影形状明确。冰箱内部的光源——淡黄色灯光——在角色身上投射出明确的高光区与阴影区，与冰箱外的自然光形成双光源效果，以干净的两套色块系统分别处理。冷气雾团以白色半透明块面与锯齿状边缘表现，饮料瓶上的冷凝水珠以白色小点精准点缀。线稿以粗细均匀的黑色或深棕线条勾勒，利落流畅，没有多余排线或厚涂堆叠。三格在色调上呈现明显的冷暖递进——上两格是温暖的米白与淡肤色，下方则引入冷白、浅蓝灰与淡黄灯光的对比，让观众从视觉上感受到冰箱内部与外部、清凉与闷热、平淡与窘迫之间的温差。View full prompt
生成一个精美插图，
明日方舟的阿米娅与杰克·斯帕罗在黑珍珠号上，
恶海涛天，杰克掌舵看着罗盘十分笃定；阿米娅则抓着缆绳，QAQ
画面充满故事感，
【Negative Prompt】
high frequency noise,moire pattern,fine speckles,micro dots,dense tiny lines,texture noise,grainy,film grain,excessively intricate details,clutter small elements,sharp artifical edge,over-sharpening artifacts,
bad hands, bad feet, missing fingers, extra fingers, extra hands, extra legs,
missing toes, extra toes, deformed hands, deformed feet,
mutated limbs, extra limbs, missing limbs,
fused fingers, fused toes, overlapping fingers,
twisted limbs, distorted limbs, broken limbs,
contorted body, unnatural joint, limb crossover,
intersecting limbs, body parts fusion,
malformed anatomy, wrong anatomy, floating limbs,
disconnected limbs, deformed body, mutated body,
extra body parts, duplicated limbs,View full prompt
Create one polished, source-grounded creative image. Create a polished four-frame stylized 3D storyboard of clearly adult firefighters performing a fictional apartment safety drill. Frame 1 ALERT: alarm activates. Frame 2 CHECK: responder assesses a smoky doorway from a safe distance. Frame 3 EXIT: adults follow a lit route while staying calm. Frame 4 CALL: team gathers outside and contacts emergency services. Use original rounded character designs, consistent red protective gear without real insignia, clean arrows, restrained smoke, and readable labels ALERT, CHECK, EXIT, CALL. Educational tone, no flames touching people, injury, gore, or named animation-studio style. Use only original worlds, characters, products, and organizations. Every depicted person is clearly an adult aged 25 or older. Do not imitate a named living artist or reference an existing franchise, celebrity, public figure, brand, trademark, or logo. No sexualized framing, gore, deceptive official seals, unsupported real-world claims, watermark, or signature. Keep anatomy, object construction, repeated details, lighting, perspective, and requested layout coherent. Render only explicitly requested text and no accidental extra lettering.View full prompt
Create one polished, source-grounded creative image. Create a glossy summer launch poster for a fictional idea-organizing tool called LUMA NOTE. Use translucent citrus-orange and turquoise shapes, condensation, playful sticky-note tiles, a luminous abstract sun, and a clean mobile-interface fragment with no resemblance to a real product. Strong sans-serif hierarchy with exactly this copy: LUMA NOTE, IDEAS IN MOTION, OPEN BETA. Warm white background, premium 3D graphic design, crisp alignment, inviting energy, no URL, price, testimonial, or unsupported claim. Use only original worlds, characters, products, and organizations. Every depicted person is clearly an adult aged 25 or older. Do not imitate a named living artist or reference an existing franchise, celebrity, public figure, brand, trademark, or logo. No sexualized framing, gore, deceptive official seals, unsupported real-world claims, watermark, or signature. Keep anatomy, object construction, repeated details, lighting, perspective, and requested layout coherent. Render only explicitly requested text and no accidental extra lettering.View full prompt
Create one polished, source-grounded creative image. Design a believable widescreen advertisement mounted inside a modern commuter train for an invented business book titled DESIGNING SMALL WORLDS by MIRA SEN. Show a clean original cover mockup beside concise copy: NOTICE MORE. BUILD LESS. TEST EARLY. Add a small button-like phrase READ THE FIRST CHAPTER. Use navy, cream, and signal orange, strong typographic grid, real train reflections and perspective, commuters softly out of focus. No bestseller badge, review quote, sales claim, publisher logo, QR code, or real brand. Use only original worlds, characters, products, and organizations. Every depicted person is clearly an adult aged 25 or older. Do not imitate a named living artist or reference an existing franchise, celebrity, public figure, brand, trademark, or logo. No sexualized framing, gore, deceptive official seals, unsupported real-world claims, watermark, or signature. Keep anatomy, object construction, repeated details, lighting, perspective, and requested layout coherent. Render only explicitly requested text and no accidental extra lettering.View full prompt
Create one polished, source-grounded creative image. Create a strict top-down knolling composition in which 28 carefully spaced workshop and botanical objects collectively form the silhouette of a hovering hummingbird. Use miniature pliers, colored thread spools, brass screws, paintbrushes, fern leaves, petals, seed pods, rulers, clips, and folded paper, all aligned at clean ninety-degree relationships while preserving the bird shape. Warm cream background, soft even shadow, four subtle color zones, museum-catalog precision, no labels or text. Use only original worlds, characters, products, and organizations. Every depicted person is clearly an adult aged 25 or older. Do not imitate a named living artist or reference an existing franchise, celebrity, public figure, brand, trademark, or logo. No sexualized framing, gore, deceptive official seals, unsupported real-world claims, watermark, or signature. Keep anatomy, object construction, repeated details, lighting, perspective, and requested layout coherent. Render only explicitly requested text and no accidental extra lettering.View full prompt
Create one polished, source-grounded creative image. Create a horizontal triptych of candid smartphone photographs following three clearly adult friends at a rainy flea market. Frame 1: laughing under one transparent umbrella beside vinyl crates. Frame 2: close-up hands comparing a tiny brass compass. Frame 3: walking away with paper bags reflected in wet pavement. Use believable phone-camera dynamic range, slight motion blur, imperfect tilted framing, realistic skin and fabric, cool overcast light with warm stall bulbs, and consistent people across all frames. No text or logos. Use only original worlds, characters, products, and organizations. Every depicted person is clearly an adult aged 25 or older. Do not imitate a named living artist or reference an existing franchise, celebrity, public figure, brand, trademark, or logo. No sexualized framing, gore, deceptive official seals, unsupported real-world claims, watermark, or signature. Keep anatomy, object construction, repeated details, lighting, perspective, and requested layout coherent. Render only explicitly requested text and no accidental extra lettering.View full prompt
{
"画面基础设定": {
"画风": "经典魔法少女赛璐璐手绘风格，平涂上色，干净利落手绘线条，无厚涂、无写实3D质感，4K高清，16:9画幅，光影柔和统一无明暗突变，人物无崩坏、无透视穿模",
"场景背景": "华丽欧式王座大厅，画面深处摆放雕花复古王座，整体氛围为守护向，核心叙事：蓝裙洛丽塔少女保护婚纱少女，暗黑水手服少女对峙二人",
"构图氛围": "中景人物互动特写，景深虚化背景突出三位少女主体，色调冷暖对比，暗黑水手服少女冷暗色调，洛丽塔与女王柔和暖调"
},
"角色详细动作与形象": [
{
"角色编号": "角色1（图一蓝发洛丽塔少女）",
"动作姿态": "站在画面中间位置，处于角色2与角色3中间形成阻隔；双手握持概念剪刀「织命」横举在身前，剪刀刀刃朝向角色2，身体微微侧转面向角色2，身体向身后的角色3倾斜，做出保护姿态，眼神警惕直视前方水手服少女"
},
{
"角色编号": "角色2（图二暗黑水手服少女）",右手佩戴黑色毛绒猫爪手套，左手为人类纤细素手",
"动作姿态": "站在画面左侧，身体正对中间的角色1；抬起佩戴猫爪手套的右手，指尖直指角色1方向，左手自然垂落身侧，眼神冷冽紧盯对面两名少女"
},
{
"角色编号": "角色3（图三婚纱女王）",
"动作姿态": "站在角色1正后方，从身后伸出双臂环抱住角色1；双手在角色1脖颈前方交叉交织紧扣，下巴轻轻搭在角色1的肩膀上，侧脸贴靠角色1后背，姿态依赖柔和；人物身后清晰露出欧式雕花王座轮廓"
}
],
"道具说明": {
"道具名称": "织命剪刀",
"外观": "高碳钢镜面刀身，深蓝色树脂握柄镶嵌银色卷草纹样，长短双指环结构，由角色1双手紧握横挡身前作为防御道具"
},
"画面核心叙事": "蓝洛丽塔少女手持剪刀隔开对峙的水手服少女，用身体护住身后被女王环抱的自己，王座衬托女王的特殊身份，整体画面传递少女挺身守护同伴的核心故事感"
}
请规避繁复的细微纹理、过度的细节刻画、颗粒噪点、粗糙质感、斜向网格纹路、瓷砖式重复纹样、泥污类叠加效果，同时去掉多余的闪光特效。
弱化复杂纹理质感，优先保证画面表面顺滑均匀、轮廓线条粗实清晰、主体轮廓辨识度高。
相较于堆砌细节，更注重造型利落、留白恰当、构图规整，打造干净的画面观感。View full prompt
Overall layout is a concept design sheet — Magical Girl · Iris. The concept design background is light grid paper. Color scheme follows Figure 1 and Figure 2. Three-view character turnaround sheet: front view, left side view, back view. Show clothing details. Use Chinese. The weapon is a cross-shaped long two-handed staff. The back view includes a large back bow that matches the front view; both the white inner hem and blue outer hem are slit at the back, and the blue outer hem is shorter than the white inner hem, matching the length shown in the front view.
The nun's veil has 1 layers, and its length is 2/3 of the hair. Hair length reaches the waist.View full prompt
Replace the characters from image 2 and image 3 completely into the scene of image 1, strictly maintaining the body posture, facial expression, gaze angle, and all subtle movements of the characters in image 1 without any deviation. The clothing should remain consistent with image 2 and image 3 respectively, with image 2 on the left and image 3 on the right. Ensure that after replacement, the characters fully integrate with the scene's lighting, perspective, and compositional atmosphere, avoiding any sense of disjointed layering or perspective errors. Focus on optimizing the proportions and symmetry of the characters' facial features, especially the perspective of the eyes and the position of the pupil highlights, which must precisely correspond to the expressions in the original images. Also, carefully handle the structure of the fingers and joint details to prevent common issues such as extra fingers, fused fingers, or structural distortion. The final result should be a highly cohesive anime-style image with clear and smooth character lines, natural color transitions, no obvious signs of artificial generation, and an overall quality resembling hand-drawn artwork by an original artist. Ensure that the characters' actions and expressions remain unchanged. The actions should fully reference image one.
proportions should maintain those of image 1, with a resolution of 4K.View full prompt
Why Labnana
The latest models, by real name
Nano Banana is Google's Gemini image model family, GPT-Image-2 is OpenAI's image model, and Seedream 5.0 Pro is ByteDance's. Labnana runs all three — pick one in the generator.
Free to start
Try image generation for free. No credit card required to make your first images.
Fast generation
Generations come back quickly, so you can iterate on a prompt instead of waiting on it.
A prompt library that shows its work
Every prompt in the library is shown with the real image it produced. Copy the prompt, or load it straight into the generator.
Reference images
Upload reference images to guide style, subject, or composition — useful for consistent characters and product shots.
High-resolution output
Generate detailed images up to 4K across portrait, landscape, and square aspect ratios.