Ai Image Prompts
产品介绍
从包含10,000+真实图像生成提示的精选库中推荐提示。兼容任何AI图像模型,包括Nano Banana Pro、Nano Banana 2、Seedream等。
资源信息
许可证信息摘自官方源,可能过时或缺失。商用前请以原仓库的 LICENSE 文件为准。
提示词库 · 2.3万
数据源:社区提示词库(MIT 许可,每日同步)共 15141 条提示词,按 11 个用途归类;同一条可归入多个用途,因此分类条数相加会大于去重后的总数。
命中 5717 条
Golden Hour Beach Fashion Editorial Prompt
product-marketingA realistic prompt for generating a fashion editorial image of a woman on a beach during golden hour. It emphasizes sun-kissed skin, a wet hair look, stylish bikini, cinematic sunlight, and ultra-detailed skin texture, aiming for a free, sensual, and natural mood.
展开提示词全文
{
"prompt": "Beautiful adult woman on a beach at golden hour, sun-kissed skin, wet hair look, natural sexy beauty, wearing a stylish bikini, confident relaxed pose, realistic body proportions, cinematic sunlight, ultra detailed skin texture, fashion editorial style",
"style": "realistic",
"quality": "ultra",
"lighting": "golden hour sunlight",
"camera": "50mm lens",
"mood": "free, sensual, natural",
"negative_prompt": "explicit nudity, pornographic pose, deformed body, bad anatomy, low resolution"
}
Casual Lifestyle Portrait with Nintendo Switch Prompt
product-marketingA detailed photorealistic prompt for generating an image of a woman sitting on a bed with Pokémon-themed sheets, holding a Nintendo Switch. It specifies soft ambient indoor lighting, natural skin tones, and uses detailed camera settings (50mm lens, f/1.8) and a negative prompt to ensure an authentic, relaxed, and intimate lifestyle photography style.
展开提示词全文
{
"prompt": "An attractive blonde woman in her 20s is sitting casually on a bed with Pokémon-themed bedsheets, wearing light, comfortable summer pajamas. She is holding and showcasing a Nintendo Switch console with a natural, confident smile. The scene is illuminated by soft, ambient indoor light from a window, creating a warm, relaxed, and intimate atmosphere. Realistic photo style with shallow depth of field, natural skin tones, subtle shadows, and gentle highlights. Composition focuses on authenticity, natural pose, and genuine expression, captured with a handheld camera look.",
"negative_prompt": "overexposed lighting, harsh shadows, unrealistic body proportions, exaggerated features, artificial skin texture, low resolution, cluttered background, studio lighting, cartoon style, distorted anatomy, fisheye lens",
"style": "natural lifestyle photography, soft ambient light, realistic detail, warm color balance",
"camera_settings": {
"lens": "50mm prime",
"aperture": "f/1.8",
"iso": "400",
"shutter_speed": "1/125",
"focus": "on subject’s face and Nintendo Switch"
},
"lighting": "soft indoor daylight, natural shadows, no artificial studio light",
"color_palette": "warm neutrals, soft pastel tones, gentle contrast",
"mood": "casual, intimate, relaxed, authentic",
"quality": "high resolution, sharp focus, realistic textures",
"aspect_ratio": "3:4"
}
High Fashion Cinematic Portrait Prompt
product-marketingA photorealistic prompt for generating a luxurious and confident portrait of an adult woman. It specifies a silk black dress, long dark hair, smooth natural skin, cinematic lighting, and uses an 85mm portrait lens and shallow depth of field to achieve a high-fashion photography style with warm tones.
展开提示词全文
{
"prompt": "A stunning adult woman, 25 years old, elegant and sexy appearance, smooth natural skin, long dark hair flowing softly, confident gaze, subtle makeup, wearing a silk black dress with a deep neckline, cinematic lighting, shallow depth of field, ultra realistic, high fashion photography, soft shadows, warm tones",
"style": "photorealistic",
"quality": "ultra",
"lighting": "cinematic soft light",
"camera": "85mm portrait lens",
"mood": "luxurious, confident, seductive",
"negative_prompt": "nudity, explicit sexual content, distorted face, extra limbs, blurry, low quality"
}
Luxury Car Lifestyle Portrait with Puppy Prompt
product-marketingA detailed JSON prompt for generating a high-end lifestyle photograph of a glamorous young woman sitting in a luxury sports car (Porsche), holding a small puppy. It specifies the subject's appearance, attire, the car's interior details (burgundy leather), and bright, soft natural daylight to achieve an influencer aesthetic.
展开提示词全文
{
"image_prompt": {
"subject": {
"description": "Young woman with fair skin and a glamorous appearance.",
"hair": "Voluminous, shoulder-length blonde hair styled in soft layers and waves.",
"face": "Blue eyes, defined eyebrows, soft natural glam makeup with nude glossy lips.",
"pose": "Sitting in the driver's seat, looking directly at the camera, hands gently lifting hair near the head."
},
"companion": {
"animal": "Small puppy, likely a {argument name="puppy breed" default="Goldendoodle or Cockapoo"}.",
"appearance": "Fluffy, golden-cream curly fur.",
"position": "Sitting calmly on the woman's lap, facing forward."
},
"attire": {
"clothing": "White, sleeveless bodycon mini dress with waist cutouts.",
"accessories": "Beige quilted leather handbag with a gold chain strap resting on the lap."
},
"environment": {
"setting": "Interior of a luxury sports car, specifically a {argument name="car brand" default="Porsche"}.",
"details": [
"Deep red (burgundy) leather seats and interior trim",
"Black leather steering wheel with visible Porsche logo",
"Modern center console with digital touchscreen interface",
"Stainless steel travel tumbler in the center cup holder",
"Sunroof and car window visible in background"
]
},
"technical_details": {
"lighting": "Bright, soft natural daylight entering through car windows.",
"style": "High-end lifestyle photography, influencer aesthetic, sharp focus, photorealistic.",
"framing": "Medium shot, eye-level perspective."
}
}
}
Nano Banana Prompt for Minimalist Branded Bag Concept
product-marketingA simple instruction prompt for Nano Banana to generate a minimalist concept design for a branded bag.
展开提示词全文
Minimalist branded bag concept
Nighttime Street Scene with Two Women in Surprise Poses
product-marketingA detailed JSON prompt for Nano Banana Pro to generate an image of two women—one blonde and one brunette—at night in a street/parking area setting, both exhibiting expressions of surprise or exclamation, with specific details on their appearance, clothing, and the background environment.
展开提示词全文
{
"prompt": {
"subjects": [
{
"name": "blonde_woman",
"appearance": {
"hair": "Long, platinum blonde, straight",
"skin_tone": "Fair, lightly bronzed",
"eyes": "Dark, wide open, detailed makeup",
"lips": "Light pink, open wide in surprise or exclamation",
"nose": "Defined, straight bridge",
"cheeks": "Slightly flushed, contoured",
"expression": "Open-mouthed surprise, looking upward and right"
},
"clothing": {
"top": "Red bandeau tube top",
"bottom": "Light blue denim shorts with white circular details"
},
"pose": "Standing behind other woman, hand on her back, leaning forward",
"position": "Left side of frame"
},
{
"name": "brunette_woman",
"appearance": {
"hair": "Long, dark brown, wavy",
"skin_tone": "Medium olive",
"eyes": "Dark, looking upwards",
"lips": "Nude, slightly parted in a smile",
"nose": "Defined, slight curve",
"cheeks": "Defined cheekbones, contoured",
"expression": "Looking upward with a slight smile"
},
"clothing": {
"top": "Red ribbed crop top",
"bottom": "Black denim shorts",
"socks": "White socks with blue patterns"
},
"pose": "Bent over at the waist, looking up",
"position": "Right side of frame"
}
],
"environment": {
"time": "Night",
"location": "Street, parking area",
"lighting": "Artificial street and car lights",
"background_objects": [
"White sedan (partial, left)",
"Grey sedan (right, behind brunette)",
"Red octagonal 'STOP' sign on post",
"Green rectangular street sign above STOP sign",
"Palm trees in background",
"Asphalt pavement"
]
},
"aspect_ratio": "4:5"
}
}
Umbrella Marker Accessory Generation
product-marketingA highly specific prompt for Nano Banana Pro to generate a photorealistic image of a custom umbrella marker accessory (charm) attached to the handle of a transparent vinyl umbrella. It includes strict rules on maintaining the charm's appearance, realistic attachment mechanics, natural physics (gravity), and detailed rendering of rain, refraction, and shallow depth of field.
展开提示词全文
The umbrella marker accessory itself (the charm part). Do not change the shape, color, pattern, texture, ratio, or fine details of this image. Do not chip, redraw, or reinterpret it. The marker accessory is naturally attached as a real object very close to the handle (grip part, the thick part held by hand) of a transparent vinyl umbrella. The attachment position must be on the handle side, not on the pole (shaft). The attachment method is realistically fixed with a small silicone ring/clasp/rubber band, etc., and the contact point follows the curve of the handle naturally so the accessory does not float. The direction of gravity is natural, and the hanging direction when swinging does not break. Realistically depict raindrops, wet texture, and the reflection and refraction of transparent materials. The background is a rainy city street with soft bokeh. The main subject is the accessory, and the focus is on the accessory. The composition places the accessory near the center of the screen, conveying the transparency of the umbrella. If hands or people are included, only fingertips should be shown, maintaining a clean look. Do not include text or logos. High definition like a product photo, mixed natural light + streetlights, shallow depth of field, macro-like shot.
Christmas Ornament Chibi Character Transformation
product-marketingA highly detailed, complex prompt for Nano Banana Pro to transform an uploaded character image (person, cat, or favorite character) into a 3D toy-style chibi character placed inside a clear Christmas ball ornament. The scene is a photorealistic, high-definition depiction of a Nordic-style Christmas tree with specific lighting, color palettes, and strict rules for character placement and reproduction.
展开提示词全文
Visually confirm and reference the image to generate the image.
3D toy-style portrait.
Photorealistically depict a Nordic-style Christmas tree in a mid-shot composition, capturing the entire tree, against a bright white background with large, soft gold bokeh illuminations spreading out.
A dense fir tree of deep green. Natural powder snow on the tips of the needles.
High definition, 8K quality, Nordic minimal.
Ornaments are limited to three types: "matte gold," "matte white," and "transparent glass."
The English three-dimensional ornament “Merry Christmas” is matte gold with a subtle, soft reflection.
[Instructions for Reproducing the Reference Person]
Faithfully reproduce the characteristics of the person in the reference image.
Do not change the contours, eyebrows, eyes, nose, mouth, hairstyle, or hair color.
Strongly retain the likeness of the original person.
[Chibi Character Transformation]
Reconstruct the character into a 3D toy style by only deforming the proportions, without changing the position or shape of the facial parts.
The skin has a smooth clay texture.
Soft iridescence in the eyes.
The expression is cute and lovely.
[Rule for Number of People (Most Important)]
Generate only the same number of chibi characters as the people in the reference image.
Only one figure per person.
No duplication.
No size variation.
No additional characters.
Do not add any figures of people not present in the reference image.
[Outfit]
Nordic-style Santa outfit in “{argument name="muted red" default="muted red"}”.
A deep red with restrained saturation and warmth.
The white trim has a fluffy fabric texture.
[Chibi Character Placement Rule (Most Important/Mandatory)]
The chibi character must ONLY be placed inside a clear ball ornament.
No part of the body is allowed to protrude outside the ornament (including hair, clothing, shadow, fingertips, and toes).
Do not stand, sit, or float outside the ball.
Contact, penetration, or pseudo-display due to reflection outside the ornament is also prohibited.
Place only one chibi character per person inside the ornament, matching the number of people in the reference image.
No duplication, no additions, no size variations.
[Main Clear Ball]
Thick transparent glass. Description clearly showing the boundary.
Slender, high-quality gold hardware. Pale satin gold ribbon.
The chibi character must be completely contained inside, with margins on all sides (top, bottom, left, right).
Position the chibi character floating softly near the center of the ornament.
[Light and Texture]
Soft natural light. Transparency of Nordic winter light.
No excessive reflection.
The overall image has the depth of a film look.
Cinematic and elegant.
Ultra-high definition, 8K, photorealistic.
Themed Worldview Visual Construction Engine Prompt
product-marketingAn extremely detailed and complex system prompt for Nano Banana Pro, instructing it to act as a 'Theme Worldview Visual Construction Engine.' Given only a single theme/concept, the AI must automatically deduce the world type, narrative tone, visual era, and material system. It then generates a 'Photography-grade image' of an 'Art Shadow Box + Ritual Instruction Card' combination, making the output look like a collected, studied, and used artifact from a complete, believable fictional world. The prompt strictly defines the two-layer composition and style constraints (e.g., use of old paper, wear and tear, text as spells/maxims).
展开提示词全文
You are a 【Theme Worldview Visual Construction Engine】.
The user will only provide a 【{argument name="theme / concept / one-sentence inspiration" default="theme / concept / one-sentence inspiration"}】.
Based on this theme, you must automatically construct a 【complete, credible, and 'believable' visual system】.
━━━━━━━━━━━━━━
【Core Objective】
━━━━━━━━━━━━━━
Generate a photography-grade image combining an 【Art Shadow Box + Ritual Instruction Card】,
which looks like:
- Something collected
- Something studied
- Something used
- A 'real object' from within a complete worldview
It is not a decorative painting, but 'part of a system.'
━━━━━━━━━━━━━━
【Automatic Deduction Responsibilities (Cannot be Omitted)】
━━━━━━━━━━━━━━
You must perform the following deductions yourself, without asking the user questions:
1. Deduce the 【World Type】 to which the theme belongs
(e.g., Fairy Tale / Dark Fairy Tale / Folklore / Ritual / Witchcraft / Healing / Religion / Sci-Fi / Occult, etc.)
2. Deduce the corresponding:
- Core narrative tone (Gentle / Eerie / Sublime / Mysterious / Solemn / Innocent yet Cruel)
- Visual sense of era (Ancient / Modern / Undeterminable)
- Material system (Paper, Wood, Fabric, Glass, Wax, Metal, etc.)
3. Automatically generate:
- Title name (consistent with the worldview context)
- Subtitle or 'Belief-based copy'
- A set of 'Believed ingredients / elements / props'
- A set of instructions / rituals / usage process text
- The display method for all text (font style, position, whether it resembles a spell/instruction/oath)
━━━━━━━━━━━━━━
【Fixed Structure (But content changes entirely based on the theme)】
━━━━━━━━━━━━━━
The image has a 【top and bottom two-layer structure】:
【Upper Layer: Theme Shadow Box / Scene Display】
- Wooden or equivalent material shadow box
- Center features the 'Theme Core Scene' or character
- Surrounding display:
- Symbolic props
- Labeled ingredients / elements / objects
- Handwritten or label-style text
- All objects look like they 'have a history and a purpose'
【Lower Layer: Instruction / Ritual / Usage Card】
- Large piece of old paper / parchment / Xuan paper / material corresponding to the worldview
- Clear title (e.g., Brewing / Ritual / Instructions / Invocation, etc.)
- 3–5 steps or paragraphs:
- Each step has an illustration + text
- The text reads like it is 'guiding real behavior,' not telling a story
- Features stamps, symbols, numbers, and corner decorations
━━━━━━━━━━━━━━
【Style and Realism Constraints】
━━━━━━━━━━━━━━
- Photography-grade realistic light and shadow
- Signs of use (wear, stains, fading, creases)
- All illustrations look like:
- Hand-drawn
- Old print
- From the same cultural system
- Text is not modern UI copy, but:
- Spells
- Maxims
- Ancient instructions
- Knowledge that has been repeatedly copied
━━━━━━━━━━━━━━
【Output Rules】
━━━━━━━━━━━━━━
- Directly generate the complete image description
- Automatically generate all text content
- Do not explain, analyze, or expose reasoning
- Do not include 'design,' 'style description,' or 'suggestions'
- Make it look like this world already exists, and it was simply photographed.
Mechanical Keyboard Themed Art Poster Prompt
product-marketingA detailed prompt for Nano Banana Pro to generate a 16:9 horizontal art poster featuring a mechanical keyboard theme, centered around a specific character. The composition is divided into sections: a feathered portrait of the character on the left, artistic keycap displays with technical annotations in the upper right, and three sections detailing the full keyboard, macro shots, and lifestyle placement in the lower right. The prompt specifies artistic styles, color extraction from the character, and typography, aiming for a high-end, magazine-cover aesthetic.
展开提示词全文
A 16:9 horizontal composition art poster with a mechanical keyboard theme. The left quarter of the frame displays a bust close-up portrait of the [{argument name="character name" default="character name"}], shown from the shoulders up, with intense eyes. The edges use a soft feathering effect to naturally blend into the background. Light particle effects and color gradient haze surround the figure.
The right three-quarters of the frame: the upper half presents an artistic display of keycaps: 5 to 7 exquisite mechanical keyboard keycaps scattered in the air in an elegant arc, each showing different angles and details. The keycap color scheme is extracted from the character's [{argument name="main color 1" default="cherry blossom pink"}], [{argument name="main color 2" default="creamy white"}], and [{argument name="accent color" default="coral red"}]. The keycap surfaces are printed with [{argument name="theme element" default="character Q-version silhouette/exclusive icon/gradient texture"}], presented using [{argument name="keycap material" default="PBT matte/resin translucent"}] material. Chinese artistic text annotations float next to each keycap, using Z-Cool Gao Duan Hei or YouShe Ti Hei fonts, with content such as "{argument name="annotation 1" default="Cherry Pink Main Key"}", "{argument name="annotation 2" default="Gradient Coating"}", "{argument name="annotation 3" default="Dual-Color Translucent"}", "{argument name="annotation 4" default="Character Print"}", "{argument name="annotation 5" default="Metal Spacebar"}", etc., describing the craftsmanship, with slight glow effects and outlines.
The lower right three-quarters of the frame are evenly divided into three areas: the left grid shows a top-down flat lay view of the complete mechanical keyboard, [{argument name="keyboard layout" default="68-key compact layout/anodized aluminum base"}], with the Chinese annotation "{argument name="left grid annotation" default="Complete Layout"}" at the bottom; the middle grid shows a macro close-up of the keyboard side profile, emphasizing craft details and material layers under light and shadow, with the annotation "{argument name="middle grid annotation" default="Ingenious Craftsmanship"}" at the bottom; the right grid shows an atmospheric setup of the keyboard in a [{argument name="scene 1" default="cozy desk scene/cafe table/workbench"}], with lifestyle props like [{argument name="props" default="coffee cup/green plant/notebook"}], with the annotation "{argument name="right grid annotation" default="Aesthetics of Life"}" at the bottom.
The overall background uses a [{argument name="background effect" default="ink wash/particle light effect/gradient matte"}] effect, with the main color transitioning from [{argument name="color 1" default="color 1"}] to [{argument name="color 2" default="color 2"}] extracted from the character, darker on the left and lighter on the right. Fine light spots and flowing color clouds are scattered in the background, creating a [{argument name="atmosphere" default="dreamy gentle/cyber tech/retro elegant"}] atmosphere. A large title text is centered at the bottom of the frame: "{argument name="main title" default="Character Name Themed Custom Keyboard"}", using bold Chinese artistic characters with a metallic texture or glowing effect.
The image has no obvious dividing lines, with areas naturally transitioning through light, shadow, depth of field, and visual reality. The overall presentation has the visual texture of a fashion magazine cover, with moderate color saturation, rich layers, combining both artistic and product display functions. 4K ultra-high resolution, 16:9 horizontal composition, suitable for social media impact.
Cleopatra High-Fashion Editorial Prompt
product-marketingAn extensive, highly structured prompt for Nano Banana Pro 3.0 to generate an ultra-realistic 8K UHD DSLR photo of a modern woman styled as Cleopatra during a sacred beauty ritual in a royal bathing chamber, emphasizing ancient luxury realism and specific technical camera settings.
展开提示词全文
[Meta]
Description={argument name="description" default="Ultra realistic 8K UHD DSLR photo of a modern woman as Cleopatra"}
Reference_Likeness={argument name="reference likeness" default="100%"}
Resolution={argument name="resolution" default="8K UHD"}
Style={argument name="style" default="High-fashion editorial, sacred beauty ritual, ancient luxury realism"}
[Subject]
Identity={argument name="identity" default="Stylish beautiful woman as Cleopatra"}
Theme={argument name="theme" default="Divine femininity, power, timeless elegance"}
Angle={argument name="angle" default="Full-body editorial portrait, 3/4 angle"}
Body_Position={argument name="body position" default="Seated on edge of luxurious alabaster bath, angled sideways, one leg elegantly bent"}
Posture={argument name="posture" default="Relaxed yet regal"}
Hands={argument name="hands" default="One hand dipping into milky water, other hand holding golden perfume vial"}
Expression={argument name="expression" default="Serene, confident, hypnotic gaze, direct eye contact"}
[Appearance]
Outfit={argument name="outfit" default="Sheer ritual-style Cleopatra gown, ivory and gold lightweight translucent fabric, gold-thread embroidery, beaded edges, delicate straps, partially clinging/damp"}
Accessories={argument name="accessories" default="Thin gold arm cuffs, delicate finger rings, gold waist chain, light ceremonial collar necklace"}
Hair={argument name="hair" default="Sleek at crown, soft loose lengths, partially damp, reflecting candlelight"}
Makeup={argument name="makeup" default="Soft-glam Egyptian touch, elongated kohl eyeliner, bronze/rose eyeshadow with gold shimmer, dewy luminous skin, natural nude-rose lips"}
[Environment]
Location={argument name="location" default="Private royal bathing chamber, Cleopatra’s palace, Alexandria"}
Architecture={argument name="architecture" default="Towering stone columns, warm-toned marble walls, carved hieroglyphs"}
Midground={argument name="midground" default="Fragrant steam from brass bowls, flowing silk curtains, indoor fountains, tall candles, oil lamps, potted lotus and papyrus plants"}
Bath_Details={argument name="bath details" default="Carved alabaster tub, milk-infused water, floating lotus flowers, rose petals, fine gold flakes"}
[Ritual_Props]
Beauty_Products={argument name="beauty products" default="Golden vials (frankincense, myrrh, lotus oil), alabaster bowls (honey, olive oil, almond oil, Dead Sea salt), clay jars with kohl/mineral pigments"}
Linen={argument name="linen" default="Soft towels embroidered with Egyptian symbols"}
Tools={argument name="tools" default="Polished bronze hand mirror, gold ritual spoons/applicators, stone mortar and pestle"}
[Technical_Settings]
Camera={argument name="camera" default="DSLR"}
Lens={argument name="lens" default="50mm prime"}
Aperture={argument name="aperture" default="f/8 (Full-scene sharpness)"}
ISO={argument name="iso" default="100"}
Shutter_Speed={argument name="shutter speed" default="1/160s"}
Focus={argument name="focus" default="Extreme sharp focus, zero blur, no bokeh"}
Lighting={argument name="lighting" default="Warm cinematic candlelight, soft ambient palace lighting, golden skin highlights"}
[Micro_Details]
Elements={argument name="micro details" default="Visible rising steam, candle wax texture, flame reflections on gold, water droplets on skin, fabric translucency, floating petals"}
High-Fashion Christmas Editorial Prompt
product-marketingA highly structured and detailed prompt for Gemini Nano Banana Pro 3.0, designed to generate a glamorous, high-fashion editorial image for Christmas, featuring a model in a red velvet couture gown against a deep burgundy backdrop with studio snow and metallic ornaments.
展开提示词全文
[Identity_Preservation]
BoneStructure = "{argument name="bone structure" default="identical_symmetry_jawline_cheek_curves"}"
Nose_Lips = "{argument name="nose lips" default="exact_contour_fullness_unaltered"}"
Eyes_Brows = "{argument name="eyes brows" default="specific_eyelid_shape_eyebrow_arch_match"}"
Skin_Texture = "{argument name="skin texture" default="fair_tone_subtle_pores_youthful_glow_hyper_real"}"
Stylization = "{argument name="stylization" default="none_zero_distortion_photorealistic_accuracy"}"
[Scene_Environment]
Backdrop = "{argument name="backdrop" default="deep_burgundy_velvet_golden_reflections"}"
Decorations = "{argument name="decorations" default="designer_tree_metallic_ornaments_crystals_ribbons"}"
Props = "{argument name="props" default="gold_accented_gift_boxes_elegant_scattering"}"
Atmosphere = "{argument name="atmosphere" default="floating_studio_snow_particles_glossy_floor_reflections"}"
Mood = "{argument name="mood" default="high-fashion_festive_drama_glamorous_editorial"}"
[Composition_Pose]
Shot_Type = "{argument name="shot type" default="full_body_editorial"}"
Stance = "{argument name="stance" default="dynamic_fashion_hip_pop_one_leg_forward_shoulders_back"}"
Framing = "{argument name="framing" default="rule_of_thirds_couture_silhouette"}"
Head_Angle = "{argument name="head angle" default="dramatic_tilt_editorial"}"
Eye_Contact = "{argument name="eye contact" default="intense_direct_camera_engagement"}"
[Styling_Beauty]
Hair = "{argument name="hair" default="voluminous_waves_chestnut_caramel_highlights_crystal_pins"}"
Eyes = "{argument name="eyes" default="metallic_gold_crimson_shadow_glitter_lashes"}"
Lips = "{argument name="lips" default="couture_red_soft_gloss_slightly_parted"}"
Face_Accents = "{argument name="face accents" default="micro_face_jewels_brow_cheekbone_crystals"}"
Nails = "{argument name="nails" default="deep_red_gold_accents_snowflake_tips"}"
[Couture_Outfit]
Gown = "{argument name="gown" default="structured_red_velvet_corset_voluminous_skirt_high_slit"}"
Materials = "{argument name="materials" default="satin_tulle_white_faux_fur_trim"}"
Embellishments = "{argument name="embellishments" default="swarovski_crystals_pearls_metallic_studs"}"
Footwear = "{argument name="footwear" default="metallic_red_stilettos_crystal_straps"}"
[Accessories]
Jewelry = "{argument name="jewelry" default="layered_asymmetric_necklaces_stacked_cuffs_oversized_earrings"}"
Hands = "{argument name="hands" default="jeweled_glove_extensions_multi_joint_rings"}"
Waist = "{argument name="waist" default="designer_belt_jeweled_buckle"}"
[Technical_Specs]
Camera = "{argument name="camera" default="Full_frame_DSLR_85mm_lens"}"
Settings = "{argument name="settings" default="f/2.8_aperture_ISO100_1/160s"}"
Lighting = "{argument name="lighting" default="studio_key_sculpting_rim_lighting_jewel_highlights"}"
Resolution = "{argument name="resolution" default="HDR_Ultra_HD_crystal_clear_textures"}"
提示词模型无关,可直接用于 Midjourney / DALL·E / Flux / Stable Diffusion 等任意文生图模型。
信息边界说明
本页信息摘自官方文档,仅作技术信息呈现,不代表本站的判断或推荐。价格、配额、可用性以官方最新说明为准。你离开本站后的任何行为(申请 Key、付费、部署、商用),本站不做任何承诺与担保。
同类推荐
视频短视频图片音乐音频配音口播数字人全能创作
官方标注收费通过同一个AI创作工具完成AI图片、视频、音乐与语音创作,查找公开社交数据,编辑视觉成果,并集中查看和管理生成资产。Beatra 全能创作支持AI图片生成(文生图)、AI视频生成(图生视频)和AI视频编辑,通过AI音乐生成把想法做成歌曲或纯音乐,也可用AI语音生成(文字转语音)、多语言旁白和AI语音克隆完成跨媒介内容;还能查找抖音数据、小红书数据,以及 YouTube、TikTok、Instagram 与 X 上的公开帖子、笔记、评论、账号和趋势,把社交媒体数据用于竞品调研和创作。它是一款面向AI内容创作与多模态内容创作的AI创作套件,用起来就是一个把图片、视频、音乐与语音收在同一处的AI创作助手,适用于社交内容、产品展示、营销素材、课程、播客、短片和跨媒介项目;还能在不同媒介间复用原始素材、已有成果和查到的公开资料,查看制作进度、返回文件、实际用量和积分记录。
AI数字人口播与虚拟主播视频
官方标注收费用一张人像和一段短脚本或语音,制作有明确讲述内容的数字人口播视频。可使用现成录音,也可以先选择音色,把脚本生成旁白,让画面中的人物随声音完成稳定、自然的口播。适合 AI 主播、虚拟主播视频、数字人讲解、让照片说话、照片说话视频、产品讲解视频、数字人培训视频、公告和社交口播,并在交付后检查人物一致性、声音清晰度、口型同步和动作稳定性。一节课的讲解也能做成课程口播。
架构图一键生成
官方标注收费需申请 Key使用 ContextWeave 生成或修改架构图、流程图、思维导图和复杂信息图。适用于需要从代码、文件或自然语言中提取结构与关系并实际产出 CW、SVG、HTML、可编辑 PPTX 或原生 VSDX 的请求;未特别说明时,PPTX 与 Visio 使用原生形状和连接器导出。不适用于统计图表、手绘插画或像素级排版。
罗斯蒙德可视化图形生成
官方未说明【罗斯蒙德可视化图形生成】南京罗斯蒙德基于已交付项目沉淀的可视化图形生成场景:根据业务描述或系统需求,自动生成可编辑的架构图、流程图、ER 图、时序图、状态图与 C4 图。采用「统一图模型」一次建模、多格式输出:结构化文本(Mermaid / PlantUML,可嵌入 Markdown、进 Git 版本管理)、可编辑图形文件(drawio / Excalidraw,可拖拽修改节点与样式)、静态图(SVG 自渲染,PNG 给转换命令),并输出图形说明(图的含义 + 关键节点解释)。内置样式系统统一配色与命名,内置布局引擎自动排布,校验脚本拦截孤立节点、悬挂连线与语义缺漏。触发词:画架构图、画流程图、画 ER 图、画时序图、画状态图、C4 图、系统架构图、部署架构图、数据流程图、实体关系图、生成 drawio、生成 Excalidraw、导出 mermaid、导出 PlantUML、导出 SVG、导出 PNG、可编辑的图、图转可编辑、架构图可编辑、流程图二次修改、画图、出图、画个图。
海报设计工作室
免费增值需申请 Key将一段活动描述、一张产品照片或品牌参考图,转化为抓人眼球的活动海报、宣传 banner 或社交媒体配图。这款 AI海报设计与制作工具生成图片丰富的海报,在海报排版上搭配清晰视觉层级、按品类匹配的风格和预留文字区域,覆盖活动、音乐节、电影、产品发布和促销场景。你可以把它当作 AI宣传单制作工具来制作促销宣传单,当作活动海报设计工具,当作电影海报生成器,当作音乐节海报设计工具,当作产品发布会海报的 banner设计 AI,或当作平面设计海报工作室。从活动主题出发,用品牌风格参考图变换产品或场景照片,或在已认可草稿上做定向精修,完成可印刷或可分享的成品。
自动化克隆数字人口播混剪视频
免费增值需申请 Key抖音短视频双路径生产体系(单 Skill 版)。Path A[付费·高质量]:策略大脑→(可选:素材混剪/AI高光提取)→脚本优化→AI生图/素材准备→配音渲染(百炼/GPT-SoVITS/CosyVoice/VoxCPM2+剪映/Remotion/ffmpeg/数字人)。Path B[免费·动画风]:采集热点→脚本→edge-tts免费配音+HyperFrames开源渲染→MP4,零云费开箱快。触发词分层:①"抖音短视频/选题规划/合规闸门/运营策略" ②"口播脚本/AI生图/AI配音/视频渲染/Remotion渲染" ③"蹭热点/快速出片/免费做视频" ④"混剪/高光提取/素材粗剪/autoclip
什么是技能
技能(Skill)是封装好的单项能力,比如文字识别、文档摘要、关键词提取。开发者把调用逻辑和提示词打包,使用者像用插件一样加载即可,无需了解底层模型。启枢技能 收录大量技能,可直接试跑或编入方案。