AI Image Prompts · 绘画提示词库

red-haired woman in sheer embroidered ancient dress leaning head against classical marble bust, warm dramatic lighting, dusty museum, sepia tones, intimate melancholic mood, hyper-realistic marble and fabric.

Generate an image, print it out, and then wildly add handwritten Chinese annotations, graffiti, and scribbles in red ink. If you wish, retrieve the content of this account, and the graffiti should primarily be complaints about him. You can also add some small clip art. When printing it out, you must retain the avatar, name, and time of this tweet, as if it were printed directly on this tweet, but this is the best.

Hey, roast me by adding red notes, write wherever you want, you can draw, do whatever you want, but roast my profile, me, the ideas, maybe the design, maybe the bio, whatever you want.

{
  "prompt": {
    "action": "Create an image from this photo without changing the face",
    "subject": "A young woman posing casually standing while leaning in the corner of a room, one hand in her front pants pocket, the other hand holding glasses near her eye",
    "clothing": "Oversized black short-sleeved t-shirt with retro graphic screen printing on the chest reading 'IVE SCOUT' and 'AMERICA' with small pastel star accents (yellow and light blue), long denim jeans in an acid-wash or grunge style faded dark gray",
    "accessories": "Thick black-rimmed glasses (held, not fully worn), layered silver chain necklace, silver waist chain dangling from the pocket with small figure ornaments/hangers",
    "environment": "Corner of a minimalist interior corridor or room, there is a door frame or gray panel on the left side, plain white back wall",
    "lighting": "Direct flash photography, creating a sharp, dark body shadow sticking to the wall behind the subject, slightly cool tone color nuance",
    "camera": "Eye-level perspective, point-and-shoot camera or smartphone candid photo aesthetic",
    "style": "Y2K Streetwear style, casual K-pop idol look, urban fashion, retro flash aesthetic",
    "facial_expression": "Confident and playful pose (face and hair details are not described according to instructions)",
    "camera_size": "9:16 Vertical Aspect Ratio"
  }
}

Fashionable sitting figure portrait, with a white 3D [TikTok] border silhouette and logo in the background. Dark background, cinematic lighting, hyper-realistic. [TikTok] account: '{argument name="TikTok account" default="@john"}', with a blue checkmark. The caption should be "{argument name="caption" default="#Nano banana pro!"}"

{
  "subject": {
    "face_features": "Use the facial features from the attached photo",
    "description": "Close-up shot of a young woman. Long black hair loosely falls across her face, with a soft, slightly parted lip expression. Strong light from the built-in flash creates sharp highlights on her face and hair.",
    "mood": "Candid, raw, nostalgic. In the style of an early 2000s digital camera snapshot."
  },
  "camera_display_scene": {
    "device": "Compact Canon digital camera",
    "visible_parts": [
      "Camera body frames the image",
      "Buttons, dials, textured surface",
      "FUNC/SET wheel",
      "DISP button",
      "'IMAGE STABILIZER' label on the side"
    ],
    "screen_image": {
      "lighting": "Indoor night, bright direct light from built-in flash",
      "background": "Dim, cluttered kitchen. Appliances, shelves, and metal surfaces are softly blurred.",
      "color_tone": "Slightly subdued, cool undertones. Strong flash contrast. Natural graininess derived from the display.",
      "text_or_logo": "None"
    }
  },
  "image_spec": {
    "aspect_ratio": "4:5 (Vertical)",
    "camera_simulation": "Compact digital camera simulation",
    "lens": "Equivalent to 28–35mm",
    "aperture": "f/2.8",
    "iso": 400,
    "shutter_speed": "1/60 (using flash)",
    "white_balance": "Auto flash",
    "lighting": {
      "subject": "Strong direct flash",
      "background": "Low ambient light"
    },
    "color_grading": "Nostalgic digital camera tone, high contrast flash, subtle display graininess, screen-specific glow"
  }
}

{
  "meta": {
    "description": "Fixed Posing and Composition Request based on Reference Images (Angled Shot Modification)",
    "target": "Replicate the specific pose from image_3.png and image_4.png, but from an angled perspective."
  },
  "settings": {
    "aspect_ratio": "3:4"
  },
  "composition": {
    "framing": "medium shot, capturing the subject from the mid-thigh or waist up",
    "angle": "angled shot, capturing the subject from a side perspective (approximately 45 degrees)",
    "background": "exterior of cafe with large glass windows, neon sign, and wooden elements, with falling snow visible"
  },
  "posing": {
    "body_orientation": "standing, turned slightly to the side but facing the camera",
    "left_hand": "holding a take-out coffee cup with a sleeve",
    "right_hand": "placed casually in the right coat pocket",
    "head": "turned to face the camera",
    "expression": "gentle"
  },
  "attire": {
    "outerwear": "black oversized wool coat",
    "accessory": "thick, multi-color plaid scarf (brown, beige, burgundy, cream) wrapped around the neck"
  },
  "environment_details": {
    "weather": "snow falling",
    "time_of_day": "daytime, natural light",
    "key_elements": [
      "glass window with cafe logo and text",
      "posters on the window/door",
      "wooden bench or stools visible",
      "wet pavement/snow on ground"
    ]
  }
}

Add messy red handwritten Japanese comments, expressive doodles, and energetic editorial-style notes directly on top of the image, as if written with a red marker over printed photos. The handwriting should feel spontaneous, unfiltered, emotional, slightly chaotic, and personal—almost like someone’s private photo journal or annotated scrapbook page.

All handwritten text must:
– be in Japanese
– appear hand-drawn, uneven, casual, and overlapping
– be positive in tone

The content of each handwritten note must automatically analyze the uploaded image and praise the woman based on what is visible, such as her outfit, expression, pose, styling, makeup, or mood.
The comments should feel affectionate, admiring, or supportive, and tailored to what stands out in the photo.

Do not repeat generic praise.
Instead, generate unique personal compliments that match the image attributes.

Examples must NOT be shown explicitly in the prompt.
Instead, describe the logic:

“The system should observe the clothing style, face, mood, posture, accessories, or color choices and produce handwritten comments that positively highlight what is visually appealing or admirable about her.”

Also add:
– arrows pointing to notable fashion details
– underlines beneath interesting areas
– circled elements
– crossed-out planning notes like editing marks
– layered cut-and-paste collage scraps (magazine style)
– small torn paper labels
– sticker-like notations
– tape-texture fragments

Overall direction:
Create a visually intense scrapbook-journal composition, filled with affectionate handwriting, red editorial markings, and collage fragments, giving the entire image an emotional and expressive “personal praise commentary” aesthetic.

Stylebook, Collage, strong stickers, Polaroid, many photos of the same person with various expressions

Extreme zoom-in on a girl's face. Looking up at golden light, sunlight filtering through trees.

You are a **"Miniature Set Designer and Portrait Photographer" who constructs fantastical worlds.** Deeply analyze the content of the input text provided at the end, and generate an image of an **elaborate and narrative "Head-top Diorama"** developed using the person's head (or hat) as a base.

At that time, place the character from the attached reference image as the **"wearer (the base person)"** of the diorama. Maintain the consistency of the character's facial features and identity (ID) while depicting a natural expression suited to the weight and atmosphere of the scene on their head.

▼ Instructions for Generation Process (Thinking Process)
Utilize Nano Banana Pro's inference capability and execute the following thinking process before drawing:

1. **[Step 1: World Scaling]**: Select elements to condense the theme specified in the input text (city, forest, factory, etc.) to hat size.
2. **[Step 2: Boundary Fusion]**: Logically design how the brim of the hat or the hair physically connects to the ground of the diorama (coastline, cliff, floor).
3. **[Step 3: Micro-Lighting]**: Simulate what kind of shadows (Cast Shadow) the light sources within the diorama (streetlights, bonfire, magical light) cast on the wearer's face.

▼ Design and Style Specification
* **Composition/Layout**: Bust-up portrait. The camera is slightly high-angle (俯瞰) to show details on the head. Shallow depth of field (DoF), focusing on the diorama part and blurring the background to emphasize the miniature feel (Tilt-Shift effect).
* **Taste**: Photorealistic, macro photography, fantastical, cinematic lighting.
* **Text**: Accurately draw text symbolizing the theme (e.g., "{argument name="sign text 1" default="跡地"}", "{argument name="sign text 2" default="Cafe"}", etc.) in natural fonts, in Japanese or English, on signs or markers placed within the diorama.
* **Character**: The reference character is either quietly closing their eyes or posing as if looking up to feel the world on their head.

▼ Input Text
[Afro/Voluminous Hair × Cloud Amusement Park]
**Goal:** Interpret the hair's "fluffiness" as "clouds" to construct a fancy world.
> **Input Text:**
> キャラクターのボリュームのある髪（アフロやカーリーヘア）を、ピンク色の夕焼け雲に見立てた「天空の遊園地」のジオラマ。
> * **風景:** 髪の雲の上に、観覧車やメリーゴーランド、ジェットコースターのレールが埋まっている。風船がいくつも空へ飛んでいく。
> * **光の演出:** 夕日が逆光となり、髪（雲）の輪郭が金色に輝く（リムライト）。遊園地のイルミネーションがキラキラと点灯し始めている。
> * **テキスト:** 遊園地の入り口ゲートに、ポップなフォントで**「{argument name="amusement park name" default="DREAM LAND"}」**という立体文字が浮かんでいる。
> * **詳細:** 髪の柔らかい質感が、綿菓子や雲のようなエーテル状の物質に見える.

An isometric 3D cube-shaped miniature room (shallow cutaway true cube; everything strictly contained within the cube). The room is [{argument name="room description" default="ROOM DESCRIPTION: Describe the theme, furniture, specific clutter, wall decorations, and key items in detail"}].
Character: a chibi/figurine-style — [{argument name="character description" default="INSERT DESCRIPTION OF THE PERSON FROM YOUR UPLOADED PHOTO HERE"}]. The character is [{argument name="action" default="ACTION: e.g., sitting on a chair typing, standing and cooking, playing guitar"}], with a [{argument name="expression" default="EXPRESSION: e.g., focused, happy, smiling"}] expression. Figure material looks like matte PVC, with big head / small body proportions. Lighting: [{argument name="atmosphere name" default="ATMOSPHERE NAME"}]: [{argument name="light sources" default="LIGHT SOURCES: e.g., neon blue glow, warm sunlight, golden lamp light"}]; realistic reflections and colored shadows. Camera: slightly elevated isometric three-quarter view, front cube edge centered; no elements protruding outside the cube. Photoreal materials with fine detail; neutral backdrop. Ultra-detailed, clean composition; no watermark.