图片提示词

"Ultra-detailed, cinematic red carpet portrait photograph taken at the 31st Annual Critics Choice Awards in a glamorous indoor venue, dramatic starry twinkling bokeh lights and soft golden ambient glow in the deep dark background, two stunning young blonde actresses standing close together arm-in-arm, smiling gently and confidently directly at the camera with poised elegance, left woman is {argument name="actress 1" default="Elle Fanning"}: 25 years old, porcelain fair skin, delicate features, large expressive blue-green eyes, subtle natural glowing makeup with soft pink lips and barely-there blush, long straight silky platinum blonde hair cascading smoothly past shoulders, wearing an ultra-luxurious sleeveless metallic gold lamé gown with extremely deep plunging V-neckline, dramatic cowl-draped bodice that clings and flows sensually over the body, shimmering liquid-metal fabric catching every light with rich golden reflections and subtle texture, floor-length fitted mermaid silhouette with gentle train, minimalist gold ring on left hand, right woman is {argument name="actress 2" default="Margaret Qualley"}: 30 years old, luminous fair skin, striking cheekbones, warm hazel eyes, soft romantic makeup with defined brows, rosy cheeks and glossy nude lips, long voluminous wavy golden-blonde hair styled in an elegant half-up half-down look with loose face-framing tendrils and a subtle braid detail, wearing a high-fashion white satin ball gown with structured fitted bodice, dramatic black velvet trimmed scoop neckline and wide velvet band accentuating the waist, exaggerated peplum hip detail creating a dramatic hourglass shape, voluminous flowing floor-length A-line skirt with soft movement, large pearl drop earrings swaying gently, both women exude poised Hollywood glamour and sisterly warmth, perfect symmetrical composition centered on their faces and upper bodies, professional event photography style like Getty Images or Vogue red carpet shot, razor-sharp focus on eyes and fabric textures, cinematic volumetric lighting with soft rim light highlighting hair and shoulders, subtle catchlights in eyes, intricate realistic skin pores and fabric sheen, photorealistic, hyper-detailed, 8k resolution, masterpiece quality --ar 2:3 --stylize 300 --v 6 --q 2 --style raw --chaos 15 --stop 100"

An adorable snail with large eyes, featured in a low-angle macro view. The background is filled with huge flowers, creating a vibrant and colorful setting. The snail has a sweet expression on its face, surrounded by bright, happy colors.

{
  "image_prompt_data": {
    "subject": {
      "identity": "young women ",
      "appearance": {
        "hair": "Shoulder-length textured bob, honey blonde with golden highlights, loose beachy waves, center part",
        "eyes": "Large, expressive blue-green eyes, sharp winged eyeliner, defined lashes",
        "skin": "Flawless fair complexion, luminous dewy finish, soft rosy blush on cheekbones",
        "lips": "Glossy nude-pink lip color, naturally full shape"
      },
      "expression": "Confident, poised, direct eye contact with a soft, neutral gaze"
    },
    "attire": {
      "garment": "{argument name="gown color" default="Ice-blue/silver"} satin gown, custom couture style",
      "details": [
        "Plunging neckline",
        "Structured bustier bodice",
        "Heavy crystal and sequin embellishment on the bust cups",
        "Off-the-shoulder crystal-encrusted straps",
        "Thin spaghetti straps",
        "Smooth, reflective satin fabric texture"
      ]
    },
    "accessories": {
      "jewelry": [
        "Delicate diamond tennis necklace",
        "Small brilliant-cut diamond stud earrings"
      ]
    },
    "environment": {
      "setting": "Red carpet media wall / Step-and-repeat",
      "background": "Dark/Black backdrop with blurred white logos (visible partial text: 'GLAAD', 'Hyundai')",
      "atmosphere": "Glamorous, high-profile celebrity event"
    },
    "lighting": {
      "type": "Professional event flash photography",
      "characteristics": [
        "Front-facing soft flash",
        "Even illumination on face",
        "Distinct catchlights in eyes",
        "Subtle specular highlights on the satin dress and crystals",
        "Minimal shadows on the subject"
      ]
    },
    "technical_details": {
      "camera_type": "High-end Full Frame DSLR (e.g., Canon EOS R5 or Sony A1)",
      "lens": "85mm f/1.4 prime portrait lens",
      "settings": {
        "aperture": "f/2.0 to f/2.8 (creating shallow depth of field)",
        "shutter_speed": "1/200s",
        "iso": "400"
      },
      "style": "Ultra-photorealistic, 8k resolution, razor-sharp facial focus, smooth bokeh background, highly detailed skin texture and fabric grain"
    }
  }
}

When I instructed it to create an X thumbnail in 5:2, it produced the perfect size.

{
  "Color": {
    "Color Behavior": "Dominant main color, supplemented by extremely soft second color accents",
    "Saturation": "Medium-high saturation, softened treatment, absolutely not harsh or muddy"
  },
  "Environment": {
    "World Type": "Abstract canvas surface",
    "Material": [
      "Ink pigment",
      "Subtle palette knife texture",
      "Minimalist brushstrokes",
      "Thin layers of pigment stacking texture"
    ],
    "Rendering Rules": "The environment symbolically represents a sports field or arena with restrained colors, clean texture, and controlled pigment thickness—absolutely no pursuit of literal realism",
    "Background Style": "Calm, uniform color blocks with subtle pigment texture"
  },
  "Subject": {
    "Scale": "Miniature model",
    "Appearance": "{argument name="appearance" default="Highly realistic human figure"}",
    "Activity": "{argument name="activity" default="Dynamic moment during movement"}",
    "Clothing": "Precise sports-specific clothing and equipment",
    "Pose Style": "Natural, in-motion posture",
    "Shadows": "Soft, subtle shadows cast directly beneath the subject, reinforcing the overhead view"
  },
  "Composition": {
    "Camera Angle": "Strict overhead view",
    "Camera Orientation": "Completely perpendicular to the surface (90-degree top-down perspective)",
    "Perspective Rules": [
      "No tilt",
      "No diagonal angles",
      "No perspective distortion",
      "No depth of field perspective"
    ],
    "Layout": "Graphic, editorial feel, simple geometry",
    "Negative Space": "Deliberate and ample",
    "Depth of Field": "Flat, poster-like depth of field"
  },
  "Lighting": {
    "Type": "Soft studio lighting",
    "Light Direction": "Uniform top lighting",
    "Contrast": "Low to medium contrast",
    "Purpose": "Maintain surface calmness and eliminate directional drama"
  },
  "Style": {
    "Style Genre": [
      "Conceptual fine art",
      "Editorial photography",
      "Surreal miniature"
    ]
  }
}

A VFX comparison image based on a scene described by the theme or specific content (Example: {argument name="theme" default="A woman flying over the sea"}), featuring the person in the attached image.

VFX comparison composition with a split screen accurately aligned by a central vertical line.
**IMPORTANT: The number of characters, gender, and appearance must exactly match the provided input image. Do not add or remove characters.**

**Left Half (Finished Shot):**
A photorealistic movie scene perfectly depicting the theme "**[Enter Theme]**".
* **Character:** The person from the input image is performing actions (pose and expression) suitable for the theme "**[Enter Theme]**".
* **Background:** A detailed and realistic environment (outdoor or indoor) suitable for the theme, with cinematic lighting and atmosphere.

**Right Half (Green Screen Shooting):**
Standing in a studio with a giant blue/green screen (chroma key) in the **exact same composition and pose** as the person in the left half.
Visible white cyclorama wall, complex lighting rigs overhead, cables, black marks (tape) indicating standing positions, dolly tracks for camera rails, harsh studio lighting that is not blocked, faint shadows of the film crew visible at the edges. The background is a completely flat, solid green screen for compositing.

Look and feel of VFX before-and-after from early 2000s Japanese cinema, texture of extremely degraded, low-quality analog video, noise, and color fading.

Please draw "{argument name="melody" default="Popopo-popopopo♪"}"

The image uses a left-right split composition, with a clear boundary between the left and right halves, aligned overall, presenting a comparison effect of "concept map versus actual implementation".
The left half is a highly detailed modern minimalist architectural floor plan illustration, consistent with the reference image style. It shows a top-down orthogonal projection of the residential layout, clearly labeling spaces and circulation: living room, dining area, open kitchen, bedroom, entrance hall, corridor and flow lines, balcony or loggia space, bay window, and window opening locations. The color scheme uses neutral beige and warm gray, with clean lines, slight soft shadows, and delicate material textures, showcasing the quality of the interior design plan, presented in a blueprint-style flat visual, with visible and accurately scaled furniture placement.
The right half is an ultra-realistic interior photo effect of the same living room as the left floor plan, with spatial proportions and layout strictly corresponding to the floor plan. The living room includes a curved sofa set, a central coffee table, soft carpet, warm wooden floor, neutral walls, and large windows introducing natural light. The overall style is modern and warm home atmosphere, with earthy tones and soft lighting, realistic and tactile materials, details that feel lived-in yet remain neat and restrained. The right side presents a real interior photography texture, with clear textures and high-resolution details.
The style and atmosphere combine architectural visualization with real interior photography, modern, warm, elegant, conveying the professional design studio presentation feel, emphasizing the contrast between the plan and the actual scene.
Lighting and color requirements: The left side uses uniform flat light and neutral colors, while the right side uses natural daylight with soft shadows and warm highlights; the colors on both sides maintain a unified harmonious relationship.
Lens and technical requirements: The left side is a top-down orthogonal view, and the right side is a flat view using an interior wide-angle lens, with sharp image clarity, rich real materials, and details.
Negative prompt: cartoon style, rough details, messy interior, mismatch between floor plan and actual scene, distorted proportions, overly harsh light, exaggerated saturated colors, text overlay, watermark, logo, noise, blur.

{
  "prompt": "Wong Kar-wai moody color palette dominated by heavy cyan-green tones (95–98% green/teal diffusion), Rembrandt chiaroscuro lighting, intense film grain, high ISO noise, low-res DV camcorder aesthetic, strong motion blur, double-exposure tunnel trails. Voyeuristic tight shot with heavy foreground occlusion, mirror reflections, frame-in-frame feel. Ultra-wide 18–24mm lens, extreme close-up (faces only 2–4 cm from lens), wildly exaggerated perspective — heads dramatically larger than distant elements. Long dark road tunnel background filled with massive blurred linear light streaks (mostly vivid green + trace pale yellow), heavy long-exposure smear.\n\nCRITICAL FACE RESTORATION - MALE (Reference Image 1):\n28-year-old male with EXACT facial features from reference image 1:\n- Face MUST be 100% identical to reference image 1\n- Face shape: {argument name="Male Face Shape" default="[exact shape from ref img 1]"}\n- Eyes: {argument name="Male Eyes" default="[exact eye shape, size, eyelid type, spacing, color from ref img 1]"}\n- Eyebrows: [exact shape, thickness, arch from ref img 1]\n- Nose: [exact bridge height, tip shape, nostril width from ref img 1]\n- Mouth: [exact lip shape, thickness, width from ref img 1]\n- Jawline: [exact jaw shape, chin shape from ref img 1]\n- Skin tone: [exact color/undertone from ref img 1]\n- Hair: [exact hairstyle, color, texture, length from ref img 1]\n- Facial hair: [exact stubble/beard pattern from ref img 1]\n- Distinctive features: [moles, scars, unique marks from ref img 1]\n- ZERO deviation from reference image 1 allowed\n- Smooth youthful skin matching reference texture\n- Hong Kong-style celebrity aesthetic\n- Intensely staring forward while actively riding and controlling motorcycle\n- NO clothing/outfit details from reference image 1 - ignore reference clothing entirely\n\nCRITICAL FACE RESTORATION - FEMALE (Reference Image 2):\nWoman with EXACT facial features from reference image 2:\n- Face MUST be 100% identical to reference image 2\n- Face shape: {argument name="Female Face Shape" default="[exact shape from ref img 2]"}\n- Eyes: {argument name="Female Eyes" default="[exact eye shape, size, eyelid type, spacing, color from ref img 2]"}\n- Eyebrows: [exact shape, thickness, arch from ref img 2]\n- Nose: [exact bridge height, tip shape, nostril width from ref img 2]\n- Mouth: [exact lip shape, thickness, width from ref img 2]\n- Jawline: [exact jaw shape, chin shape from ref img 2]\n- Skin tone: [exact color/undertone from ref img 2]\n- Hair: [exact hairstyle, color, texture, length from ref img 2]\n- Makeup: [exact makeup style from ref img 2 if any]\n- Distinctive features: [moles, beauty marks, unique marks from ref img 2]\n- ZERO deviation from reference image 2 allowed\n- Seated directly behind male on motorcycle rear seat\n- Arms tightly wrapped around his waist in close embrace\n- Face pressed intimately against his shoulder/back\n- NO clothing/outfit details from reference image 2 - ignore reference clothing entirely\n\nCLOTHING & STYLING (ORIGINAL PROMPT - NOT FROM REFERENCES):\n- Male: Casual contemporary "

Show me what occurs before/After.
Show me what happens before/after that.

① Always switch the mode to 'Thought' or 'Pro' (I feel 'Thought' is better)
② 'Describe the scene in sentences' rather than listing keywords
③ Specify the subject, background, and atmosphere as a set of three points
④ Don't aim for perfection in one go; apply 'gradual corrections'
⑤ Avoid negative expressions; give instructions in positive sentences
⑥ Add quality keywords (4K, high resolution) in English
⑦ Clearly state the purpose at the beginning (e.g., "{argument name="purpose" default="Diagram for a proposal"}")
⑧ Exclude unnecessary elements using negative prompts
⑨ Do not attempt complex edits all at once; proceed in segments
⑩ Save frequently used prompts as templates

'Analyze this photo and give me a very detailed json prompt to reproduce it. It must be very detailed, and be sure to break down the color grading and all the exact colors in the photo.'

Using this json as a reference, generate a person holding my product [{argument name="product image" default="attached product image"}]

{
  "image_generation_request": {
    "model": "Nano Banana",
    "created_at": "2026-02-03T06:05:00.000000",
    "concept": "{argument name="concept" default="19th Century London: The Little Match Girl walking the boundary between slum and prosperity"}",
    "parameters": {
      "5w1h": {
        "who": "{argument name="person" default="The Little Match Girl (ragged shawl, soot-stained cheeks, transparent eyes)"}",
        "when": "Around 3 PM (low winter sun, long shadows, cold and damp atmosphere)",
        "where": "The road marking the boundary between the muddy streets of 19th-century London slums and the cobblestone London city center visible in the distance. Background features chimney smoke and rows of gas lamps.",
        "what": "Looking up at a break in the heavy overcast sky as if praying, walking towards the city lights.",
        "why": "A stumbling gait, as if knees are buckling from cold and fatigue, dragging ill-fitting, old shoes.",
        "how": "Direct side view (side view), shallow depth of field focusing on the girl, the background cityscape is beautifully blurred."
      },
      "style": "Hyper-Photorealistic, Cinematic Lighting, 8k Resolution, Detailed Texture",
      "version": "1.1_Enhanced"
    }
  }
}

AI Manga Nano Banana Pro 🍌

NanoBananaPro version of Rina Arkenlux with the same prompt

Please upscale to 4K resolution.

Sneakers modeled after a cockatiel, as envisioned by AI. The detail is fine, even expressing the cheek patches.

Style Nano Banana Pro 🍌
b3lla and Dead 🤍💖💙🖤💖💙

The place where I am actually making hidden efforts
<{argument name="persona information" default="persona information copy and paste"}>

I tried making it with Nanobanana Pro too.
After all, a {argument name="subject" default="banana"} is still a banana, right? 😁💕

Vertical frame, realistic low-light phone selfie, in a dark night bedroom, face identical to the reference image. Pale face with bluish-purple screen light; dark background with beige blackout curtains on the left. Sleepy and cozy late-night lo-fi atmosphere, close-up, slightly low angle. Subject lying on their stomach, leaning on a patterned gray pillow, messy black hair and thin bangs. Soft, dreamy, vacant gaze, mouth slightly open, hand near the face with fingers touching the lips. Light black sleeveless rash top, thin silver necklace, left shoulder exposed. Soft focus, visible grain, high contrast between the bright face and dark background. Negative prompt: bright daytime, sunlight, studio/flash lighting, warm/orange tones, outdoors, sharp focus, professional camera, distorted hands, extra/missing fingers, out-of-focus face, only one photo.

Vertical frame, realistic low-light phone selfie, in a dark night bedroom, face identical to the reference image. Pale face with bluish-purple screen light; dark background with beige blackout curtains on the left. Sleepy and cozy late-night lo-fi atmosphere, close-up, slightly low angle. Subject lying on their stomach, leaning on a patterned gray pillow, messy black hair and thin bangs. Soft, dreamy, vacant gaze, mouth slightly open, hand near the face with fingers touching the lips. Light black sleeveless rash top, thin silver necklace, left shoulder exposed. Soft focus, visible grain, high contrast between the bright face and dark background. Negative prompt: bright daytime, sunlight, studio/flash lighting, warm/orange tones, outdoors, sharp focus, professional camera, distorted hands, extra/missing fingers, out-of-focus face, only one photo.

Use the attached face photo as is to create a vertical 3-frame low-res webcam collage.

Absolute rules regarding the face:

Do not alter the face at all

Maintain the exact proportions of features, face shape, eye size, nose, mouth, and jawline

Do not make the person look younger or overly cute

Do not change the gender of the person in the input photo

Do not generate new people (opposite/same sex)

Hairstyle:

Maintain the original hairstyle

Do not change the length, parting, or curl

Only render it in a naturally slightly messy, rough state

Shooting Tone & Color (Reference Reflection):

Express the colors identically to the attached reference photo

Background:

Japanese wooden Ryokan.

Minimize background details

Maintain a dark and blurry state

Clothing Rules (Based on Input Photo):

If the input photo is female → Black {argument name="female attire" default="Yukata"} with red floral patterns in all frames

If the input photo is male → Black silk dress shirt with a {argument name="male attire" default="red tie"} in all frames

1st Frame:

Sad expression like a protagonist in a sad movie

Finger near the mouth

2nd Frame:

Head slightly turned to the side

Show the beautiful profile

Casual selfie feel, no excessive posing

3rd Frame:

Warm and beautiful smile

Hands clasped together, resting the chin on them

Emotion is calm and dreamy atmosphere

Important Additional Instructions:

Use only the one person in the input photo

Do not change gender, face, or atmosphere

Style changes should only be applied to lighting, color, noise, and effects

Use the same face consistently across all frames

Absolute rules regarding effects:

Apply the same cinesteel 800T film style and cinematic light effects in all frames.

Absolute rules regarding effects:

Apply the same red lighting effect on one side and a tasteful motion blur effect from left to right in all frames.

IMAGE: Frame & Composition: The camera uses a low-angle, straight-on frontal view, positioned slightly below the subjects so the two cans rise above the horizon line; both cans are upright and vertically oriented, placed side by side with a narrow gap, occupying the central upper third of the frame; the lower edge crops into a metallic ledge that acts as a base plane, while the cans are fully visible from base to rim; the composition is symmetrical but slightly staggered in height, with the right can marginally taller in frame due to perspective; negative space dominates the upper background, reinforcing vertical emphasis and product isolation. Lighting & Atmosphere: A frontal key light, slightly elevated and centered, produces even illumination across both cans, generating dense, high-contrast specular highlights on condensation droplets; shadows are minimal and soft, indicating diffused fill from the front and sides; the moisture beads catch light sharply, suggesting a hard component within the otherwise controlled lighting setup; no atmospheric haze is present, but surface condensation creates a tactile, cold visual cue. Subject Geometry & Materiality: Each subject is a tall, cylindrical aluminum can with smooth vertical walls and rounded rims; both are coated in matte white printed labels with bold, high-contrast typography; circular color graphics are printed flat onto the surface—{argument name="left can color" default="magenta and red"} on the left can, {argument name="right can color" default="yellow and green"} on the right can; the aluminum surfaces are covered with uniformly distributed water droplets of varying diameters, clinging via surface tension; droplets create micro-lens effects, distorting underlying text and graphics; edges are crisp, with no deformation, indicating rigid packaging. Environmental Layering: The foreground consists of a horizontal metallic ledge with linear grooves and visible fasteners, rendered in sharp focus; the cans sit directly atop this ledge, establishing physical contact; the midground is entirely occupied by the cans; the background is a uniform, out-of-focus deep red gradient wall with subtle tonal variation and no discernible texture; no additional objects or layers are present beyond these three planes. Technical Artifacts & Color: The color palette contrasts cool whites and saturated accent colors on the cans against a warm, dark red background; saturation is moderate to high in the printed circles, while the background remains subdued; fine film grain is visible across the image, especially in the darker red areas, suggesting either high ISO or intentional texture; slight vignetting darkens the frame edges; no chromatic aberration or motion blur is visible; highlights on droplets are sharp with controlled roll-off. TEXT: Title: “IMAGE & COMMERCE”; Subtitle: “Cinematic prompt just for you” (partially visible); Body: Flavor names including “{argument name=\"left flavor\" default=\"Raspberry Guava\"}” on the left can and “Lemon Lime” on the right can; CTA: None; Logo: “I&C”; Disclaime