✦PROMPT ATLASIMAGE PROMPT · VISUAL PROMPT ATLASGitHub ↗中文

零售店高位监控视角的粗颗粒抓拍

Read the complete source prompt and attribution. Titles and source text retain their original language.

Nano Banana (specific version not disclosed)Text onlyCinematic moments
零售店高位监控视角的粗颗粒抓拍 · Source example
Source example paired with this prompt; not regenerated by this site.
Image credit: @xmliisu.Previews were resized and converted to WebP; they were not regenerated by this site.

Complete prompt

MarkdownJSON
{
  "image_description": {
    "title": "Surveillance Feed: Defiant Subject in Retail Shop",
    "aspect_ratio": "4:5",
    "mood": "Raw, gritty, confrontational, authentic"
  },
  "visual_elements": {
    "subject": {
      "framing": "Centered from mid-torso upward",
      "pose": "Head tilted back looking up at camera, relaxed yet defiant posture",
      "action": "Hand raised with middle finger extended (silhouette, ghosted by motion)",
      "facial_features": "Largely obscured by blur, mouth open with tongue faintly visible",
      "apparel": "Dark oversized sunglasses reflecting ambient light"
    },
    "environment": {
      "location": "Cramped retail shop interior",
      "foreground": "Cluttered checkout counter, papers, white shopping bag with red rope handles",
      "background": "Densely packed shelves with small items, souvenirs, and figurines (abstracted by low resolution)"
    }
  },
  "technical_specifications": {
    "camera_perspective": "High-mounted, steep downward angle, top-down CCTV view",
    "lens_distortion": "Subtle fisheye warping at frame edges",
    "lighting": "Harsh flat fluorescent, blown highlights, dull shadows",
    "color_grading": "Cool green-blue cast, uneven color reproduction, visible banding, reduced dynamic range"
  },
  "image_fidelity": {
    "quality": "Intentionally degraded, low-fidelity",
    "artifacts": [
      "Strong motion blur",
      "Digital smearing",
      "Compression artifacts",
      "Heavy noise",
      "Scan lines"
    ],
    "sharpness": "Low perceived sharpness, distinct details stretched and indistinct"
  },
  "full_prompt_text": "A heavily distorted, low-fidelity surveillance-style image depicts the Subject standing behind a cramped retail checkout counter inside a cluttered shop, captured from a high-mounted camera angled steeply downward in a top-down CCTV perspective. The image quality is intentionally degraded, with strong motion blur, digital smearing, compression artifacts, heavy noise, scan lines, and subtle fisheye distortion warping the frame edges, making fine details indistinct and stretched. The Subject is centered from mid-torso upward, looking up toward the camera with the head tilted back; facial features are largely obscured by blur and artifacts, though dark oversized sunglasses dominate the face, reflecting ambient light, and the mouth appears open with the tongue faintly visible. One hand is raised toward the camera with the middle finger extended, clearly readable in silhouette but softened and ghosted by motion and low clarity, conveying a relaxed yet defiant posture. The foreground checkout counter is cluttered with papers and a white shopping bag with red rope handles, while the background shelves are densely packed with small items, souvenirs, and figurines that blend into abstract shapes due to low resolution and noise. Harsh, flat fluorescent lighting produces blown highlights, dull shadows, uneven color reproduction, and a cool green-blue color cast with visible banding and reduced dynamic range. Despite an effectively deep depth of field, perceived sharpness remains low, reinforcing a raw, gritty, confrontational mood that emphasizes the authenticity of an unpolished, unenhanced surveillance feed in a vertical 4:5 aspect ratio"
}

Make it your own

Start from the source text. Add your own authorized reference for a specific person, logo or product when needed.

Change one element at a time. Keep useful composition and lighting, and use your own reference material when required.

Structure: [Subject] + [Composition] + [Light] + [Material or style] + [Text or details to preserve] + [Aspect ratio]

Open the gallery workbench ↗

Sources & attribution

Prompt author
@xmliisu
Original source
Original post / source page ↗
Source collection
NanoBanana Trending Prompts · MeiGen.ai
Model
Nano Banana (specific version not disclosed) (source label; not a current-version claim)
Source date
2026-01-26 · Original-post date recorded by the dataset; metric capture time is unknown.
Snapshot
2026-10-20
Evidence
773 archived likes / 93,964 archived views.Dataset archive; capture time unknown and live values not independently verified.
Content rights
CC BY 4.0 as declared by the source; attribution, exceptions and third-party rights apply..Retain attribution and source links. Upstream exceptions and third-party rights apply.

Examples were not regenerated by this site. Results vary with tools, model versions, references and editing rounds.Sources & methods

More examples: Cinematic moments